url stringlengths 11 2.25k | text stringlengths 88 50k | ts timestamp[s]date 2026-01-13 08:47:33 2026-01-13 09:30:40 |
|---|---|---|
https://developers.reddit.com/apps/trendingtattler | Trending Tattler | Reddit for Developers Readme Trending Tattler A Reddit Community App to alert subreddit moderators when a post hits a high traffic feed (i.e. /r/all, /r/popular). This can help you prepare for the extra workload of moderating a post that is liable to get busy fast. The app runs on a schedule, every 30 minutes. It checks the top posts in the high traffic feeds (configurable), and if there are any present from the subreddit the app is installed in it, will take action. Action will only be taken on a post once every three days, so if a post remains in the high traffic feed for a long period of time only one alert will be sent. Detection options You can choose to monitor /r/all, /r/popular, or both. You can choose how many posts to look back in these feeds, the default is 100 but you can configure the app to look back up to 200 posts. Action options More than one action option can be selected at a time. If no options are set at all, the app will not check high traffic feeds until one is enabled. Modmail If enabled, this will send a modmail with details of each post that has been newly found in the high traffic feed. Send Discord or Slack Notification If enabled, this will send a message to the Discord webhook specified. To learn how to create a Discord webhook, follow this guide , and use the "Copy Webhook URL" button within Discord and paste the URL into this app's configuration screen. For Slack, see this guide . If Suppress Embeds is turned off, Discord may include an embed with a preview of the post. You can force this off if you wish with this option. Report If enabled, this will report the post, making it obvious in the modqueue that the post has hit the high traffic feed. Flair This will set a flair on the post. This may be useful for alerting your users, but can also allow you to react to trending posts differently in automod rules or other bots that you may have running. If you want to use this setting, I recommend using one of these options: Flair text on its own (applies the text with default cosmetic settings) Flair text and CSS class combined (applies the text using the cosmetic settings of the CSS class) Flair text and flair template (applies the text using the cosmetic settings for the flair template) Flair template on its own (uses the flair text from the template) Sticky Comment This gives you the option to create a sticky comment on the post as a "welcome" to people who might need a reminder of your subreddit's rules. You can choose to sticky a new comment regardless of whether there is one already present, or choose to only sticky a new comment if there's not one there already. Crowd Control This gives you the option to set Crowd Control to the level of your choosing. If this is turned on, Crowd Control's level will be set to this value, even if Crowd Control is set. Test Mode Test Mode takes a random post on your subreddit and treats it as if it is trending in /r/testing, and alerts based on the option configured. This allows you to test your configuration to ensure that the options are set up to your liking. To trigger Test Mode, choose the "..." context menu at the subreddit level, and choose "Test Trending Tattler". The appropriate alerting actions should take place nearly immediately. If you have actions configured that are visible on the subreddit (post flairs, sticky comments, etc.) you may wish to test those on a private testing subreddit instead on the main subreddit. Note: Test Mode is not available on Old Reddit or third-party Reddit clients due to limitations of Devvit. You will need to use the official Reddit app, or a more modern desktop experience. Recent changes v1.7 Add option (on by default) to lock sticky comments made by the app v1.6 Add ability to set Crowd Control on posts that hit trending feeds v1.5.4 Add feature to allow placeholder for feed name(s) in sticky comments and flair text v1.5.3 Fixed a security vulnerability relating to menu items v1.5.2 Modmail notifications now go to inbox v1.5.1 Add "Test Mode" to allow mods to test out config before a post actually hits a trending feed Add support for limiting trending feed detection to specific locations Code improvements v1.4.3 fixes an issue with Discord webhook support v1.4.2 adds Slack webhook support. v1.3 Adds the ability to suppress embeds in Discord notifications, and adds "I am a bot" boilerplate text on all comments made by the app if that option is in use. v1.2 Added the ability to add a sticky comment on trending posts v1.1 Added Discord notifications Source code Trending Tattler is open source. You can find it on Github here . About this app fsv Creator App identifier trendingtattler Version 1.7.0 Send feedback Terms and conditions Privacy policy Company Reddit, Inc. Reddit for Business Careers Press Contact Blog Community Reddit.com Reddit for Community Content Policy Help Center Moderator Code of Conduct Privacy & Safety Privacy Policy User agreement Transparency Report r/redditsecurity Other Terms and Policies Copyright 2026 Reddit Inc. All rights reserved. Company Reddit, Inc. Reddit for Business Careers Press Contact Blog Community Reddit.com Reddit for Community Content Policy Help Center Moderator Code of Conduct Privacy & Safety Privacy Policy User agreement Transparency Report r/redditsecurity Other Terms and Policies Copyright 2026 Reddit Inc. All rights reserved. | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netsec/comments/1pqfoqo/how_we_pwned_x_twitter_vercel_cursor_discord_and/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://replit.com/usecases/designers | Replit for Designers Agent Products Agent Design Database Publish Security Integrations Mobile For Work Teams Replit for teams to build together Enterprise Replit with Enterprise-grade security & controls Use Cases Business Apps Rapid Prototyping Roles Enterprise PM Designers Operations Software Developers Small Businesses SMB owners Founders Resources Get Started Docs Community Expert Network Inspiration Customer Stories Gallery Blog News Pricing Careers Agent Contact sales Log in Sign up Products For Work Resources Pricing Careers Contact sales Log in Start building Th e f uture o f desi g n is h ere Replit empowers anyone with an idea to become a creator, while giving professional designers the freedom to creatively explore and build — without being held back by code or the limitations of design tools. Start now Vision to reality faster Turn any creative concept into an interactive, fully functional app with Replit in minutes — simply upload a mock or describe your idea. Then, create limitless variations without ever having to write a line of code. At every stage of your journey If you’re searching for new ideas, Replit Agent can spark inspiration from a blank canvas — or bring existing sketches to life if you already have a clear vision in mind. Iterate without the back and forth. Replit allows designers to play and iterate directly in the app or website, zero coding experience needed, allowing you to visualize and experiment with system level changes without having to wait for engineering resources. Why designers are switching to Replit Andrew Wilkinson Co-founder of Tiny (Dribbble, Serato, Letterboxd, AeroPress, and 35+ other companies) "I've tried them all... For a while it felt like the others created more beautiful output, but ultimately they are all converging and Replit feels like the perfect combination of just enough access to technical details/coding/deployment in addition to being insanely fast and outputting beautiful design" Mo Hassan Design Leader "As a product designer, I also appreciate Replit’s clean and addictive UI, it’s so seamless that I rarely go more than a day or two without using it. Honestly, if I could, I’d spend all day on the platform." Pietro Schirano CO-FOUNDER, EVERART "Replit extrapolates complex problems and takes care of all the mundane parts of coding." Unleash your creative genius Real time preview Agent turns static designs into interactive apps or websites in a matter of minutes, allowing you to validate ideas faster. Dynamic design systems Replit creates fully-functional, consistent systems that actually work across your entire application. Edit just by asking Instead of manually adjusting properties, just tell Agent what you want changed and watch it happen immediately. Integrated best practices The Agent integrates design best practices, open-source UI libraries, and accessibility standards — freeing you to concentrate solely on your creative vision. Collaborative design partner Replit Agent supplements your graphics, UI/UX, copy, web design, front-end, and back-end skills, letting you focus on pushing boundaries further than before. Truly interactive prototypes See your designs transform in real-time to functional products while Agent handles all technical implementation, eliminating the gap between concept and reality. From sketch to working app faster than ever 1 Share your designs 2 Watch it become real 3 Refine through interaction St a rt creati n g n o w Start building Handy Links About us Vibe Coding 101 Help How to guides Import from GitHub Status Additional resources Brand kit Partnerships Legal Terms of service Commercial agreement Privacy Subprocessors DPA Report abuse Connect X / Twitter Tiktok Facebook Instagram Linkedin Scroll to top All rights reserved. Copyright © 2026 Replit, Inc. | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netsec/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netsec/?f=flair_name%3A%22Cryptography%22 | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://store.steampowered.com/curator/4771848-r-pcmasterrace-Group/ | Steam Curator: /r/pcmasterrace Group Login Store Home Discovery Queue Wishlist Points Shop News Charts Community Home Discussions Workshop Market Broadcasts About Support Change language Get the Steam Mobile App View desktop website © Valve Corporation. All rights reserved. All trademarks are property of their respective owners in the US and other countries. Privacy Policy | Legal | Accessibility | Steam Subscriber Agreement | Refunds STORE Home Discovery Queue Wishlist Points Shop News Charts COMMUNITY Home Discussions Workshop Market Broadcasts About SUPPORT Install Steam login | language 简体中文 (Simplified Chinese) 繁體中文 (Traditional Chinese) 日本語 (Japanese) 한국어 (Korean) ไทย (Thai) Български (Bulgarian) Čeština (Czech) Dansk (Danish) Deutsch (German) Español - España (Spanish - Spain) Español - Latinoamérica (Spanish - Latin America) Ελληνικά (Greek) Français (French) Italiano (Italian) Bahasa Indonesia (Indonesian) Magyar (Hungarian) Nederlands (Dutch) Norsk (Norwegian) Polski (Polish) Português (Portuguese - Portugal) Português - Brasil (Portuguese - Brazil) Română (Romanian) Русский (Russian) Suomi (Finnish) Svenska (Swedish) Türkçe (Turkish) Tiếng Việt (Vietnamese) Українська (Ukrainian) Report a translation problem /r/pcmasterrace Group PCMR Website Following Follow 519,043 Followers Ignored Featured Lists About --> The official PC MASTER RACE Curator, where an experienced and dedicated team recommends the best PC Games available on Steam. Ignore this curator Remove ignore state Report this curator Recent reviews ₩ 58,900 Recommended 2 December, 2025 “Established itself as THE extraction shooter to play in 2025. Action packed and addictive with friends (and even alone). A great multiplayer experience. It features DLSS 4 w/ Multi Frame Gen & Reflex.” ₩ 32,000 Recommended 26 November, 2025 “In the style of classics like Wolf Among Us and Walking Dead, Manage and dispatch the right heroes for the job on a mission to become one again yourself. A great story with a fun cast of characters.” ₩ 79,800 Recommended 3 November, 2025 “Obsidian's RPG chops shine again. Good writing and choice-based mechanics that meet improved gunplay, abilities, perks, and traits/flaws. This is the game that Outer Worlds 1 should have been.” ₩ 16,500 Recommended 3 November, 2025 “An addictive and well-priced roguelike. It has elements of Arkanoid mixed with light base building, and it makes you want to do just another run for treasure in the pit that used to be Ballbylon. ” ₩ 80,000 Recommended 10 October, 2025 “A return to form for one of the great multiplayer shooters. Has NVIDIA DLSS 4, Multi Frame Gen & Reflex, feels hectic, chaotic, explosive, and fun, at a scale that only Battlefield seems to get right.” ₩ 49,800 Recommended 6 October, 2025 “A standalone Elden Ring DLC. Many have tried to emulate the genre, but no one does it quite like FromSoftware. An unapologetic, excruciatingly hard, beautiful piece of art, just like the main game.” ₩ 87,700 Recommended 6 October, 2025 “The remake of one of the great horror games of all time is a masterpiece in its own right. If you're even remotely interested in the genre and have never played this, make sure you do so.” ₩ 32,000 Recommended 29 September, 2025 “Figh. Die. Become stronger. Get further. Start over. It uses the same basics as its brilliant predecessor and seems to improve on it in most fronts. A beautiful, frantic, addictive, and fun roguelike.” ₩ 21,500 Recommended 12 September, 2025 “Both this and the original are amazing games, which you prefer will probably depend on if you prefer the platform and exploration aspects (Original) or the combat and much harder difficulty (Silksong)” ₩ 16,500 Recommended 12 August, 2025 “Vibey but not overly simplistic fishing game that nails the "chill" aspect. Great candidate for second screen idle play while working (yes, we know you do it). Also you can pet the dogs, which is nice” Recent Reviews Top Sellers New Releases Discounts Review Type All 0 Recommended Informational 30 Not Recommended 7 Filter to All 2680 Action 259 Adventure 223 Indie 157 RPG 108 Strategy 73 Add a tag Narrow by preferences Hide ignored items Hide items in my library Results may exclude some products based on your content or language preferences ₩ 58,900 Recommended 2 December, 2025 Established itself as THE extraction shooter to play in 2025. Action packed and addictive with friends (and even alone). A great multiplayer experience. It features DLSS 4 w/ Multi Frame Gen & Reflex. ₩ 32,000 Recommended 26 November, 2025 In the style of classics like Wolf Among Us and Walking Dead, Manage and dispatch the right heroes for the job on a mission to become one again yourself. A great story with a fun cast of characters. ₩ 84,800 Informational 19 November, 2025 Despite the launch pains, what Borderlands fans love is back: the self aware humor, paired with very fun combat, gunplay and looting. It features DLSS 4 w/ Multi Frame Gen (particularly handy here). ₩ 69,800 Not Recommended 11 November, 2025 The match engine was noticeably improved compared to FM24, but the UI, where players spend 80% of their time, is noticeably worse. As is, FM24 with a free database mod is superior to FM26. ₩ 79,800 Recommended 3 November, 2025 Obsidian's RPG chops shine again. Good writing and choice-based mechanics that meet improved gunplay, abilities, perks, and traits/flaws. This is the game that Outer Worlds 1 should have been. Live ₩ 16,500 Recommended 3 November, 2025 An addictive and well-priced roguelike. It has elements of Arkanoid mixed with light base building, and it makes you want to do just another run for treasure in the pit that used to be Ballbylon. ₩ 66,000 Not Recommended 23 October, 2025 A generic first-person open-world game with a Vampire theme. It lacks the RPG mechanics that fans of the series crave, and is overall a somewhat mediocre attempt to create a Bloodlines game. ₩ 11,000 Informational 22 October, 2025 Cheap, fast, rewarding, and runs on a potato PC. The kind of game you play to have some mindless fun for 30 minutes, then move on, then do it again the next day. It would be even better with co-op. ₩ 80,000 Recommended 10 October, 2025 A return to form for one of the great multiplayer shooters. Has NVIDIA DLSS 4, Multi Frame Gen & Reflex, feels hectic, chaotic, explosive, and fun, at a scale that only Battlefield seems to get right. ₩ 49,800 Recommended 6 October, 2025 A standalone Elden Ring DLC. Many have tried to emulate the genre, but no one does it quite like FromSoftware. An unapologetic, excruciatingly hard, beautiful piece of art, just like the main game. No results found < > Showing 1 - 10 of 418 results Per page: 10 25 50 100 Loading more content... © 2026 Valve Corporation. All rights reserved. All trademarks are property of their respective owners in the US and other countries. VAT included in all prices where applicable. Privacy Policy | Legal | Accessibility | Steam Subscriber Agreement | Refunds | Cookies View mobile website About Valve | Jobs | Steamworks | Steam Distribution | Support | Gift Cards | | | | 2026-01-13T08:47:52 |
https://twitter.com/_yoav_ | JavaScript is not available. We’ve detected that JavaScript is disabled in this browser. Please enable JavaScript or switch to a supported browser to continue using x.com. You can see a list of supported browsers in our Help Center. Help Center Terms of Service Privacy Policy Cookie Policy Imprint Ads info © 2026 X Corp. Something went wrong, but don’t fret — let’s give it another shot. Try again Some privacy related extensions may cause issues on x.com. Please disable them and try again. | 2026-01-13T08:47:52 |
https://www.reddit.com/r/technology/best/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://claude.com/claude-in-slack | Claude in Slack | Claude -------> Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Claude in Slack Claude in Slack Explore here Ask questions about this page Copy as markdown Claude and Slack, better together Draft content, do quick research, or prep for meetings—right where you’re already working. Add to Slack Add to Slack Add to Slack Bring Claude to Slack Ask your Slack workspace admin to approve the Claude app from the Slack App Marketplace , then use your existing Claude account to get started. Add to Slack Add to Slack Add to Slack Send a direct message Start a private conversation with @Claude to get one-on-one help on research, writing, or analysis. Mention Claude in any thread Claude will draft a response based on the conversation, which you can review and approve before sharing with the group. Get help wherever you are Chat with Claude in the AI assistant header from any channel or conversation. Collaborate on code with Claude Claude Code users can ask @Claude to handle coding tasks and it will run them remotely, providing updates when completed Perfect for your daily workflows Add to Slack Add to Slack Add to Slack Summarize threads Ask Claude to explain complex concepts or break down lengthy threads. Create content Draft emails, documentation, and proposals in your Claude DM, then share directly in relevant channels. Prep for meetings Analyze documents and prepare talking points before joining calls. Do quick research Get instant answers about industry trends, technical concepts, or company information. Kick off coding tasks Debug errors, get answers about code, and kick off async tasks with Claude Code . Claude Code and Slack Delegate tasks to Claude Code directly from Slack. Now in beta as a research preview. Read more Read more Read more Prev Prev Next Next Bring Slack to Claude For complex tasks that need full context, use the Slack connector in Claude. Claude can search your channels, messages, and files to provide insights. Get the Slack connector Get the Slack connector Get the Slack connector Private by design See privacy policy See privacy policy See privacy policy Visit Trust Center Visit Trust Center Visit Trust Center When you interact with Claude, it only has access to Slack messages you can see Your conversations with Claude in Slack follow your organization’s Slack retention policies and permissions You can delete your conversations any time by disconnecting your account FAQ What data will Anthropic have access to? When you prompt Claude in Slack, Anthropic gets access to your prompt and contextually relevant Slack conversation data that you can see. Anthropic retains your Slack conversation data for as long as reasonably necessary for the purposes and criteria outlined in our Privacy Policy or other agreement you’ve entered with Anthropic. Users and administrators can disconnect the Claude app at any time. How will my data be used? Anthropic retains your Slack conversation data and personal data for as long as reasonably necessary for the purposes outlined in our Privacy Policy or other agreement you’ve entered with Anthropic. Anthropic doesn’t use conversations you have with Claude in Slack to train models. How much does it cost to include Claude in the Slack app? Anthropic doesn’t charge anything additional to access the Claude App for Slack, but ordinary pricing and usage limits apply. Note: The Claude app for Slack is currently only available to install for paid Slack plans. What are the known limitations of Claude in the Slack app? Research, file creation and editing, and extended thinking will not be available for Claude in Slack to start. Remember Claude can make mistakes, so please double-check responses. How should bugs and feedback be reported? Thank you for helping us improve Claude. Please send feedback and bugs through our support center . What do I need to know to get started? Claude in Slack is available for paid Slack plans. A Slack admin must first approve the Claude app for their organization from the Slack App Marketplace in order for their employees to access the app from their workspace. From there, individuals can authenticate with their Claude login information. You must have a Team or Enterprise plan to use the Slack connector and bring Slack context to Claude. Before you can set up the Slack connector, you’ll need to install the Claude in Slack app. How does Claude in the Slack app work with Claude Code? When Claude in the Slack app detects that you’re asking about a coding-related task, it will automatically relay the request to Claude Code to start a remote session on claude.com/code . This feature is available to users who also have access to Claude Code on the web. Claude and Slack When you work with Claude in Slack, you get all the capabilities you already use—web search, document analysis, and your existing connections. Read more Read more Read more Prev Prev Next Next Homepage Homepage Next Next Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Write Button Text Button Text Learn Button Text Button Text Code Button Text Button Text Write Help me develop a unique voice for an audience Hi Claude! Could you help me develop a unique voice for an audience? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Improve my writing style Hi Claude! Could you improve my writing style? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Brainstorm creative ideas Hi Claude! Could you brainstorm creative ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Learn Explain a complex topic simply Hi Claude! Could you explain a complex topic simply? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Help me make sense of these ideas Hi Claude! Could you help me make sense of these ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Prepare for an exam or interview Hi Claude! Could you prepare for an exam or interview? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Code Explain a programming concept Hi Claude! Could you explain a programming concept? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Look over my code and give me tips Hi Claude! Could you look over my code and give me tips? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Vibe code with me Hi Claude! Could you vibe code with me? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! More Write case studies This is another test Write grant proposals Hi Claude! Could you write grant proposals? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to — like Google Drive, web search, etc. — if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can - an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Write video scripts this is a test Anthropic Anthropic © [year] Anthropic PBC Products Claude Claude Claude Claude Code Claude Code Claude Code Max plan Max plan Max plan Team plan Team plan Team plan Enterprise plan Enterprise plan Enterprise plan Download app Download app Download app Pricing Pricing Pricing Log in Log in Log in Features Claude in Chrome Claude in Chrome Claude in Chrome Claude in Slack Claude in Slack Claude in Slack Claude in Excel Claude in Excel Claude in Excel Skills Skills Skills Models Opus Opus Opus Sonnet Sonnet Sonnet Haiku Haiku Haiku Solutions AI agents AI agents AI agents Code modernization Code modernization Code modernization Coding Coding Coding Customer support Customer support Customer support Education Education Education Financial services Financial services Financial services Government Government Government Healthcare Healthcare Healthcare Life sciences Life sciences Life sciences Nonprofits Nonprofits Nonprofits Claude Developer Platform Overview Overview Overview Developer docs Developer docs Developer docs Pricing Pricing Pricing Regional Compliance Regional Compliance Regional Compliance Amazon Bedrock Amazon Bedrock Amazon Bedrock Google Cloud’s Vertex AI Google Cloud’s Vertex AI Google Cloud’s Vertex AI Console login Console login Console login Learn Blog Blog Blog Claude partner network Claude partner network Claude partner network Courses Courses Courses Connectors Connectors Connectors Customer stories Customer stories Customer stories Engineering at Anthropic Engineering at Anthropic Engineering at Anthropic Events Events Events Powered by Claude Powered by Claude Powered by Claude Service partners Service partners Service partners Startups program Startups program Startups program Tutorials Tutorials Tutorials Use cases Use cases Use cases Company Anthropic Anthropic Anthropic Careers Careers Careers Economic Futures Economic Futures Economic Futures Research Research Research News News News Responsible Scaling Policy Responsible Scaling Policy Responsible Scaling Policy Security and compliance Security and compliance Security and compliance Transparency Transparency Transparency Help and security Availability Availability Availability Status Status Status Support center Support center Support center Terms and policies Privacy choices Cookie settings We use cookies to deliver and improve our services, analyze site usage, and if you agree, to customize or personalize your experience and market our services to you. You can read our Cookie Policy here . Customize cookie settings Reject all cookies Accept all cookies Necessary Enables security and basic functionality. Required Analytics Enables tracking of site performance. Off Marketing Enables ads personalization and tracking. Off Save preferences Privacy policy Privacy policy Privacy policy Responsible disclosure policy Responsible disclosure policy Responsible disclosure policy Terms of service: Commercial Terms of service: Commercial Terms of service: Commercial Terms of service: Consumer Terms of service: Consumer Terms of service: Consumer Usage policy Usage policy Usage policy x.com x.com LinkedIn LinkedIn YouTube YouTube Instagram Instagram English (US) English (US) 日本語 (Japan) Deutsch (Germany) Français (France) 한국어 (South Korea) | 2026-01-13T08:47:52 |
https://replit.com/usecases/operations | Replit for Operations Agent Products Agent Design Database Publish Security Integrations Mobile For Work Teams Replit for teams to build together Enterprise Replit with Enterprise-grade security & controls Use Cases Business Apps Rapid Prototyping Roles Enterprise PM Designers Operations Software Developers Small Businesses SMB owners Founders Resources Get Started Docs Community Expert Network Inspiration Customer Stories Gallery Blog News Pricing Careers Agent Contact sales Log in Sign up Products For Work Resources Pricing Careers Contact sales Log in Start building Buil d ex a ctly w hat y our te a m nee d s, wit h out b ottlenecks Go from ‘wishlist’ to ‘working tool’ in minutes, not months. Build custom dashboards, tracking tools, and automations that perfectly fit your team needs with Replit Agent — no code, waiting on developers, or overpriced solutions required. Start now Go from idea to working solution, fast Build any integration or tool, exactly how you need it Feed Replit Agent API documentation or describe what you need in plain text — then watch as it creates custom tools and integrations that perfectly match your requirements without writing a single line of code. Automate entire workflows that save time and budget Replace expensive per-task tools like Zapier and Make with your own custom automations, saving hundreds monthly while unlocking new levels of productivity for your teams. Create custom dashboards to track anything and unlock new insights Transform CSVs, PDFs, and spreadsheets into powerful visualization tools that reveal patterns and metrics your team has never been able to access before. Deploy with enterprise-grade security and control Keep sensitive operations protected with private deployments, role-based authentication, and secure secrets management for all your API connections. From "that's not possible" to "I built it myself this afternoon" Build with Replit Agent to create from scratch, then refine to make quick edits — giving your team the power to turn any idea into working tools lightning-fast. How it works 1 Describe what you need Tell Replit Agent the tool, integration, or automation you want to create in simple, everyday language 2 Replit Agent builds it for you Watch as Agent generates a complete, custom solution in minutes 3 Refine and iterate Make quick improvements and bug fixes 4 Connect your data Easily integrate with your existing systems and data sources 5 Deploy instantly Share with your team and start using your new tool immediately Why operations teams love Replit Operations teams are transforming backlogs into breakthroughs — building their best ideas without technical bottlenecks while slashing costs and timelines. 90% faster implementation Build and deploy internal tools in hours instead of weeks or months of waiting for engineering resources. 40-60% cost savings Replace multiple SaaS subscriptions with custom-built tools that do exactly what you need. Unlimited customization Finally implement all those "if only we could" ideas that have been sitting on the backlog. Manufacturing Company Operations Director We needed a custom inventory tracking system that integrated with our legacy warehouse software. After six months of being told it wasn't a priority, I built it myself with Replit in two days. My team couldn't believe it. SaaS Startup RevOps Manager We were spending $800/month on workflow automation tools with frustrating limitations. We replaced our entire stack with custom solutions built on Replit, saving over $9,000 annually while getting exactly what we needed. E-commerce Brand Head of Operations I gave Replit Agent our sales data and customer support tickets and asked for a dashboard showing correlations. In minutes, I had insights we'd never been able to see before—all without writing a line of code. Your teams deserve better tools — build them yourself with Replit Unlock next level productivity and uncover new insights by creating the exact solutions your team needs with Replit. No engineering backlog, expensive software, or coding required. Get started free Handy Links About us Vibe Coding 101 Help How to guides Import from GitHub Status Additional resources Brand kit Partnerships Legal Terms of service Commercial agreement Privacy Subprocessors DPA Report abuse Connect X / Twitter Tiktok Facebook Instagram Linkedin Scroll to top All rights reserved. Copyright © 2026 Replit, Inc. | 2026-01-13T08:47:52 |
https://replit.com/customers | Customer Stories - Replit Agent Products Agent Design Database Publish Security Integrations Mobile For Work Teams Replit for teams to build together Enterprise Replit with Enterprise-grade security & controls Use Cases Business Apps Rapid Prototyping Roles Enterprise PM Designers Operations Software Developers Small Businesses SMB owners Founders Resources Get Started Docs Community Expert Network Inspiration Customer Stories Gallery Blog News Pricing Careers Agent Contact sales Log in Sign up Products For Work Resources Pricing Careers Contact sales Log in Start building Customer Stories Get inspired and simplify your work life & boost productivity. Get Replit Free How Rokt built 135 internal applications in 24 hours with Replit Global ecommerce leader Rokt empowered 700+ employees to build 135 internal apps in a single day using Replit, transforming internal operations at scale "I sat there on an iPad mini and I deployed a fully functional end-to-end application with Google OAuth in about a day. And I have no background in engineering. That was my 'holy shit' moment where I said, 'My goodness, I can't believe I just did that.'" — Jon Humphrey, SVP of Solutions and Operations, Rokt Ecommerce All Stories Consumer Software Financial Services Healthcare Real Estate Legal Logistics Ecommerce Norstella and Replit Team Up to Accelerate Innovation and Optimize Commercial Processes with AI Healthcare Software Hg increases productivity by 6x Financial Services How Plaid Built a Production SLA Dashboard with Replit Agent Financial Services Greenleaf builds custom CRM, saving tens of thousands of dollars Financial Services Real Estate Jason Lemkin Transforms SaaStr with Replit: 7 Apps in production in 3 Months Software How a $60M media company saves $1.2 million and empowers non-developers to build apps How BatchData's Chief Growth Officer built enterprise-grade tools in hours, not months Software Real Estate How Zinus Saves $140,000+ and Cuts Development Time by 50% with Replit Consumer Building a Six-Figure Business in Days, Not Years: How GenAIPI Used Replit Agent to Transform AI Education Consumer From zero code to complete healthcare platform: Dr. Fahim Hussain's 4-day journey with Replit Agent Healthcare From Idea to 17x Growth: How Spellbook Created a Prototype on Replit and Raised Funding Legal AllFly Creates Production-Ready Software with Replit Logistics Consumer National retail chain transforms service operations with custom service portals Ecommerce Consumer Handy Links About us Vibe Coding 101 Help How to guides Import from GitHub Status Additional resources Brand kit Partnerships Legal Terms of service Commercial agreement Privacy Subprocessors DPA Report abuse Connect X / Twitter Tiktok Facebook Instagram Linkedin Scroll to top All rights reserved. Copyright © 2026 Replit, Inc. | 2026-01-13T08:47:52 |
https://www.reddit.com/user/toyojuni/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://www.reddit.com/user/AlmondOffSec/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netsec/?f=flair_name%3A%22Offensive%20Techniques%22 | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://twitter.com/redditweb | JavaScript is not available. We’ve detected that JavaScript is disabled in this browser. Please enable JavaScript or switch to a supported browser to continue using x.com. You can see a list of supported browsers in our Help Center. Help Center Terms of Service Privacy Policy Cookie Policy Imprint Ads info © 2026 X Corp. Something went wrong, but don’t fret — let’s give it another shot. Try again Some privacy related extensions may cause issues on x.com. Please disable them and try again. | 2026-01-13T08:47:52 |
https://claude.com/platform/api | Claude Developer Platform | Claude -------> Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Platform Platform Explore here Ask questions about this page Copy as markdown Build on the Claude Developer Platform Use our API to create new user experiences, products, and ways to work with the most advanced AI models on the market. Start building Start building Start building See developer docs See developer docs See developer docs “Claude Opus 4.5 handles long-horizon coding tasks more efficiently than any model we’ve tested. It achieves higher pass rates on held-out tests while using up to 65% fewer tokens, giving developers real cost control without sacrificing quality.” Sean Ward, CEO and Co-founder “The decision to choose Claude was entirely data-driven. We tested multiple model providers side by side, and Claude consistently delivered the best results for case resolution rates and customer satisfaction scores.” Read story Read story Read story Timothy Addison, Engineering Org Chief of Staff “The partnership with Anthropic has been exceptional—their guidance and support have helped our engineering teams maximize the models.” Read story Read story Read story Joel Hron, CTO “With Claude, we’re not just automating customer service—we’re elevating it to truly human quality. This lets support teams think more strategically about customer experience and what makes interactions genuinely valuable.” Read story Read story Read story Fergal Reid, VP of AI “We're seeing state-of-the-art coding performance from Claude Sonnet 4.5, with significant improvements on longer horizon tasks. It reinforces why many developers using Cursor choose Claude for solving their most complex problems.” Michael Truell, CEO “The platform’s Prompt caching makes Notion AI faster and cheaper, all while maintaining state-of-the-art quality. This enables us to create a more elevated and responsive user experience for our customers.” Simon Last, Co-founder Prev Prev 0 / 5 Next Next Choose how to get started Build on your own Launch your own generative AI solution with: Access to all Claude models Usage-based tiers Automatically increasing rate limits Simple pay-as-you-go pricing Self-serve deployment on workbench Prompting guides and developer docs Start building Start building Start building Get extra support Need custom rate limits or hands-on help? Contact our sales team for: Anthropic-supported onboarding Custom rate limits Billing via monthly invoices Prompting support Deployment support Contact sales Contact sales Contact sales Claude models Right-sized for any task, our models offer the best combination of speed and performance. Start building Start building Start building Learn more Learn more Learn more Save 50% with batch processing. Learn more Batch processing Opus 4.5 Most intelligent model for building agents and coding Input $ 5 / MTok Output $ 25 / MTok Prompt caching Write $ 6.25 / MTok Read $ 0.50 / MTok Sonnet 4.5 Optimal balance of intelligence, cost, and speed Input Prompts ≤ 200K tokens $ 3 / MTok Prompts > 200K tokens $ 6 / MTok Output Prompts ≤ 200K tokens $ 15 / MTok Prompts > 200K tokens $ 22.50 / MTok Prompt caching ≤ 200K tokens Write $ 3.75 / MTok Read $ 0.30 / MTok > 200K tokens Write $ 7.50 / MTok Read $ 0.60 / MTok Haiku 4.5 Fastest, most cost-effective model Input $ 1 / MTok Output $ 5 / MTok Prompt caching Write $ 1.25 / MTok Read $ 0.10 / MTok Prompt caching pricing reflects 5-minute TTL. Learn about extended prompt caching . Do more with built-in tools See developer docs See developer docs See developer docs Prompt caching Give Claude more background knowledge and example outputs to reduce costs and latency. Web search Augment Claude’s knowledge with current, real-world data from across the web. Advanced tool use Allow Claude to interact with hundreds of external tools and APIs so it can perform a wider range of tasks. Batch processing Process large volumes of requests asynchronously and save 50% on costs. Memory Let Claude store and consult information from a dedicated memory file. Context editing Automatically clear less relevant tool calls and results from the context window when approaching token limits. MCP connector Connect Claude to any remote MCP server without writing client code. Code execution Run Python code, create visualizations, and analyze data directly within API calls. Citations Get detailed references to the exact sentences and passages Claude uses to generate responses, leading to more verifiable, trustworthy outputs. Files API Upload documents once and reference them repeatedly across conversations. Developer docs Explore Claude’s advanced features and capabilities. Read more Read more Read more Prev Prev Next Next Get to production faster with the Claude Console Integrate Claude’s powerful AI capabilities into your apps and deliver production-grade solutions faster. View prompt View prompt View prompt Existing prompt Classify all customer support tickets into the most relevant category. Here is the list of categories to choose from: {{CATEGORY_LIST}} Here is the content of the support ticket: {{TICKET_CONTENT}} What would you like to improve? Please include a rationale for the classification. You are an AI assistant specialized in classifying customer support tickets. Your task is to analyze the content of a given ticket and assign it to the most appropriate category from a predefined list. You will also provide reasoning for your classification decision. First, let's review the available categories: <category_list> {{CATEGORY_LIST}} </category_list> Now, here is the content of the support ticket you need to classify: <ticket_content> {{TICKET_CONTENT}} </ticket_content> Please follow these steps to complete the task: – Carefully read and analyze the ticket content. – Consider how the content relates to each of the available categories. – Choose the most appropriate category for the ticket. – Provide a detailed explanation of your reasoning process. Use the following structure for your response: <classification_analysis> In this section, break down your thought process: – Quote the most relevant parts of the ticket content. – List each category and note how it relates to the ticket content. – For each category, provide arguments for and against classifying the ticket into that category. – Rank the top 3 most likely categories. </classification_analysis> <classification> <category>Your chosen category goes here</category> <reasoning>A concise summary of your reasoning for choosing this category</reasoning> </classification> Remember to be thorough in your analysis and clear in your explanation. Your goal is to provide an accurate classification with well-supported reasoning. Built for developers Build, test, and iterate on your deployment: Automatically generate or improve existing prompts Evaluate model responses against real-world scenarios Build faster with pre-built cookbooks and guides Use cases for Claude Coding Our models are constantly improving on coding, math, and reasoning. Claude can complete complex engineering tasks to solve problems that would typically take a full day of engineering work. Learn more Learn more Learn more Agents Claude offers superior instruction following, tool selection, error correction, and advanced reasoning for customer-facing agents and complex AI workflows. Learn more Learn more Learn more Productivity Claude can extract relevant information from business emails and documents, categorize and summarize survey responses, and wrangle reams of text with high speed and accuracy. Customer support Claude can handle ticket triage, on-demand complex inquiries using rich context awareness, and multi-step support workflows—all with a casual tone and conversational responses. Learn more Learn more Learn more Start building See pricing See pricing See pricing Contact sales Contact sales Contact sales Get the developer newsletter Product updates, how-tos, community spotlights, and more. Delivered monthly to your inbox. Subscribe Subscribe Please provide your email address if you'd like to receive our monthly developer newsletter. You can unsubscribe at any time. Thank you! You’re subscribed. Sorry, there was a problem with your submission, please try again later. Homepage Homepage Next Next Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Write Button Text Button Text Learn Button Text Button Text Code Button Text Button Text Write Help me develop a unique voice for an audience Hi Claude! Could you help me develop a unique voice for an audience? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Improve my writing style Hi Claude! Could you improve my writing style? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Brainstorm creative ideas Hi Claude! Could you brainstorm creative ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Learn Explain a complex topic simply Hi Claude! Could you explain a complex topic simply? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Help me make sense of these ideas Hi Claude! Could you help me make sense of these ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Prepare for an exam or interview Hi Claude! Could you prepare for an exam or interview? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Code Explain a programming concept Hi Claude! Could you explain a programming concept? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Look over my code and give me tips Hi Claude! Could you look over my code and give me tips? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Vibe code with me Hi Claude! Could you vibe code with me? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! More Write case studies This is another test Write grant proposals Hi Claude! Could you write grant proposals? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to — like Google Drive, web search, etc. — if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can - an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Write video scripts this is a test Anthropic Anthropic © [year] Anthropic PBC Products Claude Claude Claude Claude Code Claude Code Claude Code Max plan Max plan Max plan Team plan Team plan Team plan Enterprise plan Enterprise plan Enterprise plan Download app Download app Download app Pricing Pricing Pricing Log in Log in Log in Features Claude in Chrome Claude in Chrome Claude in Chrome Claude in Slack Claude in Slack Claude in Slack Claude in Excel Claude in Excel Claude in Excel Skills Skills Skills Models Opus Opus Opus Sonnet Sonnet Sonnet Haiku Haiku Haiku Solutions AI agents AI agents AI agents Code modernization Code modernization Code modernization Coding Coding Coding Customer support Customer support Customer support Education Education Education Financial services Financial services Financial services Government Government Government Healthcare Healthcare Healthcare Life sciences Life sciences Life sciences Nonprofits Nonprofits Nonprofits Claude Developer Platform Overview Overview Overview Developer docs Developer docs Developer docs Pricing Pricing Pricing Regional Compliance Regional Compliance Regional Compliance Amazon Bedrock Amazon Bedrock Amazon Bedrock Google Cloud’s Vertex AI Google Cloud’s Vertex AI Google Cloud’s Vertex AI Console login Console login Console login Learn Blog Blog Blog Claude partner network Claude partner network Claude partner network Courses Courses Courses Connectors Connectors Connectors Customer stories Customer stories Customer stories Engineering at Anthropic Engineering at Anthropic Engineering at Anthropic Events Events Events Powered by Claude Powered by Claude Powered by Claude Service partners Service partners Service partners Startups program Startups program Startups program Tutorials Tutorials Tutorials Use cases Use cases Use cases Company Anthropic Anthropic Anthropic Careers Careers Careers Economic Futures Economic Futures Economic Futures Research Research Research News News News Responsible Scaling Policy Responsible Scaling Policy Responsible Scaling Policy Security and compliance Security and compliance Security and compliance Transparency Transparency Transparency Help and security Availability Availability Availability Status Status Status Support center Support center Support center Terms and policies Privacy choices Cookie settings We use cookies to deliver and improve our services, analyze site usage, and if you agree, to customize or personalize your experience and market our services to you. You can read our Cookie Policy here . Customize cookie settings Reject all cookies Accept all cookies Necessary Enables security and basic functionality. Required Analytics Enables tracking of site performance. Off Marketing Enables ads personalization and tracking. Off Save preferences Privacy policy Privacy policy Privacy policy Responsible disclosure policy Responsible disclosure policy Responsible disclosure policy Terms of service: Commercial Terms of service: Commercial Terms of service: Commercial Terms of service: Consumer Terms of service: Consumer Terms of service: Consumer Usage policy Usage policy Usage policy x.com x.com LinkedIn LinkedIn YouTube YouTube Instagram Instagram English (US) English (US) 日本語 (Japan) Deutsch (Germany) Français (France) 한국어 (South Korea) | 2026-01-13T08:47:52 |
https://www.thedrive.com/news/john-cena-just-added-a-prelude-to-his-growing-honda-collection | John Cena Just Added a Prelude to His Growing Honda Collection Search for: Latest News News by Brand The Downshift Spy Photos Car Tech Culture Deals Racing Trucks Video Games Watch This Car Reviews The Drive Awards Features Video Shop Buy A Car Merch Search for: svg]:fill-accent-900 [&>svg]:stroke-accent-900"> svg]:fill-accent-900 [&>svg]:stroke-accent-900"> svg]:fill-accent-900 [&>svg]:stroke-accent-900"> svg]:fill-accent-900 [&>svg]:stroke-accent-900"> News News by Brand Honda News John Cena Just Added a Prelude to His Growing Honda Collection The Prelude is like Cena's other daily, but a little more comfortable and better on gas. By Adam Ismail Published Jan 12, 2026 9:48 AM EST 0 John Cena via Facebook The biggest car news and reviews, no BS Our free daily newsletter sends the stories that really matter directly to you, every weekday. Email address Sign Up Thank you! Terms of Service & Privacy Policy. John Cena has been lending his dependable, confident voice to Honda commercials for a little more than five years now . (If he’s actually present in the ads, we can’t see him.) But he’s also a longtime enthusiast, and that’s reflected in the Hondas he chooses to drive. Back in 2023, he revealed that he dailied a Boost Blue, FK8 Civic Type R ; about a year later, he traded the sports sedan in for a fresh, Championship White FL5 . Now, he’s continuing the theme with a new Prelude. The wrestler and actor took the keys to one of Honda’s hybrid coupes over the weekend, matching the color of his old FK8. Cena said he picked up his Prelude from Wesley Chapel Honda outside Tampa, Florida, while taking his CTR in for service. That’s not surprising, considering he’s a superstar and ambassador for the brand, but it is still funny to think about. The guy accumulates new Hondas like he did championship belts. Of course, Cena’s two cars in that picture share plenty in common. The Prelude is built on the Civic chassis and incorporates the Type R’s suspension and brakes . Where they really differ, door count aside, is in their powertrains. The Civic Type R makes 315 horsepower from Honda’s latest K-series turbo-four, while the Prelude produces quite a bit less than that—200, to be precise—but is a hybrid, so at least it’s decently torquey. John Cena via Facebook Cena did a spot for Honda featuring the Prelude last fall , and in late 2024, he narrated one of the best motorsport-themed ads in recent memory , featuring clips of Ayrton Senna and Max Verstappen. Ultimately, if you’re the kind of guy who enjoys a good Civic but has room for something slightly more comfortable and luxurious in your garage, the Prelude is probably a fine choice. (So too would be an Integra Type S , but we’ve yet to see Cena drive one of those off the lot.) And don’t chalk it all up to an endorsement deal; Cena used to own a Jaguar XJ13 replica , so he’s a man of unquestionable taste. Got a tip? Reach out to tips@thedrive.com Adam Ismail Senior Editor Backed by a decade of covering cars and consumer tech, Adam Ismail is a Senior Editor at The Drive, focused on curating and producing the site’s slate of daily stories. .article-sidebar]:pt-0"> Trending News Are We About to Have an Electric-Motor RPM race? By Stephen Edelstein Ford News Sand Turbine: The Fluid Dynamics Behind This Unreal Ford Raptor Dakar Photo By Andrew P. Collins More in Honda News 2026 Honda Prelude Gets 44 MPG and Costs $43,195 By Adam Ismail Think the Honda Prelude Needs More Power? It’s Got Less in Europe By Adam Ismail What Would You Pay for the 2026 Honda Prelude? By Adam Ismail Here’s Why You Can’t Rev the New Honda Prelude By Adam Ismail SEE MORE More in News by Brand 2026 Honda Prelude Revealed as a Giant Bet on the Future of Compact Sports Coupes By Adam Ismail The Honda Prelude Has a Secret Design Trick to Make It Easier to Park By Adam Ismail The New Honda Prelude Doesn’t Have a Transmission. Here’s Why By Andrew P. Collins 2026 Honda Civic Type R Starts Way Too Close to $50K By Adam Ismail SEE MORE More in News New Honda Prelude Will Be Part Civic Hybrid, Part Type R, All Coupe By Byron Hurd The Honda Prelude Looks Sick as a 650-HP Super GT Race Car By Caleb Jacobs John Cena Is Sticking With Honda Civics By Andrew P. Collins Honda Civic Type R Theft Victim Accidentally Buys His Own Car Back By Beverly Braga SEE MORE Car news and reviews, no BS Our free daily newsletter sends the stories that really matter directly to you, every weekday. Thank you! Email address Sign Up By signing up you agree to our Terms of Service and Privacy Policy. About Us Watch on YouTube Merch Buy a Car Get in Touch Sitemap Privacy Policy Terms & Conditions FOLLOW US DISCLAIMER(S) © 2026 Recurrent Ventures. All Rights Reserved. Articles may contain affiliate links which enable us to share in the revenue of any purchases made. Some benefits of our Car Shopping program may not be available in your area. Please see terms for details. Do Not Sell or Share My Personal Information . News Video Car Reviews Features The Downshift Spy Photos Gear Deals | 2026-01-13T08:47:52 |
https://replit.com/enterprise | Replit for Enterprise | Enterprise Development Platform Agent Products Agent Design Database Publish Security Integrations Mobile For Work Teams Replit for teams to build together Enterprise Replit with Enterprise-grade security & controls Use Cases Business Apps Rapid Prototyping Roles Enterprise PM Designers Operations Software Developers Small Businesses SMB owners Founders Resources Get Started Docs Community Expert Network Inspiration Customer Stories Gallery Blog News Pricing Careers Agent Contact sales Log in Sign up Products For Work Resources Pricing Careers Contact sales Log in Start building End Your Software Backlog. Empower your entire organization to create applications by simply describing them. Replit's enterprise platform translates your description into production-ready software, securely and at scale. Contact Sales First Name (required) Last Name (required) Work Email (required) Phone Number (optional) Message (optional) Contact Sales Loved by 40 million app creators, including teams at: Replit is the most secure agentic platform for production-ready apps Replit’s got everything you need to make building & launching your app a breeze — build & refine your apps through conversing with Agent. Every Replit app comes with a built in database, user-authentication, integrations and Enterprise Grade security. Self-debugging & autonomous agent allows anyone to build complex production grade apps Anyone from your Product, Design or Business teams can build apps and tools within a few prompts. Agent can autonomously handle complex tasks and debugging so you don't have to. In-built Auth, Database, Hosting & Monitoring services make pushing an app to production a breeze Every project includes a pre-configured, production grade Auth and Database that grows with your project-no separate setup or installation needed. You can also easily connect to services like Stripe, Open AI and more. Enterprise controls & security for your apps Replit platform has SSO/SAML, SOC2 & all the standard Enterprise admin controls. Plus, pre deployment security screening, secure in-built services and better defaults ensure the apps you built remain secure too. Jon Humphrey, Rokt SVP of Solutions and Operations "I sat there on an iPad mini and I deployed a fully functional end-to-end application with Google OAuth in about a day. And I have no background in engineering. That was my 'holy shit' moment where I said, 'My goodness, I can't believe I just did that.'" Mike Messenger, Zillow Director of Field Operations “Replit empowers our operations teams to quickly create enterprise-grade apps, no-code needed.” Key Vaidya, Hg Capital Portfolio CTO “The ability to go from idea to working application in minutes has opened new possibilities for innovation across our portfolio. We're seeing apps built in 45 minutes that save teams hours every week." From rapidly prototyping MVPs to building internal tools or customer facing apps, the possibilities are endless Replit’s got everything you need to make building & launching your app a breeze — build & refine your apps through conversing with Agent. Every Replit app comes with a built in database, user-authentication, integrations and Enterprise Grade security. Rapid Prototyping Rapidly prototype your product ideas for customer demos and feedback. Launch it as production ready app or hand it off to engineering for continued development Internal Tools Build that perfect tool you always wanted and simplify your workflow and increase your productivity Customer facing apps Build new, production-ready apps for your customers much faster via faster prototyping and more seamless handoff from product to engineering teams Purchase Replit Enterprise Through Your Preferred Cloud Marketplace Replit Enterprise is now available on Azure Marketplace and Google Cloud Marketplace, making it easier than ever to procure our agentic development platform through your existing cloud provider relationship. Streamlined procurement — Use existing cloud credits, consolidated billing, and pre-approved vendor relationships Available on Azure Marketplace and Google Cloud Marketplace Enterprise features include — SSO/SAML, SCIM provisioning, dedicated support, and advanced privacy controls Empower your Product, Design & Business teams to bring their ideas to life Product Teams Quickly prototype and test your product ideas with clickable prototypes to speed up customer demos, gather feedback faster, and dramatically shorten your product development cycle. Don’t just hand off a PRD to engineering—hand off working source code. Designers Bring your Figma designs to life and simplify that developer handoff by building out a clickable prototype. Now your designs can be transferred to product with perfect fidelity. Sales & Marketing Teams Build that perfect tool you always wanted and simplify your workflow and increase productivity. Where you want to analyze sales call transcripts or generate quick landing pages for marketing, you can do it all with a Replit app Operations Teams Build that perfect tool you always wanted and simplify your workflow and increase productivity. Where you want to build a custom dashboard to analyze support tickets, or a procurement tool, you can build it all with a Replit app. Request a hackathon Transform your organization in 4 hours Solve real business challenges Cross-functional teams build apps that address your organizations actual needs and pain points. No coding required Anyone can participate regardless of technical background—vibe coding makes programming accessible to all. Deploy live applications Teams go from idea to working application in just 4 hours, ready to showcase and implement. Request a Hackathon Try Replit now Replit empowers anyone with an idea to become a creator, while giving professional designers the freedom to creatively explore and build — without being held back by code or the limitations of design tools: Start building Handy Links About us Vibe Coding 101 Help How to guides Import from GitHub Status Additional resources Brand kit Partnerships Legal Terms of service Commercial agreement Privacy Subprocessors DPA Report abuse Connect X / Twitter Tiktok Facebook Instagram Linkedin Scroll to top All rights reserved. Copyright © 2026 Replit, Inc. | 2026-01-13T08:47:52 |
https://claude.com/resources/use-cases | Use Cases | Claude -------> Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Use cases Use cases Explore here Ask questions about this page Copy as markdown Filter Category Education Finance HR Legal Life Sciences Marketing Nonprofits Personal Professional Research Sales Features Artifacts Connectors Extended Thinking Projects Research Skills Web Search Product Claude in Chrome Claude.ai Reset Reset Reset Apply Apply Apply Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Get inspired by what you can do with Claude Browse practical examples across research, writing, coding, analysis, and everyday tasks, whether you're working solo or with a team. Filter Category Education Finance HR Legal Life Sciences Marketing Nonprofits Personal Professional Research Sales Features Artifacts Connectors Extended Thinking Projects Research Skills Web Search Product Claude in Chrome Claude.ai Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Search Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Grid List Author Category Model Features Explore what Claude can do for you New to Claude? Start here. Tell Claude your role and get a personalized guide to the capabilities that will matter for your work. Anthropic Professional Author Anthropic Category Professional Model Opus 4.5 Features Connectors Read use case Read use case Read use case Claude.ai Explore what Claude can do for you Explore what Claude can do for you Text Link Thoughtful gift giving with Claude Turn last-minute gift panic into thoughtful, personalized presents. Claude can suggest items, search your notes for forgotten hints, find specific products you can buy locally, and help you coordinate the actual shopping. Anthropic Personal Author Anthropic Category Personal Model Opus 4.5 Features Web Search Connectors Extended Thinking Read use case Read use case Read use case Claude.ai Thoughtful gift giving with Claude Thoughtful gift giving with Claude Text Link Pull metrics from analytics dashboards Claude in Chrome can navigate your analytics dashboards, extract the numbers you need, and compile them into a summary. No exports, no tab-switching, no manual copying. Anthropic Claude in Chrome Author Anthropic Category Claude in Chrome Model Haiku 4.5 Features Browser Use Read use case Read use case Read use case Claude in Chrome Pull metrics from analytics dashboards Pull metrics from analytics dashboards Text Link Prepare and plan from your calendar Claude in Chrome reads your calendar, pulls context from email threads, flags which meetings need prep, and books rooms for the ones missing them. Run it every evening and start each day knowing what's coming. Anthropic Claude in Chrome Author Anthropic Category Claude in Chrome Model Haiku 4.5 Features Browser Use Read use case Read use case Read use case Claude in Chrome Prepare and plan from your calendar Prepare and plan from your calendar Text Link Compare products across sites Claude in Chrome reads the specs from multiple product pages you have open, normalizes the data, and creates a comparison table in Google Sheets. You stop tab-switching and start deciding. Anthropic Claude in Chrome Author Anthropic Category Claude in Chrome Model Haiku 4.5 Features Browser Use Read use case Read use case Read use case Claude in Chrome Compare products across sites Compare products across sites Text Link Log sales calls to your CRM Claude in Chrome can read your calendar, match attendees to Salesforce contacts, and draft activity logs for each call. You add notes and approve before anything gets created. Anthropic Claude in Chrome Author Anthropic Category Claude in Chrome Model Haiku 4.5 Features Browser Use Read use case Read use case Read use case Claude in Chrome Log sales calls to your CRM Log sales calls to your CRM Text Link Clean up promotional emails Claude in Chrome can scan your inbox, identify promotional and marketing emails, and flag them for your review. You decide what to delete in bulk rather than clicking through one by one. Anthropic Claude in Chrome Author Anthropic Category Claude in Chrome Model Haiku 4.5 Features Browser Use Read use case Read use case Read use case Claude in Chrome Clean up promotional emails Clean up promotional emails Text Link Organize files in Google Drive Claude in Chrome sorts through your Drive, creates a folder structure, moves files where they belong, and flags duplicates and old files for you to review. You approve the changes instead of doing the sorting yourself. Anthropic Claude in Chrome Author Anthropic Category Claude in Chrome Model Haiku 4.5 Features Browser Use Read use case Read use case Read use case Claude in Chrome Organize files in Google Drive Organize files in Google Drive Text Link Turn transit time into research time Capture rough thoughts by voice on mobile, then let Claude research your ideas and produce polished deliverables at your desk. Claude maintains full context across devices, so your commute becomes productive thinking time. Anthropic Research Author Anthropic Category Research Model Opus 4.5 Features Research Web Search Extended Thinking Read use case Read use case Read use case Claude.ai Turn transit time into research time Turn transit time into research time Text Link Organize your legal workflows using Projects Stop explaining your review standards for every contract. Claude Projects let you upload your playbooks once and reference them automatically across hundreds of reviews. Anthropic Legal Author Anthropic Category Legal Model Opus 4.5 Features Projects Read use case Read use case Read use case Claude.ai Organize your legal workflows using Projects Organize your legal workflows using Projects Text Link Workflow improvement planner Turn process pain points into structured improvement plans. Claude helps nonprofits define workflow challenges and design AI-powered solutions that save time and increase capacity. Anthropic Nonprofits Author Anthropic Category Nonprofits Model Sonnnet 4.5 Features Extended Thinking Read use case Read use case Read use case Claude.ai Workflow improvement planner Workflow improvement planner Text Link Grant proposal assembly line Build a modular content library from your successful proposals and organizational materials then produce foundation-ready submissions in a fraction of the usual time. GivingTuesday Nonprofits Author GivingTuesday Category Nonprofits Model Sonnet 4.5 Features Connectors Read use case Read use case Read use case Claude.ai Grant proposal assembly line Grant proposal assembly line Text Link Understand and extend an inherited spreadsheet Understand existing formulas and structure then add new data while preserving the original logic. Anthropic Finance Author Anthropic Category Finance Model Opus 4.5 Features Extended Thinking Read use case Read use case Read use case Claude.ai Understand and extend an inherited spreadsheet Understand and extend an inherited spreadsheet Text Link Create a sales proposal presentation Create a polished client proposal deck with professional layouts data visualizations and cohesive design—then refine through feedback until it matches your standards. Anthropic Sales Author Anthropic Category Sales Model Opus 4.5 Features Extended Thinking Connectors Read use case Read use case Read use case Claude.ai Create a sales proposal presentation Create a sales proposal presentation Text Link Build interactive diagram tools From body systems to molecular structures, turn a detailed prompt into a working reference app with the depth and design you specify. Anthropic Personal Author Anthropic Category Personal Model Opus 4.5 Features Extended Thinking Read use case Read use case Read use case Claude.ai Build interactive diagram tools Build interactive diagram tools Text Link View more 1 / 5 No posts for those filters Try another search or clear some of your filters. Clear all filters Clear all filters Clear all filters Search Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Transform how your organization operates with Claude Get started Get started Get started Homepage Homepage Next Next Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Write Button Text Button Text Learn Button Text Button Text Code Button Text Button Text Write Help me develop a unique voice for an audience Hi Claude! Could you help me develop a unique voice for an audience? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Improve my writing style Hi Claude! Could you improve my writing style? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Brainstorm creative ideas Hi Claude! Could you brainstorm creative ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Learn Explain a complex topic simply Hi Claude! Could you explain a complex topic simply? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Help me make sense of these ideas Hi Claude! Could you help me make sense of these ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Prepare for an exam or interview Hi Claude! Could you prepare for an exam or interview? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Code Explain a programming concept Hi Claude! Could you explain a programming concept? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Look over my code and give me tips Hi Claude! Could you look over my code and give me tips? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Vibe code with me Hi Claude! Could you vibe code with me? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! More Write case studies This is another test Write grant proposals Hi Claude! Could you write grant proposals? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to — like Google Drive, web search, etc. — if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can - an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Write video scripts this is a test Anthropic Anthropic © [year] Anthropic PBC Products Claude Claude Claude Claude Code Claude Code Claude Code Max plan Max plan Max plan Team plan Team plan Team plan Enterprise plan Enterprise plan Enterprise plan Download app Download app Download app Pricing Pricing Pricing Log in Log in Log in Features Claude in Chrome Claude in Chrome Claude in Chrome Claude in Slack Claude in Slack Claude in Slack Claude in Excel Claude in Excel Claude in Excel Skills Skills Skills Models Opus Opus Opus Sonnet Sonnet Sonnet Haiku Haiku Haiku Solutions AI agents AI agents AI agents Code modernization Code modernization Code modernization Coding Coding Coding Customer support Customer support Customer support Education Education Education Financial services Financial services Financial services Government Government Government Healthcare Healthcare Healthcare Life sciences Life sciences Life sciences Nonprofits Nonprofits Nonprofits Claude Developer Platform Overview Overview Overview Developer docs Developer docs Developer docs Pricing Pricing Pricing Regional Compliance Regional Compliance Regional Compliance Amazon Bedrock Amazon Bedrock Amazon Bedrock Google Cloud’s Vertex AI Google Cloud’s Vertex AI Google Cloud’s Vertex AI Console login Console login Console login Learn Blog Blog Blog Claude partner network Claude partner network Claude partner network Courses Courses Courses Connectors Connectors Connectors Customer stories Customer stories Customer stories Engineering at Anthropic Engineering at Anthropic Engineering at Anthropic Events Events Events Powered by Claude Powered by Claude Powered by Claude Service partners Service partners Service partners Startups program Startups program Startups program Tutorials Tutorials Tutorials Use cases Use cases Use cases Company Anthropic Anthropic Anthropic Careers Careers Careers Economic Futures Economic Futures Economic Futures Research Research Research News News News Responsible Scaling Policy Responsible Scaling Policy Responsible Scaling Policy Security and compliance Security and compliance Security and compliance Transparency Transparency Transparency Help and security Availability Availability Availability Status Status Status Support center Support center Support center Terms and policies Privacy choices Cookie settings We use cookies to deliver and improve our services, analyze site usage, and if you agree, to customize or personalize your experience and market our services to you. You can read our Cookie Policy here . Customize cookie settings Reject all cookies Accept all cookies Necessary Enables security and basic functionality. Required Analytics Enables tracking of site performance. Off Marketing Enables ads personalization and tracking. Off Save preferences Privacy policy Privacy policy Privacy policy Responsible disclosure policy Responsible disclosure policy Responsible disclosure policy Terms of service: Commercial Terms of service: Commercial Terms of service: Commercial Terms of service: Consumer Terms of service: Consumer Terms of service: Consumer Usage policy Usage policy Usage policy x.com x.com LinkedIn LinkedIn YouTube YouTube Instagram Instagram English (US) English (US) 日本語 (Japan) Deutsch (Germany) Français (France) 한국어 (South Korea) | 2026-01-13T08:47:52 |
https://twitter.com/chris_cooney | JavaScript is not available. We’ve detected that JavaScript is disabled in this browser. Please enable JavaScript or switch to a supported browser to continue using x.com. You can see a list of supported browsers in our Help Center. Help Center Terms of Service Privacy Policy Cookie Policy Imprint Ads info © 2026 X Corp. Something went wrong, but don’t fret — let’s give it another shot. Try again Some privacy related extensions may cause issues on x.com. Please disable them and try again. | 2026-01-13T08:47:52 |
https://www.reddit.com/r/learnprogramming/rising/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://www.reddit.com/r/learnprogramming/comments/1q05hcz/programming_as_a_job_feels_nothing_like/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://claude.com/customers | Customer stories | Claude -------> Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Customers Customers Explore here Ask questions about this page Copy as markdown Filter and sort Sort by Newest Alphabetically (A to Z) Alphabetically (Z to A) Industry Beneficial deployments Cybersecurity Ecommerce Education Entertainment Financial services Government Healthcare Insurance Legal Professional services Recruiting Scientific research Software Product Enterprise plan Claude Code Claude Developer Platform AI Platform Size Large Medium Small Partner Google AWS Geography Africa Asia Pacific EMEA Europe North America South America Reset Reset Reset Apply Apply Apply Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Customer story Play video Play video Binti helps social workers spend half the time on reports with Claude Next Next Customer story Play video Play video Intercom achieves up to 86% resolution rates with Claude Next Next Customer story Play video Play video Asana supercharges work management with Claude Next Next Customer story Play video Play video European Parliament expands access to their archives with Claude Next Next Prev Prev Next Next Meet the teams building what’s next Businesses build with Claude for the problems that matter most. Our customers include enterprises and startups across financial services, healthcare, legal, and more. Contact sales Contact sales Contact sales Prev Prev Next Next Filter and sort Sort by Sort by Newest Alphabetically (A to Z) Alphabetically (Z to A) Industry Beneficial deployments Cybersecurity Ecommerce Education Entertainment Financial services Government Healthcare Insurance Legal Professional services Recruiting Scientific research Software Product Enterprise plan Claude Code Claude Developer Platform AI Platform Size Large Medium Small Partner Google AWS Geography Africa Asia Pacific EMEA Europe North America South America Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Search Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Grid List View story View story Carta Healthcare cuts clinical data processing time by 66% with Claude Carta Healthcare Healthcare AI Platform Medium AWS North America January 12, 2026 View story View story Elation Health delivers faster clinical insights with Claude Elation Healthcare AI Platform Medium North America January 12, 2026 View story View story Qualified Health and the University of Texas System use Claude to identify patients who need life-saving care Qualified Health Healthcare AI Platform Large North America January 12, 2026 View story View story Banner Health battles physician burnout with Claude-powered AI platform Banner Health Healthcare Enterprise plan Large AWS North America January 12, 2026 View story View story Matillion reduces data pipeline creation from 40 hours to 1 with Claude-powered AI assistant Matillion Software Claude Code Large Europe December 12, 2025 View story View story bunq builds intelligent banking assistant Finn with Claude bunq Financial services Claude Code Medium Europe November 20, 2025 View story View story Wordsmith uses Claude to transform legal operations from 4-day bottlenecks to 4-minute workflows Wordsmith Legal Claude Code Small Europe November 20, 2025 View story View story IFS Nexus Black builds industrial AI with Claude IFS Software AI Platform Large Europe November 19, 2025 View story View story CodeWords enables non-technical users to build workflow automations with Claude CodeWords Software AI Platform Small Europe November 7, 2025 View story View story Doctolib accelerates developer productivity with Claude Code Doctolib Healthcare Claude Code Large Europe November 5, 2025 View story View story N26 automates customer operations with Claude n26 Financial services Claude Developer Platform Large Europe November 5, 2025 View story View story L'Oréal advances conversational analytics with Claude L'Oreal Ecommerce AI Platform Large Europe November 25, 2025 View story View story <path d="M229.5 367.417C232.59 362.507 237.01 358.767 241.23 354.897L266.95 336.217C267.84 335.397 267.29 333.617 266.53 332.857C219.4 295.667 165.421 267.107 106.35 254.377C97.2405 252.417 81.2605 249.417 72.2605 249.227C70.4205 249.187 68.8505 249.077 67.2605 250.197C61.7505 256.147 55.2205 261.047 49.3705 266.637C40.1505 275.447 31.6405 286.097 22.1505 294.437C17.6205 298.417 12.1505 301.517 7.69049 305.587C4.95049 308.087 3.05049 311.267 0.0704919 313.487V305.047C4.50049 301.697 7.94049 297.057 11.7905 293.347C25.7405 279.867 40.4605 267.237 54.3105 253.597C56.2505 251.687 60.3605 248.437 55.7905 246.637C52.2805 245.257 42.7005 245.697 38.5005 245.397C35.6005 245.187 32.1105 244.407 29.2505 244.297C19.5505 243.937 9.75049 244.407 0.0704919 244.867C0.230492 243.937 -0.149508 239.6 | 2026-01-13T08:47:52 |
https://replit.com/usecases/software-engineers | Replit for Software Engineers Agent Products Agent Design Database Publish Security Integrations Mobile For Work Teams Replit for teams to build together Enterprise Replit with Enterprise-grade security & controls Use Cases Business Apps Rapid Prototyping Roles Enterprise PM Designers Operations Software Developers Small Businesses SMB owners Founders Resources Get Started Docs Community Expert Network Inspiration Customer Stories Gallery Blog News Pricing Careers Agent Contact sales Log in Sign up Products For Work Resources Pricing Careers Contact sales Log in Start building B u ild, t e st, and sh i p f a ster than ever with Replit Replit is the only platform that combines a cloud IDE, Agentic AI coding, and seamless team collaboration to help you prototype and ship apps in record time. Build in 50+ languages, work from any device, and deploy in one click — no setup required. Start now Your new engineering cycle: fast and frictionless Build and deploy without configuration overhead Begin building instantly in pre-configured environments for 50+ languages. Replit Agent generates up to 90% of your foundational code so you can focus on building features and products that matter. Create internal tools and automations instantly Build that custom integration, AI chatbot, or data pipeline you've been putting off. Replit Agent transforms complex infrastructure needs into simple projects that deliver immediate value to your organization. Develop mock APIs for frontend and mobile testing Create and control functional API endpoints in minutes, giving you the power to unblock frontend and mobile development without disrupting production systems. Let AI handle tedious code maintenance and deployment issues Replit Agent optimizes entire codebases through multi-file updates and automated refactoring — with safe rollbacks and deployment debugging capabilities. Collaborate seamlessly across any device Work together with collaborative editing and synced terminals — from desktop or mobile. Persistent workspaces eliminate version conflicts and setup mismatches. Deploy with one click, zero infrastructure management Launch applications with Replit's integrated cloud services. No complex configuration — just production-ready deployment with enterprise-grade scaling capabilities. How it works 1 Choose your development environment Instantly access Python, JavaScript, or any of 50+ languages with zero setup time 2 Let AI jumpstart your project Watch Replit Agent transform your idea into a working codebase in minutes, not days 3 Build and iterate in real-time Code, test, and debug to refine your application from any device 4 Bring your team together Invite collaborators to a synchronized workspace where everyone can create simultaneously 5 Go live with confidence Deploy with built-in monitoring and enjoy continuous availability without DevOps overhead Why developers love Replit Developers from innovative startups to large enterprise teams use Replit to ship better products faster: 50+ programming languages Making it the most versatile cloud development platform 40% reduction in environment setup time With pre-configured workspaces & Replit Agent 30% faster development cycles Through real-time collaboration and AI powered integrated tools James Chen Senior Backend Engineer at Rippling Replit eliminated our team's Python environment inconsistencies completely. Our onboarding time went from days of setup to literally opening a browser and starting. Now our entire team can collaborate regardless of their device. Sarah Connor Engineering Lead at Scale We were spending $800/month on workflow automation tools with frustrating limitations. We replaced our entire stack with custom solutions built on Replit, saving over $9,000 annually while getting exactly what we needed. Mike Hernandez Tech Lead at Retool I built and deployed our team's internal dashboard using Replit Agent in one afternoon. It handled all the React boilerplate and API setup while I focused on the analytics logic—perfect for internal tools without engineering bottlenecks." Build in minutes what used to take weeks Create production-ready applications at unprecedented speed with Replit's Agentic AI coding platform. No complex setup, no overhead, no limits — what will you build with Replit? Get started free Handy Links About us Vibe Coding 101 Help How to guides Import from GitHub Status Additional resources Brand kit Partnerships Legal Terms of service Commercial agreement Privacy Subprocessors DPA Report abuse Connect X / Twitter Tiktok Facebook Instagram Linkedin Scroll to top All rights reserved. Copyright © 2026 Replit, Inc. | 2026-01-13T08:47:52 |
https://claude.com/regional-compliance | Regional Compliance | Claude -------> Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Platform Platform / Regional compliance Explore here Ask questions about this page Copy as markdown Deploy Claude confidently, wherever you are Claude is available globally with regional data residency and inference, comprehensive compliance certifications, and deployment across all major cloud platforms. Contact sales Contact sales Contact sales Visit Trust Center Visit Trust Center Visit Trust Center Built for regulated industries, worldwide Trusted compliance Organizations in highly regulated industries trust Claude to handle their most sensitive work while meeting strict regional compliance requirements. Flexible deployment Whether you're a startup navigating your first audit or a Fortune 500 company with global operations, Claude’s deployment options meet you where you are. Safety-first Anthropic's safety-first approach to AI extends to how we protect and process your data, from technical deployment to operational practices. Flexible deployment, data storage, and inference processing Meet your regional data residency and compliance requirements with Claude. Choose where your data is stored and processed. Available on AWS Bedrock, GCP Vertex, and Microsoft Foundry. Claude's regional availability Region AWS Bedrock Specifications GCP Vertex Specifications Microsoft Foundry Specifications Asia-Pacific AWS Bedrock Specifications GCP Vertex Specifications Microsoft Foundry Specifications Coming 2026 Canada AWS Bedrock Specifications GCP Vertex Specifications Microsoft Foundry Specifications Coming 2026 Europe AWS Bedrock Specifications GCP Vertex Specifications Microsoft Foundry Specifications Coming 2026 United States AWS Bedrock Specifications GCP Vertex Specifications Microsoft Foundry Specifications Understand data residency
and inference Claude gives you control over where your data is stored, requests are processed, and responses are generated. Data residency Controls where prompts, outputs, and conversation history are stored. Inference residency Controls where Claude processes requests and generates responses. Trusted across
regulated sectors Organizations in financial services, healthcare, life sciences, government, and legal services accelerate sensitive, mission-critical workflows with Claude while maintaining compliance standards. $1.7T Norges Bank Investment Management handles $1.7T in assets with European data protection compliance. Read story Read story Read story 90% Novo Nordisk, the maker of Ozempic, cut regulatory documentation time by 90% with Claude. Read story Read story Read story 2.1M The European Parliament transformed 2.1M archive documents accessibility with Claude via AWS Bedrock. Read story Read story Read story Compliance and certifications Claude supports compliance with industry and regional standards. Regulatory compliance GDPR (General Data Protection Regulation) with regional processing within EU/EEA HIPAA (Health Insurance Portability and Accountability Act) for protected health information Data Processing Addendum defining roles and responsibilities Support for data subject rights, retention policies, and deletion capabilities Security certifications SOC 2 Type 2 Security, Availability, and Confidentiality ISO/IEC 27001 Information Security Management ISO/IEC 27017 Cloud Security ISO/IEC 27018 Cloud Privacy CSA STAR Cloud Security Alliance Documentation and certifications View complete compliance documentation and certifications at our Trust Center. Visit Trust Center Visit Trust Center Visit Trust Center Data protection commitment By default, Anthropic does not use customer data from commercial deployments to train models. Your proprietary information and client data remain confidential across all deployment options and compliance frameworks. Prev Prev Next Next FAQ Can I choose which specific region my data is processed in? Yes. Regional endpoints allow you to specify geographic boundaries for both data storage and inference processing. For Europe, you can select country-specific deployment options through AWS Bedrock, GCP Vertex, and Microsoft Foundry to meet local data residency requirements. Where is regional data residency available? Regional data residency is available across Europe, United States, Canada, and Asia-Pacific regions including Japan, South Korea, Singapore, India, and Australia. Choose between global endpoints for maximum availability or regional endpoints for guaranteed geographic routing. What's the difference between global and regional endpoints? Global endpoints dynamically route requests to regions with available capacity, providing maximum uptime with no pricing premium. Regional endpoints guarantee that both data storage and model processing remain within your specified geographic region. Pricing for regional endpoints may reflect dedicated regional infrastructure costs. How does regional deployment affect model performance and capabilities? Regional deployment provides access to the same frontier Claude models (Sonnet 4.5, Opus 4.5, and Haiku 4.5) with the same intelligence and performance. All platforms support fundamental capabilities including vision, tool use, and extended context windows. Some advanced features may vary by platform—check the feature support documentation for AWS Bedrock, GCP Vertex, and Microsoft Foundry—or reach out to our sales team—to confirm specific capabilities for your needs. Prev Prev Next Next Get started with regional deployment Visit Trust Center Visit Trust Center Visit Trust Center Contact sales Contact sales Contact sales Homepage Homepage Next Next Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Write Button Text Button Text Learn Button Text Button Text Code Button Text Button Text Write Help me develop a unique voice for an audience Hi Claude! Could you help me develop a unique voice for an audience? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Improve my writing style Hi Claude! Could you improve my writing style? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Brainstorm creative ideas Hi Claude! Could you brainstorm creative ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Learn Explain a complex topic simply Hi Claude! Could you explain a complex topic simply? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Help me make sense of these ideas Hi Claude! Could you help me make sense of these ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Prepare for an exam or interview Hi Claude! Could you prepare for an exam or interview? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Code Explain a programming concept Hi Claude! Could you explain a programming concept? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Look over my code and give me tips Hi Claude! Could you look over my code and give me tips? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Vibe code with me Hi Claude! Could you vibe code with me? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! More Write case studies This is another test Write grant proposals Hi Claude! Could you write grant proposals? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to — like Google Drive, web search, etc. — if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can - an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Write video scripts this is a test Anthropic Anthropic © [year] Anthropic PBC Products Claude Claude Claude Claude Code Claude Code Claude Code Max plan Max plan Max plan Team plan Team plan Team plan Enterprise plan Enterprise plan Enterprise plan Download app Download app Download app Pricing Pricing Pricing Log in Log in Log in Features Claude in Chrome Claude in Chrome Claude in Chrome Claude in Slack Claude in Slack Claude in Slack Claude in Excel Claude in Excel Claude in Excel Skills Skills Skills Models Opus Opus Opus Sonnet Sonnet Sonnet Haiku Haiku Haiku Solutions AI agents AI agents AI agents Code modernization Code modernization Code modernization Coding Coding Coding Customer support Customer support Customer support Education Education Education Financial services Financial services Financial services Government Government Government Healthcare Healthcare Healthcare Life sciences Life sciences Life sciences Nonprofits Nonprofits Nonprofits Claude Developer Platform Overview Overview Overview Developer docs Developer docs Developer docs Pricing Pricing Pricing Regional Compliance Regional Compliance Regional Compliance Amazon Bedrock Amazon Bedrock Amazon Bedrock Google Cloud’s Vertex AI Google Cloud’s Vertex AI Google Cloud’s Vertex AI Console login Console login Console login Learn Blog Blog Blog Claude partner network Claude partner network Claude partner network Courses Courses Courses Connectors Connectors Connectors Customer stories Customer stories Customer stories Engineering at Anthropic Engineering at Anthropic Engineering at Anthropic Events Events Events Powered by Claude Powered by Claude Powered by Claude Service partners Service partners Service partners Startups program Startups program Startups program Tutorials Tutorials Tutorials Use cases Use cases Use cases Company Anthropic Anthropic Anthropic Careers Careers Careers Economic Futures Economic Futures Economic Futures Research Research Research News News News Responsible Scaling Policy Responsible Scaling Policy Responsible Scaling Policy Security and compliance Security and compliance Security and compliance Transparency Transparency Transparency Help and security Availability Availability Availability Status Status Status Support center Support center Support center Terms and policies Privacy choices Cookie settings We use cookies to deliver and improve our services, analyze site usage, and if you agree, to customize or personalize your experience and market our services to you. You can read our Cookie Policy here . Customize cookie settings Reject all cookies Accept all cookies Necessary Enables security and basic functionality. Required Analytics Enables tracking of site performance. Off Marketing Enables ads personalization and tracking. Off Save preferences Privacy policy Privacy policy Privacy policy Responsible disclosure policy Responsible disclosure policy Responsible disclosure policy Terms of service: Commercial Terms of service: Commercial Terms of service: Commercial Terms of service: Consumer Terms of service: Consumer Terms of service: Consumer Usage policy Usage policy Usage policy x.com x.com LinkedIn LinkedIn YouTube YouTube Instagram Instagram English (US) English (US) 日本語 (Japan) Deutsch (Germany) Français (France) 한국어 (South Korea) | 2026-01-13T08:47:52 |
https://claude.com/solutions/coding | Coding | Claude -------> Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Solutions Solutions / Coding Explore here Ask questions about this page Copy as markdown The best AI for developers Claude is the not-so-secret advantage for world class engineering teams and software companies. Start building Start building Start building Contact sales Contact sales Contact sales Play video Play video 80.9% Opus 4.5 leads on SWE-bench Verified 60x faster code review feedback for an AI platform customer 95% reduction in time to run tests for an enterprise software customer Write code with Claude Get complete insight into your codebase and accelerate exceptional software. View prompt View prompt View prompt Prompt > claude fix the authentication error in our login flow I'll investigate the auth error. Let me look at the relevant files. Examining auth-related files... * src/services/authService.js * src/components/Login.jsx * src/store/authSlice.js Running the login flow... Error detected: "401 Unauthorized: Token expired" Root cause: * Token refresh mechanism not handling expired tokens correctly * Refresh token missing from request header * Improper error handling for 401 responses Updating authService.js with proper refresh logic... Updating request interceptor for 401 handling... Testing the fix... * Login successful ✓ * Token refresh working ✓ * Proper redirection on expired tokens ✓ Authentication error fixed! The login flow now properly handles token expiration. Scale coding impact, not overhead Write, test, and debug complex software with Claude , analyze codebases with expert-level reasoning via GitHub integration, delegate development tasks through computer use, and fast-track smarter engineering decisions in a shared workspace. Explore agentic coding with Claude Code Claude Code brings Sonnet 4.5 right to your terminal, with deep codebase awareness and the ability to edit files and run commands directly in your environment. Learn more Learn more Learn more Developers love Claude “I taught a friend who has never written code in her life how to use Claude to build a simple app and deploy it on Cloudflare today. Watching someone realize that they can now build software is a great experience. Enable everyone to build anything.” Logan Grasby, @LoganGrasby “I introduced someone to Claude Code, Opus last night, and we were up til 4 am building a project. It was crazy! 20K lines of codes, audit logging, a full Prisma Database, complete architecture, and a complete roadmap with 4 phases for complete implementation.” Teneika Askew, @teneikaask_you “Just taught my fiancée how to use claude to write code that automates dumb tasks that have been making her work life miserable for months. She went from being downtrodden and skeptical to dancing around the room in about 15 minutes. END USER PROGRAMMING IS NOW.” Kasey, @kaseyklimes “Claude 4 Opus is exactly the future we were promised. I sit down, prompt a little bit, check to make sure the program is doing what i wanted. “8 hours” of work done with almost no labor or input from me. Now time to go get ice cream and watch Twitch until I get more tokens.” @airkatakana “I know this sounds cringe, but I literally have clammy hands and a racing heart because of how powerful Claude + Cursor is. Like I just made a whole new feature, frontend and backend, built on top of my own custom APIs without touching code, then I had it switch from a SwiftUI.” Majd Taby, @jtaby “Claude Code + Opus 4 is the best agentic coding tool in the world and it’s not close.” Mckay Wrigley, @mckaywrigley “Anthropic is leading the Industry with models - like Sonnet and Opus - and developer tools - like Claude Code.” Jon Meyers, @jonmeyers_io “With new Claude i officially feel like a fraud when i code, I’m the guy in the corner saying um nice job boss keep going.” Nick, @nickcammarata Prev Prev 0 / 5 Next Next Build products with the Claude Developer Platform Integrate Claude’s powerful AI capabilities into your apps and deliver production-grade solutions faster. View prompt View prompt View prompt Existing prompt Classify all customer support tickets into the most relevant category. Here is the list of categories to choose from: {{CATEGORY_LIST}} Here is the content of the support ticket: {{TICKET_CONTENT}} What would you like to improve? Please include a rationale for the classification. You are an AI assistant specialized in classifying customer support tickets. Your task is to analyze the content of a given ticket and assign it to the most appropriate category from a predefined list. You will also provide reasoning for your classification decision. First, let's review the available categories: <category_list> {{CATEGORY_LIST}} </category_list> Now, here is the content of the support ticket you need to classify: <ticket_content> {{TICKET_CONTENT}} </ticket_content> Please follow these steps to complete the task: – Carefully read and analyze the ticket content. – Consider how the content relates to each of the available categories. – Choose the most appropriate category for the ticket. – Provide a detailed explanation of your reasoning process. Use the following structure for your response: <classification_analysis> In this section, break down your thought process: – Quote the most relevant parts of the ticket content. – List each category and note how it relates to the ticket content. – For each category, provide arguments for and against classifying the ticket into that category. – Rank the top 3 most likely categories. </classification_analysis> <classification> <category>Your chosen category goes here</category> <reasoning>A concise summary of your reasoning for choosing this category</reasoning> </classification> Remember to be thorough in your analysis and clear in your explanation. Your goal is to provide an accurate classification with well-supported reasoning. Deliver amazing AI experiences Customize how Claude fits into your solution with our API Improve and evaluate your prompts in the Workbench Build frontier intelligence into your applications Turn anyone into an AI developer with rich docs and tooling See why companies choose Claude "Claude Opus 4.5 delivers high-quality code and excels at powering heavy-duty agentic workflows with GitHub Copilot. Early testing shows it surpasses internal coding benchmarks while cutting token usage in half, and is especially well-suited for tasks like code migration and code refactoring." Mario Rodriguez, Chief Product Officer, GitHub "Claude Opus 4.5 is a notable improvement over the prior Claude models inside Cursor, with improved pricing and intelligence on difficult coding tasks." Michael Truell, CEO & Co-founder “Claude Opus 4.5 delivers measurable gains where it matters most: stronger results on our hardest evaluations and consistent performance through 30-minute autonomous coding sessions.” Scott Wu, CEO, Cognition "Opus 4.5 beats Sonnet 4.5 and competition on our internal benchmarks, using fewer tokens to solve the same problems. At scale, that efficiency compounds." Michele Catasta, President “Claude Opus 4.5 handles long-horizon coding tasks more efficiently than any model we’ve tested. It achieves higher pass rates on held-out tests while using up to 65% fewer tokens, giving developers real cost control without sacrificing quality.” Sean Ward, CEO and Co-founder "Claude Opus 4.5 is yet another example of Anthropic pushing the frontier of general intelligence. It performs exceedingly well across difficult coding tasks, showcasing long-term goal-directed behavior." Eno Reyes, CTO and cofounder "Claude Opus 4.5 achieved state-of-the-art results for complex enterprise tasks on our benchmarks, outperforming previous models on multi-step reasoning tasks that combine information retrieval, tool use, and deep analysis." Kay Zhu, CTO "We've found that Opus 4.5 excels at interpreting what users actually want, producing shareable content on the first try. Combined with its speed, token efficiency, and surprisingly low cost, it's the first time we're making Opus available in Notion Agent." Sarah Sachs, AI Lead Engineer "Claude Opus 4.5 represents a breakthrough in self-improving AI agents. For automation of office tasks, our agents were able to autonomously refine their own capabilities—achieving peak performance in 4 iterations while other models couldn’t match that quality after 10. They also demonstrated the ability to learn from experience across technical tasks, storing insights and applying them later." Yusuke Kaji, General Manager (AI) "Claude Opus 4.5 catches more issues in code reviews without sacrificing precision. For production code review at scale, that reliability matters." David Loker, Director of AI "Based on testing with Junie, our coding agent, Claude Opus 4.5 outperforms Sonnet 4.5 across all benchmarks. It requires fewer steps to solve tasks and uses fewer tokens as a result. This indicates that the new model is more precise and follows instructions more effectively — a direction we’re very excited about." Andrew Zakonov, VP of Business, Junie & Kineto "Claude Opus 4.5 is the only model that nails some of our hardest 3D visualizations. Polished design, tasteful UX, and excellent planning & orchestration - all with more efficient token usage. Tasks that took previous models 2 hours now take thirty minutes." Madhav Jha, CTO "We're seeing 50% to 75% reductions in both tool calling errors and build/lint errors with Claude Opus 4.5. It consistently finishes complex tasks in fewer iterations with more reliable execution." Nicholas Charriere, Founder and CEO "Claude Opus 4.5 delivered an impressive refactor spanning two codebases and three coordinated agents. It was very thorough, helping develop a robust plan, handling the details and fixing tests. A clear step forward from Sonnet 4.5." Paulo Arruda, Staff Engineer, AI Productivity "Claude Opus 4.5 excels at long-horizon, autonomous tasks, especially those that require sustained reasoning and multi-step execution. In our evaluations it handled complex workflows with fewer dead-ends. On Terminal Bench it delivered a 15% improvement over Sonnet 4.5, a meaningful gain that becomes especially clear when using Warp’s Planning Mode." Zach Lloyd Founder & CEO Warp Prev Prev 0 / 5 Next Next 100K+ applications deployed on Google Cloud run 75% engineers saving 8–10+ hours every week Get the technical rundown Learn how to use Claude Code Learn how to use Claude Code Learn how to use Claude Code Developer docs Developer docs Developer docs Start building with our quickstart guides Start building with our quickstart guides Start building with our quickstart guides Quickstart Quickstart Quickstart How Anthropic teams use Claude Code How Anthropic teams use Claude Code How Anthropic teams use Claude Code Case study Case study Case study Homepage Homepage Next Next Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Write Button Text Button Text Learn Button Text Button Text Code Button Text Button Text Write Help me develop a unique voice for an audience Hi Claude! Could you help me develop a unique voice for an audience? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Improve my writing style Hi Claude! Could you improve my writing style? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Brainstorm creative ideas Hi Claude! Could you brainstorm creative ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Learn Explain a complex topic simply Hi Claude! Could you explain a complex topic simply? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Help me make sense of these ideas Hi Claude! Could you help me make sense of these ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Prepare for an exam or interview Hi Claude! Could you prepare for an exam or interview? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Code Explain a programming concept Hi Claude! Could you explain a programming concept? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Look over my code and give me tips Hi Claude! Could you look over my code and give me tips? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Vibe code with me Hi Claude! Could you vibe code with me? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! More Write case studies This is another test Write grant proposals Hi Claude! Could you write grant proposals? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to — like Google Drive, web search, etc. — if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can - an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Write video scripts this is a test Anthropic Anthropic © [year] Anthropic PBC Products Claude Claude Claude Claude Code Claude Code Claude Code Max plan Max plan Max plan Team plan Team plan Team plan Enterprise plan Enterprise plan Enterprise plan Download app Download app Download app Pricing Pricing Pricing Log in Log in Log in Features Claude in Chrome Claude in Chrome Claude in Chrome Claude in Slack Claude in Slack Claude in Slack Claude in Excel Claude in Excel Claude in Excel Skills Skills Skills Models Opus Opus Opus Sonnet Sonnet Sonnet Haiku Haiku Haiku Solutions AI agents AI agents AI agents Code modernization Code modernization Code modernization Coding Coding Coding Customer support Customer support Customer support Education Education Education Financial services Financial services Financial services Government Government Government Healthcare Healthcare Healthcare Life sciences Life sciences Life sciences Nonprofits Nonprofits Nonprofits Claude Developer Platform Overview Overview Overview Developer docs Developer docs Developer docs Pricing Pricing Pricing Regional Compliance Regional Compliance Regional Compliance Amazon Bedrock Amazon Bedrock Amazon Bedrock Google Cloud’s Vertex AI Google Cloud’s Vertex AI Google Cloud’s Vertex AI Console login Console login Console login Learn Blog Blog Blog Claude partner network Claude partner network Claude partner network Courses Courses Courses Connectors Connectors Connectors Customer stories Customer stories Customer stories Engineering at Anthropic Engineering at Anthropic Engineering at Anthropic Events Events Events Powered by Claude Powered by Claude Powered by Claude Service partners Service partners Service partners Startups program Startups program Startups program Tutorials Tutorials Tutorials Use cases Use cases Use cases Company Anthropic Anthropic Anthropic Careers Careers Careers Economic Futures Economic Futures Economic Futures Research Research Research News News News Responsible Scaling Policy Responsible Scaling Policy Responsible Scaling Policy Security and compliance Security and compliance Security and compliance Transparency Transparency Transparency Help and security Availability Availability Availability Status Status Status Support center Support center Support center Terms and policies Privacy choices Cookie settings We use cookies to deliver and improve our services, analyze site usage, and if you agree, to customize or personalize your experience and market our services to you. You can read our Cookie Policy here . Customize cookie settings Reject all cookies Accept all cookies Necessary Enables security and basic functionality. Required Analytics Enables tracking of site performance. Off Marketing Enables ads personalization and tracking. Off Save preferences Privacy policy Privacy policy Privacy policy Responsible disclosure policy Responsible disclosure policy Responsible disclosure policy Terms of service: Commercial Terms of service: Commercial Terms of service: Commercial Terms of service: Consumer Terms of service: Consumer Terms of service: Consumer Usage policy Usage policy Usage policy x.com x.com LinkedIn LinkedIn YouTube YouTube Instagram Instagram English (US) English (US) 日本語 (Japan) Deutsch (Germany) Français (France) 한국어 (South Korea) Why do programmers prefer dark mode? I don't know I don't know I don't know Ask Claude Ask Claude Ask Claude | 2026-01-13T08:47:52 |
https://www.reddit.com/r/AskTechnology/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://www.thedrive.com/news/the-sand-turbine-the-900-rpm-fluid-dynamics-behind-this-perfect-spiral | The Fluid Dynamics Behind This Unreal Ford Raptor Sand Spiral Photo Search for: Latest News News by Brand The Downshift Spy Photos Car Tech Culture Deals Racing Trucks Video Games Watch This Car Reviews The Drive Awards Features Video Shop Buy A Car Merch Search for: svg]:fill-accent-900 [&>svg]:stroke-accent-900"> svg]:fill-accent-900 [&>svg]:stroke-accent-900"> svg]:fill-accent-900 [&>svg]:stroke-accent-900"> svg]:fill-accent-900 [&>svg]:stroke-accent-900"> News News by Brand Ford News Sand Turbine: The Fluid Dynamics Behind This Unreal Ford Raptor Dakar Photo How camera shutter speed and a Method race wheel combined to capture a perfect visualization of aerodynamic flow. By Andrew P. Collins Updated Jan 12, 2026 7:20 PM EST 0 Ford Racing/Instagram (cropped by the author) The biggest car news and reviews, no BS Our free daily newsletter sends the stories that really matter directly to you, every weekday. Email address Sign Up Thank you! Terms of Service & Privacy Policy. We’re not even halfway through January, but Ford Racing already has a candidate for motorsports photo of the year here. One of the Ford Dakar team’s photogs captured the Raptor T1+ at exactly the right camera shutter and wheel speed to give us a spectacular piece of eye candy that doubles as a cool illustration of fluid dynamics. It’s not AI, and it’s not a render—the photo’s credited to Marcin Kin for Ford Racing and Red Bull. Let’s talk about how this almost cartoonishly perfect-looking spiral of sand was captured flying out of the Raptor race car’s aluminum Method 207 Forged Bead Grip wheels. What we’re seeing here is the wheel acting as a centrifugal impeller , or turbine, which is exactly what it’s designed to do. These wheels are shaped to eject brake rotor heat, which you can’t usually “see” in real life. But at the Dakar, heavy Saudi Arabian sand is constantly getting pulled into wheel barrels. Centrifugal force pins the sand against the inner wheel barrel walls, and as you can see, it’s ejected through the gaps between the spokes. These are both banger shots, but that second close-up one is my fave. Ford Racing, Method Wheels on Instagram Ambient temps in the Saudi desert in January aren’t as high as you might expect. It was probably, like, 60°F–75°F when this picture was taken. But the air near the Raptor T1+’s brakes would be a whole lot hotter; those vented discs could hit over 1,000°F while racing. The aluminum wheel itself, which is indeed deliberately designed as a brake heat sink, could be over 200°F. Those temperatures could affect the image in two ways. For one thing, even a tiny amount of moisture present in the sand could create a microscopic steam layer, effectively lubricating the sand flow, contributing to how clean and crisp it looks. The turbulent and hot air loaded with sand, hitting cooler ambient air, could also be creating a schlieren optics situation—that slightly warped visual you can get when there’s a temp disparity. I’m estimating a wheel speed of “900 rpm” based on the tire size and guessed vehicle speed. It’d be speed over diameter times pi , so wheel RPM = v * 1056 (mph to inches-per-minute) / D * pi . In one shot, it’s cresting a dune, but in another, it appears to be driving flat-out on flat terrain, so let’s say that second image was taken at 100 mph for simpliocity. Then it’s (100 * 1056) / (37 * 3.14159) = 908 RPM. And while the axle speed is 100 mph, the top of the tire would be at 200, but the edge of the wheel would be about 45 mph. I’m not sure what you can do with this information besides be really nerdy, but hey, that’s kind of why we’re here. These hype images from before the race capture the sand-flinging effect pretty well, too. Method Wheels The combination of the weight of the sand, the sunlight, and a high shutter speed came together here to create a very cool visual of brake venting. We’re basically seeing the solid-particle version of vortex shedding as the sand is radially accelerated. Normally, when you see a “race truck throwing sand” picture, it’s just a chaotic mass of matter getting kicked around by tire treads—this is a uniquely crisp capture of that environment. Ford’s Raptor race vehicles, made in conjunction with UK rally outfit M-Sport, are taking on the Dakar Rally in a much bigger way this year than last. Competing at the top of the heap, the T1+ class, eight of these Raptors were sent into battle for 2026, while only four took on the Dakar last year. As Ford Racing proclaimed a few days ago, at the start of the 2026 Dakar Rally: “Our earlier years at Dakar were about building knowledge: understanding the race, the rhythms, the terrain, and the operational demands. That phase was necessary. The phase we enter now is different. With scale, experience, and eight Raptors in the field, our mindset has shifted from accumulation to execution. The objective is no longer to validate the program. The objective is to contend for overall victory.” The super high-rez version of the sand-slingin’ image would make a great desktop background … you can download that here for your personal big-screen enjoyment: Ford Racing at 2026 Dakar Rally, Sand Spiral Shot by Marcin Kin Download And as of this writing (eight stages complete, five to go), Ford’s absolutely in contention for the podium. Qatari Nasser Al-Attiyah (a frequent Dakar leader) is in first in his Dacia, but Ford’s Swede Mattias Ekström is right behind him. Ford Raptor vehicles are in four of the top 10 positions at the start of Stage 9. Method shared that the wheels on the Raptor T1+ are its 207 Forged Bead Grip racing wheels, size 17×8.5, and the tires are 37×12.50 BF Goodrich KDR3s. I dropped Ford a line to see if they could name the photographer for us and the Blue Oval’s people confirmed that the main “spiral” shot was by Marcin Kin for Ford Racing and Red Bull. This thing is a beast. Method Wheels Got a tip? Send us a note at tips@thedrive.com. Andrew P. Collins Executive Editor Automotive journalist since 2013, Andrew primarily coordinates features, sponsored content, and multi-departmental initiatives at The Drive. .article-sidebar]:pt-0"> Trending News Are We About to Have an Electric-Motor RPM race? By Stephen Edelstein Honda News John Cena Just Added a Prelude to His Growing Honda Collection By Adam Ismail More in Ford News Ford’s Mustang GT3 Evolution Could Tease a Quicker, Corvette-Beating GTD By Byron Hurd Join Me While I Pour One Out for the Cadillac XT6 By Byron Hurd Lost Ford Probe IV Concept Surfaces on Facebook Marketplace By Adam Ismail Edsel Ford’s Art Deco Hot Rod Gets Remade In Carbon Fiber By Stephen Edelstein SEE MORE More in News by Brand Audi Could Finally Sell Vintage Car Parts in North America By Adam Ismail Porsche’s Emergency Pivot to Gas-Powered 718 Is an Engineering Headache By Adam Ismail The New Nissan Leaf Has a Bunch of 300ZX Easter Eggs By Joel Feder Now You Can Get A Solar Tonneau Cover For Your Rivian R1T By Stephen Edelstein SEE MORE More in News Arizona Bill Considers Removing Speed Limits From Rural Interstates By Caleb Jacobs Vin Diesel Wants Soccer Superstar Cristiano Ronaldo in Fast and Furious By Andrew P. Collins Does Emissions Testing Old Cars Actually Make Sense Anymore? By Byron Hurd Why Do Fake Gear Shifts in EVs Make People so Mad? By Jerry Perez SEE MORE Car news and reviews, no BS Our free daily newsletter sends the stories that really matter directly to you, every weekday. Thank you! Email address Sign Up By signing up you agree to our Terms of Service and Privacy Policy. About Us Watch on YouTube Merch Buy a Car Get in Touch Sitemap Privacy Policy Terms & Conditions FOLLOW US DISCLAIMER(S) © 2026 Recurrent Ventures. All Rights Reserved. Articles may contain affiliate links which enable us to share in the revenue of any purchases made. Some benefits of our Car Shopping program may not be available in your area. Please see terms for details. Do Not Sell or Share My Personal Information . News Video Car Reviews Features The Downshift Spy Photos Gear Deals | 2026-01-13T08:47:52 |
https://github.com/kasznar/geometric-constraint-solver | GitHub - kasznar/geometric-constraint-solver: A Simple Geometric Constraint Solver Skip to content Navigation Menu Toggle navigation Sign in Appearance settings Platform AI CODE CREATION GitHub Copilot Write better code with AI GitHub Spark Build and deploy intelligent apps GitHub Models Manage and compare prompts MCP Registry New Integrate external tools DEVELOPER WORKFLOWS Actions Automate any workflow Codespaces Instant dev environments Issues Plan and track work Code Review Manage code changes APPLICATION SECURITY GitHub Advanced Security Find and fix vulnerabilities Code security Secure your code as you build Secret protection Stop leaks before they start EXPLORE Why GitHub Documentation Blog Changelog Marketplace View all features Solutions BY COMPANY SIZE Enterprises Small and medium teams Startups Nonprofits BY USE CASE App Modernization DevSecOps DevOps CI/CD View all use cases BY INDUSTRY Healthcare Financial services Manufacturing Government View all industries View all solutions Resources EXPLORE BY TOPIC AI Software Development DevOps Security View all topics EXPLORE BY TYPE Customer stories Events & webinars Ebooks & reports Business insights GitHub Skills SUPPORT & SERVICES Documentation Customer support Community forum Trust center Partners Open Source COMMUNITY GitHub Sponsors Fund open source developers PROGRAMS Security Lab Maintainer Community Accelerator Archive Program REPOSITORIES Topics Trending Collections Enterprise ENTERPRISE SOLUTIONS Enterprise platform AI-powered developer platform AVAILABLE ADD-ONS GitHub Advanced Security Enterprise-grade security features Copilot for Business Enterprise-grade AI features Premium Support Enterprise-grade 24/7 support Pricing Search or jump to... Search code, repositories, users, issues, pull requests... --> Search Clear Search syntax tips Provide feedback --> We read every piece of feedback, and take your input very seriously. Include my email address so I can be contacted Cancel Submit feedback Saved searches Use saved searches to filter your results more quickly --> Name Query To see all available qualifiers, see our documentation . Cancel Create saved search Sign in Sign up Appearance settings Resetting focus You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} kasznar / geometric-constraint-solver Public Notifications You must be signed in to change notification settings Fork 1 Star 22 A Simple Geometric Constraint Solver 22 stars 1 fork Branches Tags Activity Star Notifications You must be signed in to change notification settings Code Issues 0 Pull requests 0 Actions Projects 0 Security Uh oh! There was an error while loading. Please reload this page . Insights Additional navigation options Code Issues Pull requests Actions Projects Security Insights kasznar/geometric-constraint-solver main Branches Tags Go to file Code Open more actions menu Folders and files Name Name Last commit message Last commit date Latest commit History 3 Commits cmd cmd docs docs pkg pkg .gitignore .gitignore Makefile Makefile README.md README.md go.mod go.mod go.sum go.sum View all files Repository files navigation README Geometric Constraint Solver A toy geometric constraint solver for learning. Simplified for easy understanding and using only the Go standard library, so there is no magic, just about 2000 lines of code. You can step through it and understand how CAD programs work. It is inspired by SolveSpace , but built independently from the ground up. Geometric constraints are represented as a system of nonlinear equations and solved by multidimensional Newton's method . I built a simple symbolic algebra system that calculates derivatives by traversing the syntax tree. To keep the codebase simple, this implementation assumes that the system will converge. I included a short math summary . Demo solver-demo.mp4 Running the program go run ./cmd About A Simple Geometric Constraint Solver Resources Readme Uh oh! There was an error while loading. Please reload this page . Activity Stars 22 stars Watchers 0 watching Forks 1 fork Report repository Releases No releases published Packages 0 No packages published Languages Go 99.8% Makefile 0.2% Footer © 2026 GitHub, Inc. Footer navigation Terms Privacy Security Status Community Docs Contact Manage cookies Do not share my personal information You can’t perform that action at this time. | 2026-01-13T08:47:52 |
https://future.forem.com/subforems | Subforems - Future Forem Feed Follow new Subforems to improve your feed DEV Community Follow A space to discuss and keep up software development and manage your software career Future Follow News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Open Forem Follow A general discussion space for the Forem community. If it doesn't have a home elsewhere, it belongs here Gamers Forem Follow An inclusive community for gaming enthusiasts Music Forem Follow From composing and gigging to gear, hot music takes, and everything in between. Vibe Coding Forem Follow Discussing AI software development, and showing off what we're building. Popcorn Movies and TV Follow Movie and TV enthusiasm, criticism and everything in-between. DUMB DEV Community Follow Memes and software development shitposting Design Community Follow Web design, graphic design and everything in-between Security Forem Follow Your central hub for all things security. From ethical hacking and CTFs to GRC and career development, for beginners and pros alike Golf Forem Follow A community of golfers and golfing enthusiasts Crypto Forem Follow A collaborative community for all things Crypto—from Bitcoin to protocol development and DeFi to NFTs and market analysis. Parenting Follow A place for parents to the share the joys, challenges, and wisdom that come from raising kids. We're here for them and for each other. Forem Core Follow Discussing the core forem open source software project — features, bugs, performance, self-hosting. Maker Forem Follow A community for makers, hobbyists, and professionals to discuss Arduino, Raspberry Pi, 3D printing, and much more. HMPL.js Forem Follow For developers using HMPL.js to build fast, lightweight web apps. A space to share projects, ask questions, and discuss server-driven templating Dropdown menu Dropdown menu Skip to content Navigation menu Search Powered by Algolia Search Log in Create account Future Close Subforems DEV Community A space to discuss and keep up software development and manage your software career Follow Future News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Follow Open Forem A general discussion space for the Forem community. If it doesn't have a home elsewhere, it belongs here Follow Gamers Forem An inclusive community for gaming enthusiasts Follow Music Forem From composing and gigging to gear, hot music takes, and everything in between. Follow Vibe Coding Forem Discussing AI software development, and showing off what we're building. Follow Popcorn Movies and TV Movie and TV enthusiasm, criticism and everything in-between. Follow DUMB DEV Community Memes and software development shitposting Follow Design Community Web design, graphic design and everything in-between Follow Security Forem Your central hub for all things security. From ethical hacking and CTFs to GRC and career development, for beginners and pros alike Follow Golf Forem A community of golfers and golfing enthusiasts Follow Crypto Forem A collaborative community for all things Crypto—from Bitcoin to protocol development and DeFi to NFTs and market analysis. Follow Parenting A place for parents to the share the joys, challenges, and wisdom that come from raising kids. We're here for them and for each other. Follow Forem Core Discussing the core forem open source software project — features, bugs, performance, self-hosting. Follow Maker Forem A community for makers, hobbyists, and professionals to discuss Arduino, Raspberry Pi, 3D printing, and much more. Follow HMPL.js Forem For developers using HMPL.js to build fast, lightweight web apps. A space to share projects, ask questions, and discuss server-driven templating Follow 💎 DEV Diamond Sponsors Thank you to our Diamond Sponsors for supporting the DEV Community Google AI is the official AI Model and Platform Partner of DEV Neon is the official database partner of DEV Algolia is the official search partner of DEV Future — News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Home About Contact Code of Conduct Privacy Policy Terms of Use Built on Forem — the open source software that powers DEV and other inclusive communities. Made with love and Ruby on Rails . Future © 2025 - 2026. Stay on the cutting edge, and shape tomorrow Log in Create account | 2026-01-13T08:47:52 |
https://www.anthropic.com/learn | Skip to main content Skip to footer Research Economic Futures Commitments Learn News Try Claude Anthropic Academy Get in the know with Anthropic resources. From API development guides to enterprise deployment best practices, the academy has you covered. Featured courses New courses available on Anthropic Academy. Learn more in-depth about AI Fluency, API development, Model Context Protocol and Claude Code. Earn certificates upon completion. See all courses Featured Course Claude Code in Action Featured Course Claude 101 Build with Claude Start developing Claude-powered applications with our comprehensive API guides and best practices Learn more Claude for Work Learn to implement Claude across your organization and maximize team productivity Learn more Claude for Personal Discover how to leverage Claude's capabilities for your individual projects and daily tasks Learn more Products Claude Claude Code Claude in Chrome Claude in Excel Claude in Slack Skills Max plan Team plan Enterprise plan Download app Pricing Log in to Claude Models Opus Sonnet Haiku Solutions AI agents Code modernization Coding Customer support Education Financial services Government Healthcare Life sciences Nonprofits Claude Developer Platform Overview Developer docs Pricing Regional Compliance Amazon Bedrock Google Cloud’s Vertex AI Console login Learn Blog Claude partner network Connectors Courses Customer stories Engineering at Anthropic Events Powered by Claude Service partners Startups program Tutorials Use cases Company Anthropic Careers Economic Futures Research News Responsible Scaling Policy Security and compliance Transparency Help and security Availability Status Support center Terms and policies Privacy policy Consumer health data privacy policy Responsible disclosure policy Terms of service: Commercial Terms of service: Consumer Usage policy © 2025 Anthropic PBC AI Learning Resources & Guides from Anthropic \ Anthropic | 2026-01-13T08:47:52 |
https://github.com/antonzy | antonzy (Anton Zagrebelny) · GitHub Skip to content Navigation Menu Toggle navigation Sign in Appearance settings Platform AI CODE CREATION GitHub Copilot Write better code with AI GitHub Spark Build and deploy intelligent apps GitHub Models Manage and compare prompts MCP Registry New Integrate external tools DEVELOPER WORKFLOWS Actions Automate any workflow Codespaces Instant dev environments Issues Plan and track work Code Review Manage code changes APPLICATION SECURITY GitHub Advanced Security Find and fix vulnerabilities Code security Secure your code as you build Secret protection Stop leaks before they start EXPLORE Why GitHub Documentation Blog Changelog Marketplace View all features Solutions BY COMPANY SIZE Enterprises Small and medium teams Startups Nonprofits BY USE CASE App Modernization DevSecOps DevOps CI/CD View all use cases BY INDUSTRY Healthcare Financial services Manufacturing Government View all industries View all solutions Resources EXPLORE BY TOPIC AI Software Development DevOps Security View all topics EXPLORE BY TYPE Customer stories Events & webinars Ebooks & reports Business insights GitHub Skills SUPPORT & SERVICES Documentation Customer support Community forum Trust center Partners Open Source COMMUNITY GitHub Sponsors Fund open source developers PROGRAMS Security Lab Maintainer Community Accelerator Archive Program REPOSITORIES Topics Trending Collections Enterprise ENTERPRISE SOLUTIONS Enterprise platform AI-powered developer platform AVAILABLE ADD-ONS GitHub Advanced Security Enterprise-grade security features Copilot for Business Enterprise-grade AI features Premium Support Enterprise-grade 24/7 support Pricing Search or jump to... Search code, repositories, users, issues, pull requests... --> Search Clear Search syntax tips Provide feedback --> We read every piece of feedback, and take your input very seriously. Include my email address so I can be contacted Cancel Submit feedback Saved searches Use saved searches to filter your results more quickly --> Name Query To see all available qualifiers, see our documentation . Cancel Create saved search Sign in Sign up Appearance settings Resetting focus You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} antonzy Follow Overview Repositories 44 Projects 0 Packages 0 Stars 202 More Overview Repositories Projects Packages Stars antonzy Follow Anton Zagrebelny antonzy Follow 6 followers · 11 following Achievements x2 x3 Achievements x2 x3 Block or Report Block or report antonzy --> Block user Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users . You must be logged in to block users. Add an optional note Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you. Block user Report abuse Contact GitHub support about this user’s behavior. Learn more about reporting abuse . Report abuse Overview Repositories 44 Projects 0 Packages 0 Stars 202 More Overview Repositories Projects Packages Stars Popular repositories Loading appolo-inject appolo-inject Public Forked from shmoop207/appolo-inject dependency injection for nodejs JavaScript appolo appolo Public Forked from shmoop207/appolo nodejs server framefork JavaScript nodeEventStore nodeEventStore Public Forked from thenativeweb/node-eventstore EventStore Implementation in node.js JavaScript mongo-migrate mongo-migrate Public Forked from afloyd/mongo-migrate JavaScript js-bson js-bson Public Forked from mongodb/js-bson BSON Parser for node and browser JavaScript node-mongodb-native node-mongodb-native Public Forked from mongodb/node-mongodb-native Mongo DB Native NodeJS Driver JavaScript Something went wrong, please refresh the page to try again. If the problem persists, check the GitHub status page or contact support . Uh oh! There was an error while loading. Please reload this page . Footer © 2026 GitHub, Inc. Footer navigation Terms Privacy Security Status Community Docs Contact Manage cookies Do not share my personal information You can’t perform that action at this time. | 2026-01-13T08:47:52 |
https://replit.com/enterprise | Replit for Enterprise | Enterprise Development Platform Agent Products Agent Design Database Publish Security Integrations Mobile For Work Teams Replit for teams to build together Enterprise Replit with Enterprise-grade security & controls Use Cases Business Apps Rapid Prototyping Roles Enterprise PM Designers Operations Software Developers Small Businesses SMB owners Founders Resources Get Started Docs Community Expert Network Inspiration Customer Stories Gallery Blog News Pricing Careers Agent Contact sales Log in Sign up Products For Work Resources Pricing Careers Contact sales Log in Start building End Your Software Backlog. Empower your entire organization to create applications by simply describing them. Replit's enterprise platform translates your description into production-ready software, securely and at scale. Contact Sales First Name (required) Last Name (required) Work Email (required) Phone Number (optional) Message (optional) Contact Sales Loved by 40 million app creators, including teams at: Replit is the most secure agentic platform for production-ready apps Replit’s got everything you need to make building & launching your app a breeze — build & refine your apps through conversing with Agent. Every Replit app comes with a built in database, user-authentication, integrations and Enterprise Grade security. Self-debugging & autonomous agent allows anyone to build complex production grade apps Anyone from your Product, Design or Business teams can build apps and tools within a few prompts. Agent can autonomously handle complex tasks and debugging so you don't have to. In-built Auth, Database, Hosting & Monitoring services make pushing an app to production a breeze Every project includes a pre-configured, production grade Auth and Database that grows with your project-no separate setup or installation needed. You can also easily connect to services like Stripe, Open AI and more. Enterprise controls & security for your apps Replit platform has SSO/SAML, SOC2 & all the standard Enterprise admin controls. Plus, pre deployment security screening, secure in-built services and better defaults ensure the apps you built remain secure too. Jon Humphrey, Rokt SVP of Solutions and Operations "I sat there on an iPad mini and I deployed a fully functional end-to-end application with Google OAuth in about a day. And I have no background in engineering. That was my 'holy shit' moment where I said, 'My goodness, I can't believe I just did that.'" Mike Messenger, Zillow Director of Field Operations “Replit empowers our operations teams to quickly create enterprise-grade apps, no-code needed.” Key Vaidya, Hg Capital Portfolio CTO “The ability to go from idea to working application in minutes has opened new possibilities for innovation across our portfolio. We're seeing apps built in 45 minutes that save teams hours every week." From rapidly prototyping MVPs to building internal tools or customer facing apps, the possibilities are endless Replit’s got everything you need to make building & launching your app a breeze — build & refine your apps through conversing with Agent. Every Replit app comes with a built in database, user-authentication, integrations and Enterprise Grade security. Rapid Prototyping Rapidly prototype your product ideas for customer demos and feedback. Launch it as production ready app or hand it off to engineering for continued development Internal Tools Build that perfect tool you always wanted and simplify your workflow and increase your productivity Customer facing apps Build new, production-ready apps for your customers much faster via faster prototyping and more seamless handoff from product to engineering teams Purchase Replit Enterprise Through Your Preferred Cloud Marketplace Replit Enterprise is now available on Azure Marketplace and Google Cloud Marketplace, making it easier than ever to procure our agentic development platform through your existing cloud provider relationship. Streamlined procurement — Use existing cloud credits, consolidated billing, and pre-approved vendor relationships Available on Azure Marketplace and Google Cloud Marketplace Enterprise features include — SSO/SAML, SCIM provisioning, dedicated support, and advanced privacy controls Empower your Product, Design & Business teams to bring their ideas to life Product Teams Quickly prototype and test your product ideas with clickable prototypes to speed up customer demos, gather feedback faster, and dramatically shorten your product development cycle. Don’t just hand off a PRD to engineering—hand off working source code. Designers Bring your Figma designs to life and simplify that developer handoff by building out a clickable prototype. Now your designs can be transferred to product with perfect fidelity. Sales & Marketing Teams Build that perfect tool you always wanted and simplify your workflow and increase productivity. Where you want to analyze sales call transcripts or generate quick landing pages for marketing, you can do it all with a Replit app Operations Teams Build that perfect tool you always wanted and simplify your workflow and increase productivity. Where you want to build a custom dashboard to analyze support tickets, or a procurement tool, you can build it all with a Replit app. Request a hackathon Transform your organization in 4 hours Solve real business challenges Cross-functional teams build apps that address your organizations actual needs and pain points. No coding required Anyone can participate regardless of technical background—vibe coding makes programming accessible to all. Deploy live applications Teams go from idea to working application in just 4 hours, ready to showcase and implement. Request a Hackathon Try Replit now Replit empowers anyone with an idea to become a creator, while giving professional designers the freedom to creatively explore and build — without being held back by code or the limitations of design tools: Start building Handy Links About us Vibe Coding 101 Help How to guides Import from GitHub Status Additional resources Brand kit Partnerships Legal Terms of service Commercial agreement Privacy Subprocessors DPA Report abuse Connect X / Twitter Tiktok Facebook Instagram Linkedin Scroll to top All rights reserved. Copyright © 2026 Replit, Inc. | 2026-01-13T08:47:52 |
https://replit.com/products/mobile | Mobile - Replit Agent Products Agent Design Database Publish Security Integrations Mobile For Work Teams Replit for teams to build together Enterprise Replit with Enterprise-grade security & controls Use Cases Business Apps Rapid Prototyping Roles Enterprise PM Designers Operations Software Developers Small Businesses SMB owners Founders Resources Get Started Docs Community Expert Network Inspiration Customer Stories Gallery Blog News Pricing Careers Agent Contact sales Log in Sign up Products For Work Resources Pricing Careers Contact sales Log in Start building Join 40M+ creators making apps with Replit Create, share, and host web apps all from the palm of your hand. Download the app on Android or iOS. Get it on Google Play Download on the App Store Start by chatting with Agent Watch your app ideas come to life Add features with natural language View progress as you chat Deploy live to the internet, securely What are you waiting for? Get it on Google Play Download on the App Store Handy Links About us Vibe Coding 101 Help How to guides Import from GitHub Status Additional resources Brand kit Partnerships Legal Terms of service Commercial agreement Privacy Subprocessors DPA Report abuse Connect X / Twitter Tiktok Facebook Instagram Linkedin Scroll to top All rights reserved. Copyright © 2026 Replit, Inc. | 2026-01-13T08:47:52 |
https://nba.2k.com/2k25/faq/?c | FAQs | NBA 2K25 BUY NOW EN character if not provided --> ENGLISH (EN) ENGLISH (GB) FRANÇAIS (FR) ITALIANO (IT) DEUTSCH (DE) ESPAÑOL (ES) ESPAÑOL (MX) PORTUGUÊS (BR) 日本語 (JP) 한국어 (KR) 繁體中文 (TW) 简体中文 (CN) FEATURES & GAME MODES FEATURES & GAME MODES TEAM 2K 2K BEATS GRAVITY BALL COMMUNITY COMMUNITY TWITCH DROPS DISCORD LOGO GAUNTLET SEASON PLAYBOOK BLEACHER REPORT #1 NEWS NEWS COURTSIDE REPORTS PATCH NOTES SUPPORT & FAQS SUPPORT & FAQS FAQs LEAGUE PASS FAQs SEASON PASS FAQs PC FAQs GRAVITY BALL FAQs MyTEAM MOBILE FAQs MANUALS SERVER STATUS 2K SUPPORT OUR GAMES OUR GAMES NBA 2K26 NBA 2K24 NBA 2K23 NBA 2K22 NBA 2K21 NBA 2K20 MyNBA NBA 2K MOBILE EN character if not provided --> ENGLISH (EN) ENGLISH (GB) FRANÇAIS (FR) ITALIANO (IT) DEUTSCH (DE) ESPAÑOL (ES) ESPAÑOL (MX) PORTUGUÊS (BR) 日本語 (JP) 한국어 (KR) 繁體中文 (TW) 简体中文 (CN) NBA 2K25 FAQs Q: When is the release date for NBA 2K25? A: NBA 2K25 will be available globally on September 6, 2024. Q: What platforms will I be able to purchase NBA 2K25 on? A: NBA 2K25 will be available for purchase on PlayStation®5, Xbox Series X|S, PlayStation®4, Xbox One, Nintendo Switch, and Steam for PC. Q: What Editions will be available for purchase this year? A: NBA 2K25 will offer four different versions of the game: Standard Edition, WNBA Edition, All-Star Edition, and the Hall of Fame Edition. You can learn more about the different editions on the Buy page. Q: What’s included in the NBA 2K25 All-Star Edition? A: Digital copies of the NBA 2K25 All-Star Edition on PlayStation®5, Xbox Series X|S, PlayStation®4, Xbox One, Nintendo Switch, and Steam for PC are available for purchase, and include the base game, 100,000 VC, Dual Entitlement, the MyTEAM Promo Box, and MyCAREER content to be detailed at a later date. NBA 2K25 All-Star Edition is not available in Belgium. Q: Will physical versions of the All-Star Edition be available for purchase? A: All-Star Edition has limited physical availability for PlayStation®5 and will include a code in the box with bonus content for the following countries: Spain, France, Germany, ANZ (Australia and New Zealand), RoA (Singapore, Taiwan, Hong Kong) Q: What’s included in the NBA 2K25 Hall of Fame Edition? A: The NBA 2K25 Hall of Fame Edition includes the base game, a 12-month NBA League Pass subscription, the Season 1 Pro Pass, 100,000 VC, Dual Entitlement, the MyTEAM Promo Box, and MyCAREER content. NBA 2K25 Hall of Fame Edition is not available in Belgium. Q: How can I learn more about the 12-month subscription to NBA League Pass*? A: You can find more information about the 12-month subscription to NBA League Pass included with NBA 2K25 Hall of Fame Edition here: https://nba.2k.com/2k25/league-pass-faq/ Q: Is the 12-month subscription to NBA League Pass included with the Hall of Fame Edition offered worldwide? A: The 12-month subscription to NBA League Pass is not available with the NBA 2K25 Hall of Fame Edition in Japan or China. Also, NBA League Pass is not available in Belarus, Cuba, Iran, Iraq, Libya, Kosovo, North Korea, Russia, South Sudan, Sudan, Swaziland, or Syria. Q: Where can I purchase digital copies of NBA 2K25 Hall of Fame Edition? A: The NBA 2K25 Hall of Fame Edition for PlayStation®5, Xbox Series X|S, PlayStation®4, Xbox One, and Steam for PC has limited availability and is only available until September 8, 2024. Visit our Buy page to purchase your copy or for more details. Q: Where can I purchase physical copies of NBA 2K25 WNBA Edition? A: You can purchase physical copies of NBA 2K25 WNBA Edition for PlayStation®5 and Xbox Series X|S exclusively in the United States and Canada at GameStop. Q: What platforms will New Gen be available for? A: New Gen versions of NBA 2K25 will be available on PlayStation®5, Xbox Series X|S, and Steam for PC. Q: Will there be crossplay in NBA 2K25? A: Enjoy crossplay and play with your friends in NBA 2K25 across PlayStation®5 and Xbox Series X|S consoles. You can experience cross-platform competition in co-op matches and online tournaments on PS5® and Xbox Series X|S consoles.** Q: Will there be cross-gen progression in NBA 2K25? A: NBA 2K25 features MyTEAM Cross-Progression and a Shared VC Wallet within the same console family (PlayStation®4 and PlayStation®5, or Xbox One and Xbox Series X|S). MyTEAM Cross-Progression enables all MyTEAM Points, cards and progress to be shared across both versions of NBA 2K25 on generations of consoles in the same console family. Similarly, the Shared VC Wallet allows any earned or purchased VC to be accessible across generations of consoles in the same console family. Q: How does dual entitlement work for NBA 2K25? A: Players that purchase the digital versions of the Standard, All-Star, or Hall of Fame Edition will receive both versions of NBA 2K25 across generations of consoles from the same console family (PlayStation®4 and PlayStation®5, or Xbox One and Xbox Series X|S). Using PlayStation®4 as an example, you will receive the PlayStation®4 version of NBA 2K25 and an accompanying digital copy of the PlayStation®5 version, which remains a separate product. For digital purchases of the Standard, All-Star, or Hall of Fame Edition, the accompanying digital copy will be automatically entitled to your platform account. For physical purchases of the Standard Edition and All-Star Edition, a redemption code for the accompanying digital copy will be included in the game box. More information on the different editions is available on the Buy page. Q: How do I receive the Trendsetter bonus offer? A: Trendsetter bonus offer is available on purchases of any edition of NBA 2K25 through October 17, 2024. Trendsetter bonus content will be available to redeem via the Season Pass page in-game and must be redeemed by October 17, 2024. Internet connection and NBA 2K Account required to redeem and use bonus content. Terms apply. *Offer only available with purchases of the NBA 2K25 Hall of Fame Edition (Digital). The Hall of Fame Edition (Digital) will only be available through September 8, 2024. Not available on Nintendo Switch. See https://nba.2k.com/2k25/faq/ for availability details. NBA League Pass code will be delivered to the email address associated with the NBA 2K Account with which the Hall of Fame Edition Bonus Content was redeemed within 3 days of redemption (but no earlier than October 7, 2024). If you return your purchase or do not redeem the code for your Bonus Content in-game before December 1, 2024, you will not receive your NBA League Pass code. Code for NBA League Pass must be redeemed by December 31, 2024. Any codes for NBA League Pass not redeemed by such date will be void. Limit one (1) NBA League Pass code per person or account. Each code can only be used once and subsequent attempts to re-submit or re-use the same code will be void. If a person enters the same code into multiple accounts or attempts to establish multiple accounts, the code and/or account may be void. Code has no cash value. To the extent permitted by law, in-game items are provided "as is” with no warranty or guarantee. Codes cannot be substituted, transferred, sold, bartered or auctioned. If any code or redemption thereof is counterfeited, or if any part of a code is illegible, mutilated or tampered with in any way or obtained through illegitimate means, or if a code contains or reflects printing, typographical, mechanical or other errors, the code and/or redemption thereof, as applicable, will be rejected and will be deemed void and invalid. Liability for an irregular code is limited to providing another code, subject to verification of original code irregularity. NBA League Pass valid for 12 months from redemption and auto-renews monthly unless canceled prior to the renewal date at the then-current published MSRP for NBA League Pass in your territory. You will be notified in advance of auto-renew and will be able to opt-out before auto-renewal without being charged. Full auto-renewal details, including how to cancel: https://support.watch.nba.com/hc/en-us/articles/360055657714-Auto-Renewal-Policy . Credit Card, NBA 2K Account and NBA Account required. NBA League Pass is provided by NBA Properties, Inc. NBA Properties Inc. is solely responsible and liable for the NBA League Pass service and you must accept the NBA League Pass Subscriber Agreement here for U.S.: https://www.nba.com/subscriberagreement and here for outside of the U.S.: https://www.nba.com/league-pass-termsofuse-outside-us . Offer not available in Japan, China or Belgium. NBA League Pass not available in Belarus, China, Cuba, Iran, Iraq, Ivory Coast, Japan, Libya, Kosovo, North Korea, Russia, Rwanda, South Sudan, Sudan, Swaziland and Syria. See https://nba.2k.com/2k25/league-pass-faq / , for full terms, availability, redemption and cancellation instructions. **Crossplay is only available on PS5 ® and Xbox Series X|S console versions of NBA 2K25. NBA 2K Account, internet connection, and separate, paid online console subscription required. 2K.COM NBA 2K SUPPORT 2K STORE 2K ACCOUNT LOGIN PRIVACY POLICY TERMS OF SERVICE COOKIE POLICY 2K AD PARTNERS DO NOT SELL OR SHARE MY PERSONAL INFORMATION Cookie Settings © 2005-2025 Take-Two Interactive Software, Inc. Published by 2K. 2K, T2, and related logos, are all trademarks and/or registered trademarks of Take-Two Interactive Software, Inc. The NBA and individual NBA member team identifications reproduced on this product are trademarks and copyrighted designs, and/or other forms of intellectual property, that are the exclusive property of NBA Properties, Inc. and the respective NBA member teams and may not be used, in whole or in part, without the prior written consent of NBA Properties, Inc. © 2025 NBA Properties, Inc. All rights reserved. © 2025 the National Basketball Players Association. All rights reserved. © 2025 Sony Interactive Entertainment LLC. “PlayStation Family Mark”, “PlayStation”, “PS5 logo”, “PS5”, “PS4 logo”, “PS4”, “PlayStation Shapes Logo” and “Play Has No Limits” are registered trademarks or trademarks of Sony Interactive Entertainment Inc. Microsoft, the Xbox Sphere mark, the Series X logo, Series S logo, Series X|S logo, Xbox One, Xbox Series X, Xbox Series S, and Xbox Series X|S are trademarks of the Microsoft group of companies. Nintendo Switch is a trademark of Nintendo. The ESRB ratings icon is a trademark of the Entertainment Software Association. All other marks and trademarks are the property of their respective owners. All rights reserved. | 2026-01-13T08:47:52 |
https://future.forem.com/t/space | Space - Future Forem Feed Follow new Subforems to improve your feed DEV Community Follow A space to discuss and keep up software development and manage your software career Future Follow News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Open Forem Follow A general discussion space for the Forem community. If it doesn't have a home elsewhere, it belongs here Gamers Forem Follow An inclusive community for gaming enthusiasts Music Forem Follow From composing and gigging to gear, hot music takes, and everything in between. Vibe Coding Forem Follow Discussing AI software development, and showing off what we're building. Popcorn Movies and TV Follow Movie and TV enthusiasm, criticism and everything in-between. DUMB DEV Community Follow Memes and software development shitposting Design Community Follow Web design, graphic design and everything in-between Security Forem Follow Your central hub for all things security. From ethical hacking and CTFs to GRC and career development, for beginners and pros alike Golf Forem Follow A community of golfers and golfing enthusiasts Crypto Forem Follow A collaborative community for all things Crypto—from Bitcoin to protocol development and DeFi to NFTs and market analysis. Parenting Follow A place for parents to the share the joys, challenges, and wisdom that come from raising kids. We're here for them and for each other. Forem Core Follow Discussing the core forem open source software project — features, bugs, performance, self-hosting. Maker Forem Follow A community for makers, hobbyists, and professionals to discuss Arduino, Raspberry Pi, 3D printing, and much more. HMPL.js Forem Follow For developers using HMPL.js to build fast, lightweight web apps. A space to share projects, ask questions, and discuss server-driven templating Dropdown menu Dropdown menu Skip to content Navigation menu Search Powered by Algolia Search Log in Create account Future Close # space Follow Hide Discussions about space exploration, astronomy, and cosmology. Create Post Posts Left menu 👋 Sign in for the ability to sort posts by relevant , latest , or top . Right menu The Wonders of Cosmic Physics: From Black Holes to Dark Matter sydne sloan sydne sloan sydne sloan Follow Nov 29 '25 The Wonders of Cosmic Physics: From Black Holes to Dark Matter # science # space Comments Add Comment 3 min read Why Blue Origin’s Mars Launch Matters Now Qwegle Tech Qwegle Tech Qwegle Tech Follow Nov 15 '25 Why Blue Origin’s Mars Launch Matters Now # blueorigin # space # nasa # qwegle Comments Add Comment 4 min read SpaceX vs Blue Origin: Why the Next Big Shock in Spaceflight Might Come From Bezos, Not Musk Mashraf Aiman Mashraf Aiman Mashraf Aiman Follow Nov 23 '25 SpaceX vs Blue Origin: Why the Next Big Shock in Spaceflight Might Come From Bezos, Not Musk # news # space # ai # machinelearning 1 reaction Comments Add Comment 3 min read 📰 Major Tech News: September 20, 2025 Om Shree Om Shree Om Shree Follow Sep 20 '25 📰 Major Tech News: September 20, 2025 # ai # space # productivity # blockchain 22 reactions Comments 6 comments 6 min read loading... trending guides/resources The Wonders of Cosmic Physics: From Black Holes to Dark Matter Why Blue Origin’s Mars Launch Matters Now SpaceX vs Blue Origin: Why the Next Big Shock in Spaceflight Might Come From Bezos, Not Musk 💎 DEV Diamond Sponsors Thank you to our Diamond Sponsors for supporting the DEV Community Google AI is the official AI Model and Platform Partner of DEV Neon is the official database partner of DEV Algolia is the official search partner of DEV Future — News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Home About Contact Code of Conduct Privacy Policy Terms of Use Built on Forem — the open source software that powers DEV and other inclusive communities. Made with love and Ruby on Rails . Future © 2025 - 2026. Stay on the cutting edge, and shape tomorrow Log in Create account | 2026-01-13T08:47:52 |
https://blogs.windows.com/windowsdeveloper/2020/05/19/introducing-winui-3-preview-1/ | Introducing WinUI 3 Preview 1 - Windows Developer Blog Skip to main content Skip to main content Microsoft Windows Blogs Windows Blogs Windows Blogs Home Windows Experience Devices Windows Developer Microsoft Edge Windows Insider Microsoft 365 More All Microsoft Global Microsoft 365 Teams Copilot Windows Surface Xbox Deals Small Business Support Software Software Windows Apps AI Outlook OneDrive Microsoft Teams OneNote Microsoft Edge Moving from Skype to Teams PCs & Devices PCs & Devices Computers Shop Xbox Accessories VR & mixed reality Certified Refurbished Trade-in for cash Entertainment Entertainment Xbox Game Pass Ultimate PC Game Pass Xbox games PC games Business Business Microsoft Security Dynamics 365 Microsoft 365 for business Microsoft Power Platform Windows 365 Microsoft Industry Small Business Developer & IT Developer & IT Azure Microsoft Developer Microsoft Learn Support for AI marketplace apps Microsoft Tech Community Microsoft Marketplace Marketplace Rewards Visual Studio Other Other Microsoft Rewards Free downloads & security Education Gift cards Licensing Unlocked stories View Sitemap Search Search blogs.windows.com No results Cancel / Windows Developer Blog Share on Facebook Share on X Share on LinkedIn Share on Threads Subscribe to RSS May 19, 2020 PC Introducing WinUI 3 Preview 1 Ryan Demopoulos Today at Microsoft Build 2020 the WinUI team is excited to announce the latest version of WinUI 3 available for public preview: WinUI 3 Preview 1 . This preview expands the world of WinUI to an even wider audience of developers – the previously-released WinUI 3 Alpha was only available to UWP app developers, but Preview 1 now enables WinUI usage in Desktop (Win32) apps as well! What is WinUI? WinUI is Microsoft’s most advanced user interface technology for building Windows apps. There are two versions of WinUI in active development: WinUI 2 and WinUI 3. WinUI 2 is a library of Fluent-based UI controls & styles for UWP XAML apps; it was first shipped in Oct 2018 and its latest release is v2.4 which came out recently on May 8 th . WinUI 3 is a currently-in-development, dramatic expansion of this library into a full-fledged, end-to-end, standalone UI framework. This UI framework continues the tradition of WinUI and UWP XAML, providing the very latest graphical capabilities and Fluent Design styling that embraces today’s modern devices, hardware, and inputs. Technically, WinUI 3 decouples the XAML, Composition, and Input layers of Windows 10, and ships them independently via NuGet for any app targeting Windows 10 1803 and above. It can be used in both C++ and .NET-based apps. WinUI 3 Preview 1 is the first pre-release of WinUI 3 that can be used in both UWP and Desktop apps, allowing every developer a chance to tap into the very latest UI technologies from Microsoft for building Windows apps. You can learn more about WinUI here . What’s new in WinUI 3 Preview 1? In addition to the aforementioned ability to use WinUI from Desktop apps, Preview 1 will also support .NET 5 when run in this Desktop context. Preview 1 is also the first preview of WinUI 3 to include the SwapChainPanel control – this is key for developers working with DirectX for providing custom graphical rendering as a part of their user experience. In February, the WinUI team released an Alpha of WinUI 3 with an all-new Chromium-based WebView2 control. This same control carries through to Preview 1 and has been updated with several improvements. Preview 1 also offers several other advancements compared to the February Alpha: Support for the .NET versions of several interfaces when using .NET 5. In Preview1, .NET 5 is used with Desktop apps. The interfaces (and a class) are: INotifyPropertyChanged, INotifyCollectionChanged, ObervableCollection<T>, and ICommand. New, recently released controls ported forward from WinUI v2.4. Several important bug fixes & stability improvements. A full articulation of the capabilities and limitations of Preview 1 can be found in the WinUI 3 Preview 1 Release Notes . Of special note: Preview 1 should not be used in production apps, as it does not guarantee forward compatibility and may break in future updates we make to Windows 10. Who’s using WinUI? At Build 2020 we’ll share stories of customers and ecosystem partners we’re working with to improve & develop WinUI 3. Examples of these partnerships that will be referenced during the conference include: Magix , a developer of audio & video solutions for creators, who’s showcasing how they’ve harnessed the power of WinUI to modernize some of the UI components in their Win32-based VEGAS Pro app Esri , market leader in geographic information system (GIS) software, using ArcGIS Runtime , .NET and SwapChainPanel with WinUI 3 Preview 1 to render gigabytes of geospatial data in rich, high performance mapping components Telerik , a leading vendor of high quality .NET and JavaScript components for building modern, high performance, feature rich web, mobile and desktop apps Uno platform , an open source platform for building apps that span across mobile endpoints, Windows, macOS, and the Web These are just some of the great companies exploring and engaging with us as we develop WinUI 3, and in the coming months you’ll learn more about these and other engagements as we prepare for the eventual release of WinUI 3.0 for general availability. How can I get started? To start with WinUI 3.0 Preview 1, head over to our download and release notes page . You can also find more information and technical setup details in our documentation on creating a Desktop app with WinUI . Tags: Microsoft Build WinUI What's new Surface Pro Surface Laptop Surface Laptop Studio 2 Copilot for organizations Copilot for personal use AI in Windows Explore Microsoft products Windows 11 apps Microsoft Store Account profile Download Center Microsoft Store support Returns Order tracking Certified Refurbished Microsoft Store Promise Flexible Payments Education Microsoft in education Devices for education Microsoft Teams for Education Microsoft 365 Education How to buy for your school Educator training and development Deals for students and parents AI for education Business Microsoft Security Dynamics 365 Microsoft 365 Microsoft Power Platform Microsoft Teams Microsoft 365 Copilot Small Business Developer & IT Azure Microsoft Developer Microsoft Learn Support for AI marketplace apps Microsoft Tech Community Microsoft Marketplace Marketplace Rewards Visual Studio Company Careers About Microsoft Company news Privacy at Microsoft Investors Diversity and inclusion Accessibility Sustainability Your Privacy Choices Opt-Out Icon Your Privacy Choices Your Privacy Choices Opt-Out Icon Your Privacy Choices Consumer Health Privacy Sitemap Contact Microsoft Privacy Manage cookies Terms of use Trademarks Safety & eco Recycling About our ads © Microsoft 2026 | 2026-01-13T08:47:52 |
https://www.npopov.com/ | nikic's Blog Blog by nikic . Find me on GitHub , StackOverflow , Twitter and Mastodon . Learn more about me . LLVM: The bad parts 11. January 2026 A collection of issues with LLVM, ranging from social and infrastructure problems to specific technical challenges. This year in LLVM (2024) 05. January 2025 Summary of my work on LLVM in 2024. External: Making memcpy(NULL, NULL, 0) well-defined 11. December 2024 C2y makes memcpy(NULL, NULL, 0) and various other zero-length operations on null pointers well defined. This year in LLVM (2023) 01. January 2024 Summary of my work on LLVM in 2023. External: How single-iteration InstCombine improves LLVM compile time 07. December 2023 Avoiding multiple iterations of InstCombine results in large compilation time improvements in LLVM 18. How to reduce LLVM crashes 22. October 2023 Step-by-step guide on how to reduce LLVM crashes. LLVM: Scalar evolution 03. October 2023 A brief introduction to LLVM's scalar evolution analysis, which models how values change inside loops. LLVM: Canonicalization and target-independence 10. April 2023 This documents LLVM's design philosophy when it comes to target-dependence in the middle-end optimizer. LLVM: The middle-end optimization pipeline 07. April 2023 A high-level overview of LLVM's middle-end optimization pipeline and some of the design considerations behind it. This year in LLVM (2022) 20. December 2022 Summary of my work on LLVM in 2022. The opcache optimizer 22. May 2022 An introduction to the inner workings of the opcache optimizer, or at least some parts of it. Type variance in PHP 08. November 2021 Type variance allows types to change during inheritance in a way that is compatible with the Liskov substitution principle. This article describes how this works on a technical level. Early binding in PHP 20. October 2021 Early binding allows using a class before its declaration in the same file. However, the precise behavior is rather arcane. How opcache works 13. October 2021 A brief overview of how the PHP opcache extension works, covering the caching-related aspects only. Design issues in LLVM IR 02. June 2021 Discusses a number of design issues related to IR canonicality: Pointer element types, type-based GEP, and constant expressions. Make LLVM fast again 10. May 2020 Introduces a compile-time tracking service for LLVM, and some specific compile-time improvements I have implemented. PHP 7 Virtual Machine 14. April 2017 An overview of the PHP virtual machine. Internal value representation in PHP 7 - Part 2 19. June 2015 Covers the implementation of complex types like strings and objects in PHP 7, as well as a number of special types like indirect zvals. Internal value representation in PHP 7 - Part 1 05. May 2015 Describes and compares the zval implementations used by PHP 5 and PHP 7, including a discussion of references. Other types are covered in the next part. PHP's new hashtable implementation 22. December 2014 In this article we'll explore how the new hashtable implementation used by PHP 7 improved memory usage and performance. Methods on primitive types in PHP 14. March 2014 This article discusses the merits of allowing method calls on primitive PHP types, like strings and arrays. Fast request routing using regular expressions 18. February 2014 This article describes a number of techniques to improve performance of regular expression based dispatch processes, as used in request routing or lexing. The case against the ifsetor function 10. January 2014 The ifsetor function can be used to suppress notices when accessing array indices. This post discusses some of the issues this function has and how to resolve them. Cooperative multitasking using coroutines (in PHP!) 22. December 2012 This post explains how coroutines can be used for task scheduling and handling asynchronous operations in a synchronous-seeming way. Are PHP developers functophobic? 10. August 2012 PHP developers don't seem to like normal functions much. I think that this is related to the one-to-one class to file mapping that PHP has inherited from Java. How to add new (syntactic) features to PHP 27. July 2012 In this post I'm describing how one can add new syntax to PHP. At the same time, this post can be seen as a general introduction to the workings of the Zend Engine. What PHP 5.5 might look like 10. July 2012 PHP 5.5 is still in an early development stage, but there are already many proposals that are being worked on. This post gives some insights into the recent developments. A plea for less (XML) configuration files 09. July 2012 Configuration files typically use XML or some other domain specific language. But why? Why not just use the usual programming language instead? PHP solves problems. Oh, and you can program with it too! 29. June 2012 PHP is a great language to start programming. And once you started, PHP is also good for "real" programming. So what's the problem? The true power of regular expressions 15. June 2012 There is a major misunderstanding about what modern regular expression implementation can or cannot do. This article analyses the situation by walking through the different grammar classes. Understanding PHP's internal array implementation (PHP's Source Code for PHP Developers - Part 4) 28. March 2012 The fourth part of the "PHP's Source Code for PHP Developers" series, covering how arrays are internally implemented in PHP and how they are used in the source code. PHP's Source Code for PHP Developers - Part 3 - Variables 21. March 2012 Cross-link to the third part of the "PHP's Source Code for PHP Developers" series, covering how PHP values are represented internally and used throughout the source code. Understanding PHP's internal function definitions (PHP's Source Code for PHP Developers - Part 2) 16. March 2012 The second part of the "PHP's Source Code for PHP Developers" series, covering how to find functions in the PHP source code and how they are structured. Scalar type hinting is harder than you think 06. March 2012 A quick overview of the different scalar type hinting proposals and why PHP is having such a hard time deciding. Pointer magic for efficient dynamic value representations 02. February 2012 JS implementations use some neat tricks to achieve good performance. One of those tricks is a good bit of pointer magic to make dynamically typed values more efficient. htmlspecialchars() improvements in PHP 5.4 28. January 2012 There is some nice new stuff for htmlspecialchars() in PHP 5.4, which hasn't yet got the attention it deserves. Careful: XDebug can skew your performance numbers 19. January 2012 In some cases XDebug can significantly skew your benchmarking and profiling numbers. So make sure that you do measurements without it. Disproving the Single Quotes Performance Myth 09. January 2012 One of the oldest myths around PHP is that single quotes are faster than double quotes. And. It. Is. Not. True. Supercolliding a PHP array 28. December 2011 Inserting 65536 specially crafted values into a PHP array can take 30 seconds, whereas normally it would only take 0.01 seconds. Don't be STUPID: GRASP SOLID! 27. December 2011 Introducing STUPID: Singleton, Tight Coupling, Untestability, Premature Optimization, Indescriptive Naming, Duplication. How big are PHP arrays (and values) really? (Hint: BIG!) 12. December 2011 PHP's memory usage might seem atrocious to some - twenty times more than the optimum you would have in C. This post tries to explain those numbers and why they are necessary. PCRE and newlines 10. December 2011 There is a huge number of newline related features in PCRE (regular expressions) that nearly nobody knows about. I want to shed light on some of those. Manually installing PEAR on Windows 03. December 2011 If you ever tried to install PEAR on Windows you probably know what a woeful task it is. This is a short instruction on how to manually install PEAR (without using go-pear.phar). PHP internals: When does foreach copy? 11. November 2011 PHP's foreach language construct sometimes copies the array it iterates and sometimes does not. This post analyzes when and why this happens. Improving lexing performance in PHP 23. October 2011 Some thoughts on improving lexing performance in PHP by compiling the individual token regexes into one big super-regex. | 2026-01-13T08:47:52 |
https://www.npopov.com/2026/01/11/LLVM-The-bad-parts.html#fnref:bors | LLVM: The bad parts Blog by nikic . Find me on GitHub , StackOverflow , Twitter and Mastodon . Learn more about me . « Back to article overview. LLVM: The bad parts 11. January 2026 A few years ago, I wrote a blog post on design issues in LLVM IR . Since then, one of these issues has been fixed fully (opaque pointers migration), one has been mostly fixed (constant expression removal), and one is well on the way towards being fixed (ptradd migration). This time I’m going to be more ambitious and not stop at three issues. Of course, not all of these issues are of equal importance, and how important they are depends on who you ask. In the interest of brevity, I will mostly just explain what the problem is, and not discuss what possible solutions would be. Finally, I should probably point out that this is written from my perspective as the lead maintainer of the LLVM project: This is not a list of reasons to not use LLVM, it’s a list of opportunities to improve LLVM. High level issues Review capacity Unlike many other open-source projects, LLVM certainly does not suffer from a lack of contributors. There are thousands of contributors and the distribution is relatively flat (that is, it’s not the case that a small handful of people is responsible for the majority of contributions.) What LLVM does suffer from is insufficient review capacity. There are a lot more people writing code than reviewing it. This is somewhat unsurprising, as code review requires more expertise than writing code, and may not provide immediate value 1 to the person reviewing (or their employer). Lack of review capacity makes for a bad contributor experience, and can also result in bad changes making their way into the codebase. The way this usually works out is that someone puts up a PR, then fails to get a qualified review for a long period of time, and then one of their coworkers (who is not a qualified reviewer for that area) ends up rubberstamping the PR. A related problem is that LLVM has a somewhat peculiar contribution model where it’s the responsibility of the PR author to request reviewers. This is especially problematic for new contributors, who don’t know whom to request. Often relevant reviewers will become aware of the PR thanks to a label-based notification system, but this is not apparent from the UI, and it’s easy for PRs to fall through the cracks. A potential improvement here would be a Rust-style PR assignment system . Churn Both the LLVM C++ API and LLVM IR are not stable and undergo frequent changes. This is simultaneously a great strength and weakness of LLVM. It’s a strength because LLVM does not stagnate and is willing to address past mistakes even at significant cost. It’s a weakness because churn imposes costs on users of LLVM. Frontends are somewhat insulated from this because they can use the largely stable C API. However, it does not cover everything, and most major frontends will have additional bindings that use the unstable C++ API. Users that integrate with LLVM more tightly (for example downstream backends) don’t have that option, and have to keep up with all API changes. This is part of LLVM’s general development philosophy, which I’ll express somewhat pointedly as “upstream or GTFO”. LLVM is liberally licensed and does not require you to contribute changes upstream. However, if you do not upstream your code, then it will also not factor into upstream decision-making. This point is somewhat unlike the rest, in that I’m not sure it’s possible to make things “strictly better” here. It’s possible that LLVM’s current point on the stability scale is not optimal, but moving it somewhere else would come with significant externalities. Making major changes in LLVM is already extremely hard due to the sheer scale of the project, without adding additional stability constraints on top. Build time LLVM is a huge project. LLVM itself is >2.5 million lines of C++ and the entire monorepo is something like 9 million. C++ is not exactly known for fast build times, and compiling all that code takes time. This is bearable if you either have fast hardware or access to a build farm, but trying to build LLVM on a low-spec laptop is not going to be fun. An additional complication is building with debug info (which I always recommend against), in which case you’ll add the extra gotchas of slow link times, high risk of OOM and massive disk usage. There are ways to avoid that (using shared libs or dylib build, using split dwarf, using lld), but it takes some expertise. Promising changes in this area are the use of pre-compiled headers (which significantly improves build time), and changing to use a dylib build by default (which reduces disk usage and link time, esp. for debuginfo builds). Another is to reduce test overhead using daemonization (not strictly part of the “build time”, but relevant for the development cycle). CI stability LLVM CI consists of over 200 post-commit buildbots that test LLVM in lots of different configurations on lots of different hardware. Commits that turn a buildbot from green to red result in an email to the commit author. Unfortunately, this CI is never fully green, and flaky on top. This is in part due to flaky tests (typically in lldb or openmp), but can also be due to buildbot-specific issues. The end result is that it’s “normal” to get buildbot failure notifications for any given commit, even if it is perfectly harmless. This dilutes the signal, and makes it easier to miss the real failures. The introduction of pre-merge testing on PRs did significantly improve the overall CI situation, but not the buildbot problem as such. I think we need to start taking flaky tests/buildbots more seriously before we can really make progress here. Because someone is definitely going to mention how this is not rocket science , and we just need to start using bors / merge queues to guarantee an always-green build: It’s a problem of scale. There are >150 commits on a typical workday, which would be more than one commit every 10 minutes even if they were uniformly distributed. Many buildbots have multi-hour runs. This is hard to reconcile. 2 End-to-end testing In some respects, LLVM has very thorough test coverage. We’re quite pedantic about making sure that new optimizations have good coverage of both positive and negative tests. However, these tests are essentially unit tests for a single optimization pass or analysis. We have only a small amount of coverage for the entire optimization pipeline (phase ordering tests), so optimizations sometimes regress due to pass interactions. Tests for the combination of the middle-end and backend pipelines are essentially nonexistent. There is likely room for improvement here, though it comes with tradeoffs. However, what actually concerns me are end-to-end executable tests. LLVM’s test suite proper does not feature these at all. Executable tests are located in a separate llvm-test-suite repo, which is typically not used during routine development, but run by buildbots. It contains a lot of different code ranging from benchmarks to unit tests. However, llvm-test-suite has quite few tests (compared to LLVM lit tests) and does not comprehensively cover basic operations. Things like testing operations on different float formats, on integers of different sizes, vectors of different sizes and element types, etc. In part this is because of limitations of testing through C/C++, which is very heterogeneous in type support (C compilers don’t like exposing types that don’t have a defined psABI for the target). But that’s no excuse to delegate this testing to Zig instead (which exposes everything, everywhere, and has the corresponding test coverage). Backend divergence While LLVM’s middle-end is very unified, backend implementations are very heterogeneous, and there is a tendency to fix issues (usually performance, but sometimes even correctness) only for the backend you’re interested in. This takes many forms, like implementing target-specific DAG combines instead of generic ones. Though my definite favorite is to introduce lots of target hooks for optimizations – not because the optimization is actually only beneficial for one target, but because the person introducing it just doesn’t want to deal with the fallout on other targets. This is understandable – after all, they may lack the knowledge to evaluate a change for other targets, so it may require working with many other maintainers, which can slow progress a lot. But the end result is still increasing divergence and duplication. Lack of end-to-end testing compounds this issue, because that would act as something of a forcing function that at least all operations compile without crashing and produce correct results for all tested targets. Compilation time Because I’ve complained about this enough in the past, I’ll keep it short: LLVM is slow, which is an issue both for JIT use cases, and anything that tends to produce huge amounts of IR (like Rust or C++). Since I’ve started tracking compile-times , the situation has significantly improved, both through targeted improvements and avoidance of regressions. However, there is still a lot of room for improvement: LLVM still isn’t fast, it’s just less slow. One thing that LLVM is particularly bad at are -O0 compile-times. The architecture is optimized for optimization, and lots of costs remain even if no optimization takes place. The LLVM TPDE alternative backend shows that it’s possible to do better by an order of magnitude. Performance tracking The flip side of the compile-time coin is runtime performance. This is something that LLVM obviously cares a lot about. Which is why I find it rather surprising that LLVM does not have any “official” performance tracking infrastructure. Of course, there are lots of organizations which track performance of LLVM downstream, on their own workloads. In some ways this is good, because it means there is more focus on real-world workloads than on synthetic benchmarks like SPEC. However, not having readily accessible, public performance tracking also makes it hard for contributors to evaluate changes. To be fair, LLVM does have an LNT instance, but a) it’s currently broken, b) LNT is one of the worst UX crimes ever committed, c) little data gets submitted there, and d) it’s not possible to request a test run for a PR, or something like that. This point is frankly just baffling to me. I don’t personally care about SPEC scores, but I know plenty of people do, so why there is no first-class tracking for this is a mystery to me. IR design Undef values Undef values take an arbitrary value from a certain set. They are used to model uninitialized values, and have historically been used to model deferred undefined behavior. The latter role has been replaced by poison values, which have much simpler propagation rules and are more amenable to optimization. However, undef is still used for uninitialized memory to this day. There are two main problems with undef values. The first is the multi-use problem: An undef value can take a different value at each use. This means that transforms that increase the use count are generally invalid, and care has to be taken when optimizing based on value equality. The mere existence of undef values prevents us from performing optimizations we want to do, or greatly increases their complexity. The second issue is that undef is very hard to reason about. Humans have trouble understanding it, and for proof-checkers it is computationally expensive. Most likely, uninitialized memory will be represented using poison values instead in the future, but this runs into the problem that LLVM currently is not capable of correctly treating poison in memory. Proper support for poison in memory requires additional IR features, like the byte type . Unsoundness and specification incompleteness While most miscompilations (that is, correctness bugs) in LLVM are resolved quickly, there are quite a few that remain unfixed despite having been known for a long time. These issues usually combine the qualities of being largely theoretical (that is, appearing only in artificially constructed examples rather than real-world code) and running up against issues in LLVM’s IR design. Some of them are cases where we have a good idea of how the IR design needs to change to address the issue, but these changes are complex and often require a lot of work to recover optimization parity. There is often a complexity cliff where you can do something that’s simple and nearly correct, or you can do something very complex that is fully correct. Then there are other cases, where just deciding on how things should work is a hard problem. The provenance model is a prime example of this. The interaction of provenance with integer casts and type punning is a difficult problem with complex tradeoffs. However, at some point these issues do need to be resolved. The recently formed formal specification working group aims to tackle these problems. Constraint encoding A key challenge for optimizing compilers is encoding of constraints (like “this value is non-negative” or “this add will not overflow”). This includes both frontend-provided constraints (based on language undefined behavior rules), but also compiler-generated ones. In particular, there are many different analyses that can infer facts about the program, but keeping these up-to-date throughout optimization is challenging. One good way to handle this is to encode facts directly in the IR. Correctly updating or discarding these annotations then becomes part of transform correctness. LLVM has many different ways to encode additional constraints (poison flags, metadata, attributes, assumes), and these all come with tradeoffs in terms of how much information can be encoded, how reliably it is retained during optimization and to what degree it can negatively affect optimization. Information from metadata is lost too often, while information from assumes is not lost often enough. Floating-point semantics There are various issues with floating-point (FP) semantics once we move outside the nice world of “strictly conforming IEEE 754 floats in the default environment”. A few that come to mind are: Handling of signaling NaN and FP exceptions, and non-default FP environment in general. LLVM represents this using constrained FP intrinsics. This is not ideal, as all the FP handling is split into two parallel universes. Handling of denormals. LLVM has a function attribute to not assume IEEE denormal behavior, but this is only suitable for cases where flush to zero (FTZ) is used globally. It does not help with modeling cases like ARM, where scalar ops are IEEE, while vector ops use FTZ. Handling of excess precision, in particular when using the x87 FPU. Other technical issues Partial migrations LLVM is a very large project, and making any significant changes to it is hard and time consuming. Migrations often span years, where two different implementations of something coexist, until all code has been migrated. The two prime examples of this are: New pass manager: The “new” pass manager was first introduced more than a decade ago. Then about five years ago, we started using it for the middle-end optimization pipeline by default, and support for the legacy PM was dropped. However, the back-end is still using the legacy pass manager. There is ongoing work to support the new pass manager in codegen, and we’re pretty close to the point where it can be used end-to-end for a single target. However, I expect it will still take quite a while for all targets to be ported and the legacy pass manager to be completely retired. GlobalISel: This is an even more extreme case. GlobalISel is the “new” instruction selector that is intended to replace SelectionDAG (and FastISel). It was introduced approximately one decade ago, and to this day, none of the targets that originally used SelectionDAG have been fully migrated to GlobalISel. There is one new target that’s GlobalISel-only, and there is one that uses GlobalISel by default for unoptimized builds. But otherwise, SelectionDAG is still the default everywhere. There are two backends (AMDGPU and AArch64) that have somewhat complete GlobalISel support, but it’s not clear when/if they’ll be able to switch to using it by default. A big problem here is that new optimizations are continually being implemented on the SDAG side, so it’s hard to keep parity. ABI / calling convention handling Essentially everything about the handling of calling conventions in LLVM is a mess. The responsibility for handling calling conventions is split between the frontend and the backend. There are good reasons why LLVM can’t do this by itself (LLVM IR sits at a too low level of abstraction to satisfy the extremely arcane ABI rules). This is not a problem in itself – however, there is zero documentation of what the calling convention contract between the frontend and LLVM is, and the proper way to implement C FFI is essentially to look at what Clang does and copy that (invariably with errors, because the rules can be very subtle). I’ve proposed to fix this by introducing an ABI lowering library and vortex73 has implemented a prototype for it as part of GSoC. So we’re well on the way to resolving this side of the problem. There are more problems though. One that Rust has struggled with a lot is the interaction of target features with the calling convention. Enabling additional target features can change the call ABI, because additional float/vector registers start getting used for argument/return passing. This means that calls between functions with a feature enabled and disabled may be incompatible, because they assume different ABIs. Ideally, ABI and target features would be orthogonal, and only coupled in that some ABIs require certain target features (e.g. you can’t have a hard float ABI without enabling FP registers). Target features are a per-function choice, while the ABI should be per-module. Some of the newer architectures like Loongarch and RISC-V actually have proper ABI design, but most of the older ones don’t. For example, it’s currently not possible to target AArch64 with a soft float ABI but hard float implementation. Builtins / libcalls Somewhat related to this is the handling of compiler builtins/libcalls, which are auxiliary functions that the compiler may emit for operations that are not natively supported by the target. This covers both libcalls provided by libc (or libm), and builtins provided by compiler runtime libraries like libgcc, compiler-rt or compiler-builtins. There are two sources of truth for this, TargetLibraryInfo (TLI) and RuntimeLibcalls. The former is used by the middle-end, primarily to recognize and optimize C library calls (this mostly covers only libc, but not libgcc). The latter is used by the backend, primarily to determine which libcalls may be emitted by the compiler and how they are spelled (this covers libgcc, and the subset of libc covered by LLVM intrinsics). A problem with RuntimeLibcalls is that it currently largely works off only the target triple, which means that we have to make “lowest common denominator” assumptions about which libcalls are available, where the lowest common denominator is usually libgcc. If --rtlib=compiler-rt is used, LLVM does not actually know about that, and cannot make use of functions that are in compiler-rt but not libgcc. This also means that we’re missing a customization point for other runtime libraries. For example, there is no way for Rust to say that it provides f128 suffix libcalls via compiler-builtins, overriding target-specific naming and availability assumptions based on which type long double in C maps to. There is a lot of ongoing work in this area (by arsenm), so the situation here will hopefully improve in the near-ish future. Context / module dichotomy LLVM has two high-level data holders. A module corresponds to a compilation unit (e.g. pre-LTO, a single file in C/C++). The LLVM context holds various “global” data. There’s usually one context per thread, and multiple modules can (in principle) use a single context. Things like functions and globals go into the module, while constants and types go into the context. The module also contains a data layout, which provides important type layout information like “how wide is a pointer”. The fact that constants and types do not have access to the data layout is a constant source of friction. If you have a type, you cannot reliably tell its size without threading an extra parameter through everything. We have subsystems (like ConstantFold vs. ConstantFolding) that are separated entirely by whether data layout is available or not. At the same time, I feel like this split is not actually buying us a lot. Having shared types and constants is somewhat convenient when it comes to module linking, because they can be directly shared, but I think performing explicit remapping in that one place would be better than having complexity everywhere else. Additionally, this would also allow cross-context linking, which is currently only possible by going through a bitcode roundtrip. In theory, the context could also allow some memory reuse when compiling multiple modules, but I think in practice there is usually a one-to-one correspondence between those. LICM register pressure This is getting a bit down in the weeds, but I’ll mention it anyway due to how often I’ve run across this in recent times. LLVM considers loop invariant code motion (LICM) to be a canonicalization transform. This means that we always hoist instructions out of loops, without any target specific cost modelling. However, LICM can increase the live ranges of values, which can increase register pressure, which can lead to a large amount of spills and reloads. The general philosophy behind this is that LICM hoists everything, all middle-end transforms can work with nicely loop invariant instructions, and then instructions will get sunk back into the loop by the backend, which can precisely model register pressure. Except… that second part doesn’t actually happen. I believe that (for non-PGO builds) instructions only get sunk back into loops either through rematerialization in the register allocator, or specialized sinking (typically of addressing modes), but for anything not falling into those buckets, no attempt to sink into loops in order to reduce register pressure is made. Other This list is not exhaustive. There’s more I could mention, but we’d get into increasingly narrow territory. I hope I covered most of the more important things – please do let me know what I missed! If you’re not concerned with overall project health, the primary value of reviews is reciprocity. People are more likely to review your PR, if you reviewed theirs. ↩ The way Rust reconciles this is via a combination of “rollups” (where multiple PRs are merged as a batch, using human curation), and a substantially different contribution model. Where LLVM favors sequences of small PRs that do only one thing (and get squash merged), Rust favors large PRs with many commits (which do not get squashed). As getting an approved Rust PR merged usually takes multiple days due to bors, having large PRs is pretty much required to get anything done. This is not necessarily bad, just very different from what LLVM does right now. ↩ If you liked this article, you may want to browse my other articles or follow me on Twitter or Mastodon . | 2026-01-13T08:47:52 |
https://go.mcptotal.io/blog/a-practical-guide-to-build-secure-mcp-servers | A Practical Guide to Build Secure MCP Servers Platform Blog Company Log in Book a Demo Back to Blog January 8, 2026 Gil Dabah A Practical Guide to Build Secure MCP Servers api server mcp server security security by design We wanted to come up with a practical guide on how to implement a secure and hardened MCP server—or, in reality, any API server. Not surprisingly, they are technically very identical. However, in an era where "users" are increasingly autonomous agents and backends are being wrapped in Model Context Protocol (MCP) layers, the attack surface has shifted to the client side too. To build any resilient system, developers must move beyond the basics of writing secure code (which is a challenge by itself) and address how the architecture and infrastructure are designed as well. While you should always tailor your defenses to your specific threat model, there are certain universal "must-haves" for any secure system, let's go. The MCP Frontier The Model Context Protocol (MCP) connects LLMs to your data and accounts. There are two types of MCP servers as we see it - Thin Wrappers vs. Standalone Servers . For standalone MCP servers, the golden rule is to design tools with an API-first mindset , applying the below 5 pillars across the board. If you are integrating a third-party server , prioritize a 'passthrough' architecture. Minimize the logic within your wrapper to reduce the attack surface and ensure security integrity. Security by Design: The Foundation Security is now more critical than ever. In the age of AI, autonomous agents can be turned into bitter adversaries, scanning your APIs for vulnerabilities and executing exploits at machine speed. To counter this and before jumping to actual guidelines let's hit the foundation first, we must build following "Security by Design" principles: Never Trust Anything: You cannot know who the client is or what their intent is. Therefore, every single piece of data—headers, parameters, and bodies—must be verified and sanitized. Least Privilege: Every process and user should only have the minimum permissions necessary to perform its job. This is vital to contain the "blast radius" if a breach occurs. Multi-Layered Defense (Defense in Depth): No single measure is enough. We use WAFs, activity monitoring, sandboxing, and non-root permissions. Layering defenses slows down adversaries and provides multiple opportunities to fully stop a takeover. Segregate/Isolate Assets: Architecture matters. Logically divide your sub-systems so that a compromise in one sub-system/machine doesn't grant access to the whole puzzle. This applies to data (don't put everything in one "users table") and file systems (uploads should go to a system-controlled directory where they cannot be executed). Continuous Updates: Security is a moving target. Always keep your libraries, packages, OS, and server frameworks up to date to patch known vulnerabilities before they are exploited. The Backend is the Last Frontier: Developers often sanitize user input like name/email, etc, in the frontend browser and assume they are safe. This is a dangerous fallacy. Adversaries bypass your UI and hit your APIs directly. Your backend must verify everything as if the frontend doesn't exist. Most developers don't overlook security intentionally; they simply haven't been introduced to these specific principles. There is a reason cybersecurity has become its own dedicated field. However, with your experience in backend development, you’ll find these concepts very intuitive to pick up. Our Own Secure Architecture of MCPTotal.io As you begin to internalize these guidelines, it’s worth noting that we’ve applied these exact principles to our own architecture. This foundational security is what allows us to safely offer high-trust features, such as letting customers run their own MCP servers and custom code directly within our backend. Our philosophy is to: assume 'breached'. When we design a system, we ask ourselves, assuming this component is breached, what an adversary can do and how far can they get. You can learn more about real security and how we look at it from reading other blog posts. For example, the fact that we use a token vault to store customer credentials securely , where we talk further about other security principles related data storage. Or you can read more about our general backend architecture here . Local vs External Threats One final note before we dive in. Many MCP developers begin by building a simple STDIO server that runs locally on their own machine. That approach is perfectly reasonable. However, it’s important to recognize that the threat model for a local server is fundamentally different from that of a server exposed to the internet. In a local setup, it’s often acceptable to make assumptions about how the server is used and to largely ignore external interactions, which are minimal to-non-existent unless the server explicitly accesses online resources. Problems arise when a server originally designed for local use is later deployed as a public-facing service. At that point, those assumptions no longer hold, and previously acceptable shortcuts can become serious security issues. Keep this distinction in mind when building an MCP server that will be accessible over the internet. Also, be mindful of binding your server to 0.0.0.0 , which many MCP SDKs do by default. This is generally a bad idea, as it allows any device on your local network to connect to the server—potentially enabling unauthorized access to your data or the execution of actions on your behalf. From a technical standpoint, binding to 0.0.0.0 means the socket listens on all network interfaces, including those exposed to other machines. In most cases, this behavior is unintended and introduces unnecessary risk. The fix is simple, bind to 127.0.0.1 or use STDIO. Part 1: The 5 Pillars of API Hardening 1. Identity & Ownership: The Mandatory Baseline Mandatory Authentication: All endpoints must check for authenticated users. Use centralized middleware to enforce token validation (JWT, OAuth2) across the entire API surface. Resource Ownership (BOLA/IDOR): Authentication proves who a user is; Authorization proves what they can do. Broken Object Level Authorization is when the system can access everything, but it doesn't enforce the scope to the logged in user, that's a big issue, causing an attacker to access resources of another user. This is easy to overlook, each API must check ownership of everything first. The Rule: For example, in database, every query must be "scoped." Never fetch a resource by its ID alone (unless it's a global data resource). Secure Query: SELECT * FROM orders WHERE id = $order_id AND user_id = $authenticated_user_id 2. Input Integrity: Sanitization & Business Logic All parameters of your APIs must verify input for correctness, better drop requests if input doesn't make sense. Sometimes you can sanitize some bad characters or inputs too, but that's the least preferred method (it can create some issues on its own). Strings (The HTML/XSS Trap): Attackers provide names containing malicious scripts (e.g., <script>...</script> ). If stored raw, any dashboard rendering this name will execute the script ( Stored XSS ). Integers (Type Enforcement): Prevent quantity manipulation (e.g., quantity: -1 ). File Paths (Directory Traversal): Prevent access to system files (e.g., filename: "../../../etc/passwd" ). The "Price" Rule: Never accept a price from the client. The server must look up the price in its own database based on a product_id . Remember, don't trust stuff coming from the client side, definitely not things that the system should find in a 'source of truth' location. 3. Resource Handling: SSRF and File Logic Server-Side Request Forgery (SSRF): This makes your server a trusted proxy to attack your internal network or cloud metadata services. Must check and verify URLs correctly, it's tricky by itself. The Zip Bomb: Tiny archives that expand into gigabytes to crash your server (DoS). So set your quotas correctly to avoid this stuff, check file sizes, etc. Secure File Uploads: Rename every file to a GUID and store them in a fixed directory that the system controls which the outside world doesn't have direct HTTP access to. Never run or execute files from this directory to avoid an adversary taking over your backend. Remember the segregation principle. 4. Hardening the Runtime: Isolation Run as "Nobody": Never run your server as root or admin . If hijacked, the attacker's permissions are severely limited. This can also go to remove envars that aren't used anymore that might contain sensitive data like credentials. Tenant Isolation: Ensure one customer's data is logically separated from another's, that requires a whole DB schema design, most developers might overlook this because it requires extra work. Network Lockdown: Close SSH (Port 22) to the public internet, seriously. Use a VPN to access your back-office server. Don't mix it with your own public facing server, or make sure it's super secure, but you just opened more attack surface to the world and it will be used against you. 5. Metrics & Network Observability Seriously, make sure you have logs recorded somewhere. They only come handy when you need them. Post-mortem and diagnostics are only one reason, runtime security is another... Performance Baselines: Monitor CPU and Memory. A spike without a traffic increase often indicates a compromise, such as a hidden crypto-miner. Network Traffic: Watch for deviations in network egress. If your server sends data to unknown external IPs or too much data outside, it's a sign of a breach. WAF: Deploy a Web Application Firewall to block attack patterns before they hit your code. It saved the day with the lethal react2shell bug recently. Part 2: Related Security Concerns 1. The Inversion of Trust: Malicious MCP Servers In MCP, the user fears the server . A malicious server can return results designed to perform Indirect Prompt Injection on an Agent, tricking it into running commands like rm -rf / . And there's no good cure around, you will need an MCP gateway to filter it. 2. The "Plaintext JSON" Secret Problem In The Endpoint Users who use agents, normally configure and store API keys in plaintext JSON files. This is the (terrible) standard today. Use a password manager. 3. BOLA & Input Verification in MCP To re-iterate: if your MCP server is a simple wrapper, you are essentially delegating the heavy lifting of security to the underlying API server. In that case, you must trust that the API server is rigorously performing input verification and enforcing the principles we’ve discussed. If it isn't, or if you are building a standalone MCP, that responsibility falls entirely on you. If you choose a dual architecture—splitting your system into an MCP wrapper and a dedicated API server— place your primary defenses within the API server. This centralizes your security logic and protects you against internal threats; even if a malicious actor gains access to your internal network, they could attempt to bypass the MCP layer and connect to your API servers directly. 4. If you're building a thin-wrapper MCP server for existing APIs, here's a couple of things to note: API Key Management: If your MCP server holds credentials for connecting to cloud services, implement strict tenant isolation to prevent cross-client data leakage. Furthermore, ensure all API keys are stored securely within a dedicated token vault. Normally the API key would fully come from the AI agent, so you wouldn't want to cache it permanently or store it on disk as is. The Caching Trap: Naive caching is both a security and privacy nightmare. If you cache data for User A and serve it to User B, you have a major data leak. But the fact you cache data in one more place now might violate your own privacy policies. Isolate caches by identity per user. Conclusion Securing a server isn't a mystery; it’s about fanatical verification of input at the code level and solid architecture to reduce blast reduce. If you validate inputs, check ownerships, and run a least-privilege environment, you’ve won most of the battle. However, the "missing if-statement" remains our greatest enemy. In today's interconnected ecosystem, even generic features can be turned into weapons. Look no further than MongoBleed —a critical memory leak triggered by one missing integer check. To protect your data and your sanity, remember: never trust an input you haven't verified. Last updated: January 12, 2026 Back to Blog MCPTotal The most secure platform for running, managing, discovering and governing MCP servers across your organization. Autonomous Security Inc 135 W. 50th St. Suite 200 New York, NY 10020 Platform Hub Gateway Desktop Chrome Company Blog Contact About Legal Terms of Service Privacy Policy Security Policy Connect Twitter LinkedIn GitHub Autonomous Security Inc 135 W. 50th St. Suite 200 New York, NY 10020 MCPTotal is owned by Autonomous Security Inc. All rights reserved 2026 . MCPTotal is currently in beta. Features and functionality may change as we continue to improve the platform. | 2026-01-13T08:47:52 |
https://www.npopov.com/2021/06/02/Design-issues-in-LLVM-IR.html | Design issues in LLVM IR Blog by nikic . Find me on GitHub , StackOverflow , Twitter and Mastodon . Learn more about me . « Back to article overview. Design issues in LLVM IR 02. June 2021 On the whole, LLVM has a well-designed intermediate representation (IR), which is specified in the language reference . However, there are a number of areas where design mistakes have been made. And while the LLVM project is generally open to addressing such issues, mistakes in core IR design tend to be firmly embedded in the code base, making them hard to fix in practice. This blog post discusses some of the problems. Canonicalization In the middle-end, we commonly view transformations not as optimizations, but as canonicalizations. There are many different ways to write the same program, and the purpose of target-independent middle-end transforms is to reduce them to a single form. Of course, the chosen form will often (but not always) coincide with the more efficient form. (This does not apply to all transforms, for example runtime unrolling and vectorization are certainly not canonicalization transforms.) Why do we care about canonicalization? The main reason is that it reduces the number of permutations that other passes need to deal with. If 1 + a is canonicalized to a + 1 , everything else only needs to handle the latter form. Another reason is that it improves the effectiveness of redundancy-elimination transforms (like common subexpression elimination and global value numbering). Let’s look at an example: define i1 @test ( i32 %x ) { %y = sub i32 %x , 1 %z = add i32 %x , -1 %c = icmp eq i32 %y , %z ret i1 %c } Instruction combining will canonicalize x - 1 to x + (-1) : define i1 @test ( i32 %x ) { %y = add i32 %x , -1 %z = add i32 %x , -1 %c = icmp eq i32 %y , %z ret i1 %c } At this point it becomes trivial to detect that %y and %z are in fact the same, so we can replace %z with %y : define i1 @test ( i32 %x ) { %y = add i32 %x , -1 %c = icmp eq i32 %y , %y ret i1 %c } Once that is done, we can also see that the equality comparison is trivially true: define i1 @test ( i32 %x ) { ret i1 true } So, what does this have to do with IR design? A good IR design can make certain redundancies non-existent by design. Primarily, this is “just” a matter of not encoding any unnecessary information. For example, early LLVM versions distinguished between signed and unsigned integers, while later versions only have a single integer type (for a given bitwidth) and signedness is only encoded in the few places it matters: comparisons, extensions and overflow flags. This means that there is only one representation of x + 1 regardless of whether x is signed or not. This is an outcome of the core IR design, and does not require additional canonicalization. You will notice that the problems discussed in the following are quire similar in flavor. Pointer element types Currently, LLVM pointer types look a lot like C pointer types: i8* is a pointer to an 8-bit integer. Let’s copy around an i8* pointer: define void @copy.i8ptr ( i8 ** %dst , i8 ** %src ) { %val = load i8 *, i8 ** %src store i8 * %val , i8 ** %dest ret void } Now let’s copy an i32* pointer instead: define void @copy.i32ptr ( i32 ** %dst , i32 ** %src ) { %val = load i32 *, i32 ** %src store i32 * %val , i32 ** %dest ret void } The astute reader will notice that these two pieces of code do exactly the same thing. They copy a pointer-sized value from one location to another, and the fact that this happens to be a pointer to i8 or i32 is wholly irrelevant. If we detect this fact and want to merge these functions by implementing one in terms of the other, we have to insert bitcast s: define void @copy.i32ptr ( i32 ** %dst , i32 ** %src ) { %dst.i8ptr = bitcast i32 ** %dst to i8 * %src.i8ptr = bitcast i32 ** %src to i8 * call void @copy.i8ptr ( i8 ** %dst.i8ptr , i8 ** %src.i8ptr ) ret void } Bitcasts are LLVMs way of representing a cast that reinterprets a value in different type, without changing its binary representation. These pointer bitcasts are only needed because LLVM encodes an unnecessary pointer element type. Pointer type conversions are pervasive and often occur when data goes through different layers. A pointer may start out as [8 x i32]* when representing a specific object of known size, then become [0 x i32]* when interpreted as a slice, then i8* when passed to a memcpy as a generic pointer. Thankfully, LLVM is in the process of removing pointer element types and switching to opaque pointers . With opaque pointers, the above code would like this: define void @copy.ptr ( ptr %dst , ptr %src ) { %val = load ptr , ptr %src store ptr %val , ptr %dest ret void } This renders both functions equivalent by-design, and removes any need for pointer bitcasts. An interesting question to ask here is: Can’t we go one step further, and just treat a pointer as an integer? Say i64 on a platform with 64-bit address space: define void @copy.i64 ( i64 %dst , i64 %src ) { %val = load i64 , i64 %src store i64 %val , i64 %dest ret void } This is not possible for two main reasons. The first is that pointers carry provenance, which is important for alias analysis . A pointer has an “underlying object” it is based on, and dereferencing it is only valid if it points into that object. Integers do not track provenance, and as such conversions between integers and pointers are not considered no-ops (and are not represented as bitcasts). The second is that there are different kinds of pointers: Even with opaque pointers, LLVM still distinguishes pointers in different address spaces. While these would be the same on a von Neumann architecture, some targets may have separate address spaces for data and instructions, which might be represented as ptr and ptr addrspace(1) . Pointers may even be non-integral , in which case they don’t have an integer representation at all. The migration to opaque pointers is already “in progress” for many years, though that progress has been rather slow and has only recently picked up again . The state of opaque pointers in LLVM itself is actually fairly okay, because there is a general awareness of the issue, and any optimization that tries to make use of pointer element types will not pass review. However, the state in clang is, diplomatically speaking, less than stellar. I especially like this cute comment – “simply” indeed. Type-based GetElementPtr LLVM performs address calculations using the getelementptr instruction , which accepts a base pointer and a number of indices: %struct = type { i32 , { i32 , { [ 2 x i32 ] } } } define i32 * @test ( %struct * %base ) { %ptr = getelementptr %struct , %struct * %base , i64 1 , i32 1 , i32 1 , i32 0 , i64 1 ret i32 * %ptr } The first i64 means that we take the second element from the pointer, akin to &base[1] in C. The following indices drill down to a specific element in the nested struct and array structure. Assuming that i32 is 4-byte aligned, if you add up all the offsets, it turns out that this getelementptr is equivalent to the following one: %struct = type { i32 , { i32 , { [ 2 x i32 ] } } } define i32 * @test ( %struct * %base ) { %base.i8 = bitcast %struct * %base to i8 * %ptr = getelementptr i8 , i8 * %base.i8 , i64 11 ret i32 * %ptr } These two GEPs compute the same address in two different ways, which adds up to another canonicalization problem. It also means that analyses usually need to decompose type-based GEPs into offset-based calculations. This is surprisingly expensive, because it requires computing the alloc size of all involved types from data layout information, including potential alignment constraints. It is not atypical for a couple percent of total compile-time to be spent in nothing but GEP offset calculations. The better alternative is to make GEPs directly offset based, which works best in conjunction with opaque pointers: define ptr @test ( ptr %base ) { %ptr = getelementptr ptr %base.i8 , i64 11 ret ptr %ptr } What is not entirely clear is how variable indices should be encoded. Either the necessary scale could be part of the GEP instruction: define ptr @test ( ptr %base , i64 %index ) { %ptr = getelementptr ptr %base.i8 , 4 * %index ret ptr %ptr } Or else the index calculation could be explicit in IR: define ptr @test ( ptr %base , i64 %index ) { %offset = shl i64 %offset , 2 %ptr = getelementptr ptr %base.i8 , i64 %offset ret ptr %ptr } The latter variant is once again beneficial from a canonicalization perspective, as there is no choice between an explicit offset calculation and an offset calculation embedded in the GEP. However, inbounds GEPs carry additional constraints on the offset calculation, which would be lost with such an encoding. GEP instructions are not the only kind of instruction afflicted by too much type information. For example, the alloca instruction , which is used to reserve stack space, accepts a type, while it really only needs to know the number of bytes to reserve: %ptr = alloca [ 8 x i32 ], align 4 ; should be %ptr = alloca i64 32 , align 4 However, canonicality is not particularly important for allocas in practice, as they are typically not subject to redundancy elimination or structural equality checks. Constant Expressions Next to instructions, LLVM also supports constant expressions . The add instruction in this function define i64 @test () { %res = add i64 1 , 2 ret i64 %res } can be equivalently written using a constant expression: define i64 @test () { ret i64 add ( i64 1 , i64 2 ) } A nice thing about constant expressions is that they are maximally folded and uniqued at time of construction. So this example will actually be converted into define i64 @test () { ret i64 3 } when the file is parsed. Isn’t this great for canonicalization? By construction, we can’t have different representations of the same constant expression, because it is always fully folded! Unfortunately, things aren’t that simple. Constant expressions are unique per LLVM context, which is not data layout aware. This means that at time of construction, only folds that do not depend on data layout can be performed. For example, it’s not possible to fold an expression like this: define i64 @sizeof_int64 () { ret i64 ptrtoint ( i64 * getelementptr ( i64 , i64 * null , i64 1 ) to i64 ) } This expression is the encoding for the alloc size of i64 , and requires knowing the ABI alignment of i64 , which is provided by the data layout, and not known by the constant expression itself. This means that there are two levels of constant folding: One that is target-independent and happens on construction, and one that is target-dependent and performed by certain passes like instruction combining. This second folding needs to recursively walk all referenced constant expressions and attempt to fold them at all levels, essentially defeating the benefits of the “always folded” representation. It goes beyond that, however. Instructions and constant expressions typically have the same constraints to permit uniform treatment, which means that we can’t enforce IR validity constraints that depend on data layout. For example, the ptrtoint instruction/expression allows the integer type to have a different size than the pointer type and performs an implicit truncation or zero extension if they don’t match. Such IR does not occur in practice, because it will be canonicalized to an explicit trunc or zext , but all passes still need to deal with the possibility. We can’t actually enforce that the sizes are the same, because constant expressions don’t have data layout. However, data layout is only part of the problem. The other issue is the simple fact that operations can be represented either using an instruction or a constant expression. This means that code generally needs to be able to deal with both representations, to avoid pessimizing optimizations if constant folding (into an expression) has occurred. LLVM is generally fairly good about doing this, thanks to many generic pattern matchers that treat instructions and constant expressions transparently. One significant complication is that a lot of code assumes that performing an operation on a constant is “free”. For example, an optimization that pushes a negation through an instruction sequence might assume that pushing a negation into a constant operand is free, because it will just turn 1 into -1 , or similar. Of course, this is not true for constant expressions, where the negation may not be folded, and you’ll be left with a sub (i64 0, i64 ...) . This is one of the most common sources of infinite loops in the optimizer. A transform pushes an operation into a constant, on the assumption that it will get folded. Thanks to constant expressions, it doesn’t. A different transform may see the new constant expression and perform the reverse change, resulting in an infinite combine loop. Constant expressions also have pathological cases in IR printing: define i64 @test ( i64 %x1 ) { %x2 = mul i64 %x1 , %x1 %x3 = mul i64 %x2 , %x2 %x4 = mul i64 %x3 , %x3 %x5 = mul i64 %x4 , %x4 ret i64 %x5 } Written in instructions, this is a nice linear chain, where each instruction is used twice. Using constant expressions, the same also holds for the in-memory representation. However, printed out as textual IR, there is no way to reuse a constant sub-expression that appears multiple times, so the root value %x1 will end up being repeated 2^4 times. It is easy to construct IR that cannot be printed in any reasonable amount of time. Finally, as divisions can occur inside constant expressions, it’s possible for a constant materialization to trigger undefined behavior. This has odd implications: For example, an instruction may be rendered non-speculatable due to a “constant” operand. This will essentially never occur in practice, but still needs to be considered and accounted for. So what is the alternative here? Having data layout available during construction (even if the resulting constant is data layout independent) would resolve a part of the problem. The remainder would require removing the concept of constant expressions, or rather reducing their scope. Constant expressions do exist for a reason: global initializers, which only accept constants. However, while these initializers can hold arbitrary constant expressions on the LLVM IR level, only limited “relocatable” expressions will be accepted during lowering. The constant expression mechanism is only really needed for such relocatable expressions. LLVM’s mistake was to combine the representation of these relocatable expressions together with the constant folding machinery. Closing thoughts The design issues discussed here are evident with the benefit of hindsight. Of course, there tend to be sensible historical reasons why these choices were made in the first place. For example, having pointer element types and type-based GEPs makes it convenient to implement a front-end that lowers directly to LLVM IR – in other words, clang. It means that the task of keeping track of types is delegated to LLVM. Similarly, I believe that the constant expression design dates back to a time where LLVM still supported a concept of target-independent modules without an associated data layout. The issues covered in this post are related to IR canonicality. There is a separate class of issues related to correctness. The biggest of these is the concept of undef values , which represent a quantum superposition state of all possible bit patterns. Yes, this is exactly as bad as it sounds. Thankfully, undef values are in the process of being replaced by poison values . But all this is a discussion for another time. If you liked this article, you may want to browse my other articles or follow me on Twitter or Mastodon . | 2026-01-13T08:47:52 |
https://porkbun.com/?coupon=DEVOPS&utm_campaign=2023&utm_medium=podcast&utm_source=devops | porkbun.com | An oddly satisfying experience. Toggle navigation porkbun $0.00 (0) products Domains Transfers Local Marketplace Local Auctions 3rd Party Aftermarket Web Hosting All Web Hosting Options Easy WordPress Link In Bio Articulation Sitebuilder Cloud WordPress Shared cPanel Hosting Static Hosting Website Builder Easy PHP Email Hosting All Email Hosting Options Proton Mail Porkbun Email Free Email Forwarding Marketing Tools Textla - SMS Marketing Free WHOIS Privacy Free SSL Certificates Free URL Forwarding transfer Free WordPress SALE! .COM SALE! About --> About Who We Are Why Choose Porkbun Porkbun vs Cloudflare FAQs Resources Knowledge Base Porkbun Blog Service Status Help $0.00 (0) sign in An oddly satisfying experience. 3+ million domains managed by 500K+ customers , who clearly have good taste. bulk search Uh oh! Domain List TLD Selection Enter one domain per line in the box above. You can search for a maximum of 100 domains at a time. Enter a single SLD in the box above and select the TLDs to search below. You can select a maximum of 100 TLDs. abogado ac ac.nz academy accountant accountants actor adult ae.org ag agency ai airforce am apartments app archi army art as asia associates attorney auction audio auto autos baby band bar bargains basketball bayern beauty beer best bet bh bible bid bike bingo bio biz biz.pr black blackfriday blog blue boats bond boo boston bot boutique br.com broker build builders business buzz bz ca cab cafe cam camera camp capital car cards care careers cars casa cash casino catering cc center ceo cfd channel charity chat cheap christmas church city claims cleaning click clinic clothing cloud club club.tw cn.com co co.ag co.bz co.com co.gg co.in co.je co.lc co.nz co.uk coach codes coffee college com com.ag com.ai com.bz com.de com.lc com.mx com.ph com.pr com.sc com.se com.vc community company compare computer condos construction consulting contact contractors cooking cool country coupons courses credit creditcard cricket cruises cv cx cymru cyou dad dance date dating day de de.com deal dealer deals degree delivery democrat dental dentist desi design dev diamonds diet digital direct directory discount diy doctor dog domains download earth ebiz.tw eco education email energy engineer engineering enterprises equipment esq estate eu eu.com events exchange expert exposed express fail faith family fan fans farm fashion fast feedback finance financial firm.in fish fishing fit fitness flights florist flowers fly fm fo foo food football forex forsale forum foundation free fun fund furniture futbol fyi gallery game game.tw games garden gay gb.net geek.nz gen.in gen.nz gg gift gifts gives giving glass global gmbh gold golf gr.com graphics gratis green gripe group guide guitars guru hair haus health healthcare help hiphop hiv hockey holdings holiday homes horse hospital host hosting hot house how hu.net icu id immo immobilien in in.net inc ind.in industries info info.pr ing ink institute insure international investments io irish isla.pr it.com je jetzt jewelry jobs jp.net jpn.com juegos kaufen kids kim kitchen kiwi.nz kyoto l.lc la land lat law lawyer lc lease legal lgbt life lifestyle lighting limited limo link live living llc loan loans lol london lotto love ltd ltda luxe luxury maison makeup management maori.nz market marketing markets mba me me.uk med media melbourne meme memorial men menu mex.com miami mn mobi moda moe moi mom money monster mortgage motorcycles mov movie mu music mx my nagoya name name.pr navy net net.ag net.ai net.bz net.gg net.in net.je net.lc net.nz net.ph net.pr net.vc network new news nexus ngo ninja nl nom.ag now nrw nyc nz observer off.ai one ong onl online ooo org org.ag org.ai org.bz org.gg org.in org.je org.lc org.mx org.nz org.ph org.pr org.sc org.uk org.vc organic osaka p.lc page partners parts party pet ph phd photo photography photos pics pictures pink pizza place plumbing plus poker porn pr press pro pro.pr productions prof promo properties property protection pub pw qpon quest racing radio.am radio.fm realty recipes red rehab reise reisen rent rentals repair report republican rest restaurant review reviews rich rip rocks rodeo rsvp ru.com rugby run sa.com saarland sale salon sarl sbs sc school school.nz schule science se.net security select services sex sexy sh shiksha shoes shop shopping show singles site ski skin soccer social software solar solutions soy spa space spot srl storage store stream studio study style sucks supplies supply support surf surgery sydney systems taipei talk tattoo tax taxi team tech technology tel tennis theater theatre tickets tienda tips tires tm to today tokyo tools top tours town toys trade trading training travel tube tv tw uk uk.com uk.net university uno us us.com us.org vacations vana vc vegas ventures vet viajes video villas vin vip vision vodka vote voto voyage wales wang watch watches webcam website wedding wiki win wine work works world ws wtf xn--5tzm5g xn--6frz82g xn--czrs0t xn--fjq720a xn--q9jyb4c xn--unup4y xn--vhquv xxx xyz yachts yoga yokohama you za.com zip zone Add available domains to the cart. 100 max. .COM from $11.08 .INC from $257.98 .XYZ from $2.04 .ONE from $2.57 Ranked #1 2023, 2024 & 2025 Ranked #1 2025 Trustpilot 4.8 stars 1,700+ reviews All-In-One Domain Management Tools Domains Named the #1 domain registrar by USA Today. We offer lower prices on domain registrations and renewals. Get Domain Web Hosting With Cloud WordPress, Articulation Sitebuilder, a link in bio tool, and multiple cPanel hosting options; our hosting plans have you covered. Learn More Email Hosting Look professional with email hosting. Only $2/month per inbox, billed annually. Compare to $8/month elsewhere. Learn More Transfer Paying too much? Transfer your domain to Porkbun and get the best multi-year value. Transfer Now Save Money With Free Domain Features These premium features come free with every Porkbun domain. Free WHOIS Privacy Keep your private contact information hidden from prying eyes with our WHOIS privacy service. Most registrars charge for this service; we believe your privacy shouldn't come at a price. Learn More Free SSL Certificates Security is important and that's why we offer Let's Encrypt SSL certificates at no charge for all supported domains. We'll even auto renew them for you! Learn More URL Forwarding Quickly and easily point your domain somewhere else with free URL Forwarding. Our URL Forwarder supports permanent, temporary, and masked forwards. Learn More Email Forwarding Give your online presence a more professional feel with up to 20 free email forwards. Learn More Cloudflare DNS Management With free DNS management powered by Cloudflare, you can rest easy knowing your site's DNS will be robust and available. Learn More You're In Good Hooves We are the highest-rated domain name registrar on Trustpilot, as reviewed by real customers. Trustpilot We Stand Behind You Phone Support Tired of talking to an automated system? At Porkbun, the first person you speak to is a knowledgeable domain expert on our support team. 1.855.PORKBUN (1.855.767.5286) 9AM - 5PM Pacific Time Other Hours: Your mileage may vary, but give it a whirl Call Us. Maybe? Knowledge Base Want to find the answers on your own? Check out our extensive knowledge base of how-to articles, instructions, guides, and tutorials. We walk you through how to perform essential tasks like transferring your domain or setting up a custom email address. Visit Knowledge Base Email and Chat Prefer to write out your questions? Get a handcrafted response from a real person. Contact Us × Modal Title Close Close × Modal Title Close porkbun Porkbun is an amazingly awesome ICANN accredited domain name registrar based out of the Pacific Northwest. We're different, we're easy, and we're affordable. Use us, you won't be sorry. If you don't use us we'll be sad, but we'll still love you. Get Pork-Puns In Your Inbox Stay in the loop on all things Porkbun by signing up for our newsletter! 21370 SW Langer Farms Parkway, Suite 142-429 Sherwood, OR 97140, US If you're looking for support, you might be able to answer your own question using our Knowledge Base . Support Hours Impacted From January 3rd to January 11th we will be holding our annual company summit which will impact live and after hours support. Our goal is to provide you with an excellent domain registration experience and support and we all appreciate your patience as the whole company works together to make Porkbun even better. Thank you. Reach our USA-Based phone support team: 1.855.PORKBUN (1.855.767.5286) 9AM - 5PM Pacific Time Other Hours: Your mileage may vary, but give it a whirl support@porkbun.com 24 / 7 Email Support Chat Support Hours Vary Your browser does not support the audio element. This plays a little Porkbun jingle. Stay up to date with Porkbun. Sign up for our cool newsletter and we'll keep you up to date with sweet deals, amazing info, and maybe even the occasional limerick or sonnet. Sign Up Products Domain Names Greatest Deals Local Marketplace Local Auctions 3rd Party Aftermarket Web Hosting Link In Bio Articulation Sitebuilder Cloud WordPress cPanel Hosting Static Hosting Easy PHP Website Builder Email Hosting WHOIS Privacy DNS Management SSL Certificates Email Forwarding URL Forwarding Quick Connect Domain Transfer Affiliate Program Handshake Names Ethereum Name Service International Domain Names API Access Support Contact Us Knowledge Base Payment Options Report Abuse Tools Domain Search Domain Suggestion Generator RDAP (WHOIS) Password Generator Service Status Clear Saved Coupons Don't like our name? The Buniverse Your IP Address Online DNS Lookup Our Company About Us Our Official Blog Careers Branding Guidelines Policies and Legal Privacy Policy Data Disclosure Policy Bug Bounty Program Porkbun Merchandise Awesomeness Copyright © Porkbun LLC. All rights reserved. Porkbun is a Top Level Design Company Made in the USA 🇺🇸 This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply. WARNING: This site has been known to cause a mind blowing experience. We recommend you prepare yourself mentally and if possible be sitting down. Side effects may include saving money, letting out a chuckle, and sporadic oinking. 1 × Modal Title Cancel Continue | 2026-01-13T08:47:52 |
https://2kgam.es/4l6Wst1 | FAQs | NBA 2K26 BUY NOW EN character if not provided --> ENGLISH (EN) ENGLISH (GB) FRANÇAIS (FR) ITALIANO (IT) DEUTSCH (DE) ESPAÑOL (ES) ESPAÑOL (MX) PORTUGUÊS (BR) 日本語 (JP) 한국어 (KR) 繁體中文 (TW) 简体中文 (CN) OUR GAMES OUR GAMES NBA 2K25 NBA 2K24 NBA 2K23 NBA 2K22 NBA 2K21 NBA 2K20 MyNBA NBA 2K MOBILE EN character if not provided --> ENGLISH (EN) ENGLISH (GB) FRANÇAIS (FR) ITALIANO (IT) DEUTSCH (DE) ESPAÑOL (ES) ESPAÑOL (MX) PORTUGUÊS (BR) 日本語 (JP) 한국어 (KR) 繁體中文 (TW) 简体中文 (CN) NBA 2K26 FAQs Q: When is the release date for NBA 2K26? A: NBA 2K26 will be available globally on September 5, 2025. Q: What platforms will I be able to purchase NBA 2K26 on? A: NBA 2K26 will be available for purchase on PlayStation®5, Xbox Series X|S, PlayStation®4, Xbox One, Nintendo Switch 2, Nintendo Switch, and Steam for PC. Q: What Editions will be available for purchase this year? A: NBA 2K26 will offer four different versions of the game: Standard Edition, WNBA Edition, Superstar Edition , and Leave No Doubt Edition . NBA 2K26 Superstar Edition and Leave No Doubt Edition not available in Belgium and South Korea. You can learn more about the different editions on the Buy page. Q: Will there be Early Access* for NBA 2K26? A: Up to 7-day Early Access will be offered to players who pre-order NBA 2K26 Superstar Edition or NBA 2K26 Leave No Doubt Edition. Early Access begins August 29, 2025. Q: What’s included in the NBA 2K26 Superstar Edition? A: NBA 2K26 Superstar Edition is digital only and will be available on PlayStation®5, Xbox Series X|S, and Steam for PC for purchase. This edition includes: 100,000 VC 7-Day Early Access MyTEAM Content Full Series 1 Team Selection Triple Threat Park Free Agent Pack 5x Series 1 Packs 2-Hour 2XP Coin MyCAREER Content 25x 6 Types of Skill Boosts 25x 3 Types of Gatorade Boosts 2-Hour 2XP Coin Shai Gilgeous-Alexander Cover Jersey Q: What’s included in the NBA 2K26 Leave No Doubt Edition? A: NBA 2K26 Leave No Doubt Edition is digital only and will be available on PlayStation®5, Xbox Series X|S, and Steam for PC for purchase. This edition includes: 135,000 VC 7-Day Early Access Season 1 Pro Pass Summer Pass (Season 7-9 Pro Pass) MyTEAM Content Full Series 1 Team Selection Triple Threat Park Free Agent Pack 5x Series 1 Packs 2-Hour 2XP Coin Leave No Doubt MyTEAM Pack MyCAREER Content 25x 6 Types of Skill Boosts 25x 3 Types of Gatorade Boosts 2-Hour 2XP Coin Shai Gilgeous-Alexander Cover Jersey Puffer Jacket Q: Where can I purchase digital copies of NBA 2K26 Leave No Doubt Edition? A: You can purchase digital copies of the NBA 2K26 Leave No Doubt Edition for PlayStation®5, Xbox Series X|S, and Steam for PC. This edition is only available until September 7, 2025. NBA 2K26 Leave No Doubt Edition not available in Belgium and South Korea. Q: What is NBA 2K26 Leave No Doubt Edition loyalty discount**? A: NBA 2K25 players will receive a 10% loyalty discount when pre-ordering NBA 2K26 Leave No Doubt Edition on the same platform. Q: Where can I purchase physical copies of NBA 2K26 WNBA Edition? A: You can purchase physical copies of NBA 2K26 WNBA Edition for PlayStation®5 and Xbox Series X|S exclusively in the United States at GameStop. Q: What platforms will Gen 9 be available for? A: Gen 9 versions of NBA 2K26 will be available on PlayStation®5, Xbox Series X|S, Steam for PC, and Nintendo Switch 2. Q: Will there be crossplay*** in NBA 2K26? A: Enjoy crossplay and play with your friends in NBA 2K26 across PlayStation®5 and Xbox Series X|S consoles. You can experience cross-platform competition in co-op matches and online tournaments on PS5® and Xbox Series X|S consoles. Q: Will there be cross-gen progression in NBA 2K26? A: NBA 2K26 features MyTEAM Cross-Progression and a Shared VC Wallet within the same console family (PlayStation®4 and PlayStation®5, or Xbox One and Xbox Series X|S). MyTEAM Cross-Progression enables all MyTEAM Points and progress to be shared across both versions of NBA 2K26 on generations of consoles in the same console family. Similarly, the Shared VC Wallet allows any earned or purchased VC to be accessible across generations of consoles in the same console family. Q: How does dual entitlement work for NBA 2K26? A: Players that purchase the digital version of the Standard Edition will receive both versions of NBA 2K26 across console generations within the same family (PlayStation®4 and PlayStation®5, or Xbox One and Xbox Series X|S). Using PlayStation®4 as an example, you will receive the PlayStation®4 version of NBA 2K26 and an accompanying digital copy of the PlayStation®5 version, which remains a separate product. For digital purchases of the Standard Edition, the accompanying digital copy will be automatically entitled to your platform account. For physical purchases of the Standard Edition, a redemption code for the accompanying digital copy will be included in the game box. Visit the Buy page for more information on the different editions. Q: What is the MyTEAM Full Series 1 Team Selection? A: The NBA 2K26 Superstar Edition and Leave No Doubt Edition include a selection to receive any franchise teams' full lineup of '26: Series 1 Player Cards. Locking in this collection will reward players with an Amethyst Player Card. Q: What is the MyTEAM Leave No Doubt Promo Pack? A: The NBA 2K26 Leave No Doubt Edition includes two Leave No Doubt Promo Packs, which rewards players with a Galaxy Opal Player Card in December 2025 and an Invincible Player Card in May 2026. SEASON PASS FAQ Season Pass Explainer NBA 2K26 boasts a multitude of new content for you to earn, via the Season rewards ladder and the Season Pass. Cross progression returns in NBA 2K26 and gives you the opportunity to combine your MyCAREER and MyTEAM XP and earn coveted items from both the MyCAREER and MyTEAM progression track. Compete in a variety of formats and reap the rewards as you garner XP and continue leveling up. This year, take advantage of additional content with two premium paid Season Pass options: Pro Pass or the Hall of Fame Pass, featuring more rewards, up to 45,000 earnable VC, XP Boosts, and Level Skips on your journey to Level 40. How you decide to spend your VC and utilize your Boosts is entirely up to you. Set your sights on Level 40 and beyond, and flaunt your collection of rewards on and off the court! There are two Premium Season Pass options available in NBA 2K26 : Pro Pass and Hall of Fame Pass. Each Season, the Pro Pass provides players with access to 40 additional earnable premium rewards. The Hall of Fame Pass includes everything in the Pro Pass, plus 10 immediate Level Skips and a 15% XP Booster that is applied throughout the Season! Play MyCAREER and/or MyTEAM to earn XP and level up to reach Level 40. Pro Pass ($9.99)**** Access to 40 additional earnable premium rewards and up to 45,000 VC as you progress through the Season Four additional Season Pass Rewards automatically applied to your account (separate from the reward track) Hall of Fame Pass ($19.99)**** Includes everything in the Pro Pass 15% XP Booster applied throughout the Season 10 Level Skips immediately applied to the Season reward track 15,000 VC immediately applied to your account (separate from the reward track) Season Pass will be accompanied by 2 additional options: Pass Upgrade ($10)***** Allowing players who purchased the Pro Pass to upgrade to the Hall of Fame Pass (10 Level Skips will be consumed immediately after purchase and progress a player 10 levels beyond the level they are when purchase is made) Level Skips ($1.99) Allowing you to advance by 1 Level in a Season (Level Skips are immediately applied upon purchase. A player cannot purchase more than the total levels they have left to progress.) *Early Access available from 9am PT, August 29. **Loyalty Discount only available via the Platform Store through September 5, 2025. Discount based on 2K’s SRP. Digital only. Loyalty Discount has no cash value and cannot be transferred or refunded. Discount cannot be combined with other offers or discounts, unless expressly authorized by the retailer. Limit 1 per Platform Account. Void where prohibited. See retailer site for details and terms. 2K Games is not responsible for fulfillment of Loyalty Discount. ***Crossplay is only available on PS5 & Xbox Series X|S. Online play requires an Internet connection and NBA 2K Account. Console online play requires separate paid subscription. Terms apply. **** NBA 2K26 Pro Passes and Hall of Fame passes are available for separate purchase and require base game, internet connection and NBA 2K account. Paid premium passes unlock additional rewards for the season that are earnable through gameplay. Progress and rewards reset at the end of each season. ***** NBA 2K26 Pass Upgrade is only available on PlayStation, Xbox, Nintendo Switch 1, and Nintendo Switch 2. LEGAL PRIVACY POLICY TERMS OF SERVICE COOKIE POLICY 2K AD PARTNERS DO NOT SELL OR SHARE MY PERSONAL INFORMATION Cookie Settings LEGAL PRIVACY POLICY TERMS OF SERVICE COOKIE POLICY 2K AD PARTNERS DO NOT SELL OR SHARE MY PERSONAL INFORMATION Cookie Settings SUPPORT 2K.COM NBA 2K SUPPORT 2K STORE 2K ACCOUNT LOGIN SUPPORT 2K.COM NBA 2K SUPPORT 2K STORE 2K ACCOUNT LOGIN © 2005-2025 Take-Two Interactive Software, Inc. Published by 2K. 2K, T2, and related logos, are all trademarks and/or registered trademarks of Take-Two Interactive Software, Inc. The NBA and individual NBA member team identifications reproduced on this product are trademarks and copyrighted designs, and/or other forms of intellectual property, that are the exclusive property of NBA Properties, Inc. and the respective NBA member teams and may not be used, in whole or in part, without the prior written consent of NBA Properties, Inc. © 2025 NBA Properties, Inc. All rights reserved. © 2025 the National Basketball Players Association. All rights reserved. © 2025 Sony Interactive Entertainment LLC. “PlayStation Family Mark”, “PlayStation”, “PS5 logo”, “PS5”, “PS4 logo”, “PS4”, “PlayStation Shapes Logo” and “Play Has No Limits” are registered trademarks or trademarks of Sony Interactive Entertainment Inc. Microsoft, the Xbox Sphere mark, the Series X logo, Series S logo, Series X|S logo, Xbox One, Xbox Series X, Xbox Series S, and Xbox Series X|S are trademarks of the Microsoft group of companies. Nintendo Switch is a trademark of Nintendo. The ESRB ratings icon is a trademark of the Entertainment Software Association. All other marks and trademarks are the property of their respective owners. All rights reserved. | 2026-01-13T08:47:52 |
https://arstechnica.com/google/2026/01/apps-like-grok-are-explicitly-banned-under-googles-rules-why-is-it-still-in-the-play-store/ | Apps like Grok are explicitly banned under Google’s rules—why is it still in the Play Store? - Ars Technica Skip to content Ars Technica home Sections Forum Subscribe Search AI Biz & IT Cars Culture Gaming Health Policy Science Security Space Tech Feature Reviews AI Biz & IT Cars Culture Gaming Health Policy Science Security Space Tech Forum Subscribe Story text Size Small Standard Large Width * Standard Wide Links Standard Orange * Subscribers only Learn more Pin to story Theme HyperLight Day & Night Dark System Search dialog... Sign In Sign in dialog... Sign in Special treatment Apps like Grok are explicitly banned under Google’s rules—why is it still in the Play Store? Google describes apps exactly like Grok and says they are banned from Google Play. Ryan Whitwam – Jan 12, 2026 2:36 pm | 86 A smartphone shows Ani, a virtual anime-style assistant character featured in the Grok 4 AI chatbot developed by xAI. Credit: Cheng Xin / Contributor | Getty Images News A smartphone shows Ani, a virtual anime-style assistant character featured in the Grok 4 AI chatbot developed by xAI. Credit: Cheng Xin / Contributor | Getty Images News Text settings Story text Size Small Standard Large Width * Standard Wide Links Standard Orange * Subscribers only Learn more Minimize to nav Elon Musk’s xAI recently weakened content guard rails for image generation in the Grok AI bot. This led to a new spate of non-consensual sexual imagery on X, much of it aimed at silencing women on the platform. This, along with the creation of sexualized images of children in the more compliant Grok, has led regulators to begin investigating xAI . In the meantime, Google has rules in place for exactly this eventuality—it’s just not enforcing them. It really could not be more clear from Google’s publicly available policies that Grok should have been banned yesterday. And yet, it remains in the Play Store. Not only that—it enjoys a T for Teen rating, one notch below the M-rated X app. Apple also still offers the Grok app on its platform, but its rules actually leave more wiggle room. App content restrictions at Apple and Google have evolved in very different ways. From the start, Apple has been prone to removing apps on a whim, so developers have come to expect that Apple’s guidelines may not mention every possible eventuality. As Google has shifted from a laissez-faire attitude to more hard-nosed control of the Play Store, it has progressively piled on clarifications in the content policy. As a result, Google’s rules are spelled out in no uncertain terms, and Grok runs afoul of them. Google has a dedicated support page that explains how to interpret its “Inappropriate Content” policy for the Play Store. Like Apple, the rules begin with a ban on apps that contain or promote sexual content including, but not limited to, pornography. That’s where Apple stops, but Google goes on to list more types of content and experiences that it considers against the rules. “We don’t allow apps that contain or promote content associated with sexually predatory behavior, or distribute non-consensual sexual content ,” the Play Store policy reads (emphasis ours). So the policy is taking aim at apps like Grok, but this line on its own could be read as focused on apps featuring “real” sexual content. However, Google is very thorough and has helpfully explained that this rule covers AI. Recent additions to Google’s Play Store policy explicitly ban apps like Grok. Credit: Google Recent additions to Google’s Play Store policy explicitly ban apps like Grok. Credit: Google The detailed policy includes examples of content that violate this rule, which include much of what you’d expect—nothing lewd or profane, no escort services, and no illegal sexual themes. After a spate of rudimentary “nudify” apps in 2020 and 2021, Google added language to this page clarifying that “apps that claim to undress people” are not allowed in Google Play. In 2023, as the AI boom got underway, Google added another line to note that it also would remove apps that contained “non-consensual sexual content created via deepfake or similar technology.” Sound like any apps you know? The archetype of a bannable app, approved for teens Taken together, Google’s description of bannable apps describes Grok’s app to a tee. Google made these additions as new threats became apparent, knowing that developers would try to publish AI-undressing apps in the Play Store. The company did not, apparently, think the world’s richest person would be the one pushing digital humiliation tools on its platform. And Google’s response to this situation so far has been to do nothing. The backlash to xAI’s loosened restrictions prompted the company to limit access to image editing slightly. You can no longer edit images on X without paying for a premium plan. However, the Grok app does not have that limitation. Anyone who downloads Grok can use it to create non-consensual sexual content. Since the app is cleared for teens, even devices with parental controls enabled will permit 13- to 17-year-olds to download Grok. There is no paywall, and you don’t even have to log in before editing your first image. The app does ask the user to confirm their birth year, but teenagers would never lie about that, right? This is not xAI’s first problem with non-consensual sexual content. Last year, the AI was widely used to create fake Taylor Swift nudes . However, in that case, users were simply prompting the bot with the singer’s name—Grok can create entirely new images of famous people because the training data includes real images of them. Grok’s newer ability to “edit” images of people is a different and more insidious feature because it can turn anyone into an AI plaything. Ars has reached out to Google to ask why Grok has not been removed and why it has retained a Teen rating. The company has declined to make a statement at this time. So we’re left with a policy that explicitly bans apps like Grok, but Google is taking no action to enforce those policies, allowing impressionable teenagers and unsavory weirdos to use it to sexualize real people. Ryan Whitwam Senior Technology Reporter Ryan Whitwam Senior Technology Reporter Ryan Whitwam is a senior technology reporter at Ars Technica, covering the ways Google, AI, and mobile technology continue to change the world. Over his 20-year career, he's written for Android Police, ExtremeTech, Wirecutter, NY Times, and more. He has reviewed more phones than most people will ever own. You can follow him on Bluesky , where you will see photos of his dozens of mechanical keyboards. 86 Comments Comments Forum view Loading comments... Prev story Next story Most Read 1. Judge: Trump violated Fifth Amendment by ending energy grants in only blue states 2. The most fascinating monitors at CES 2026 3. That time Will Smith helped discover new species of anaconda 4. Is this the beginning of the end for GameStop? 5. Verizon to stop automatic unlocking of phones as FCC ends 60-day unlock rule Customize Ars Technica has been separating the signal from the noise for over 25 years. With our unique combination of technical savvy and wide-ranging interest in the technological arts and sciences, Ars is the trusted source in a sea of information. After all, you don’t need to know everything, only what’s important. More from Ars About Us Staff Directory Ars Newsletters General FAQ Posting Guidelines RSS Feeds Contact Contact us Advertise with us Reprints Manage Preferences © 2026 Condé Nast. All rights reserved. Use of and/or registration on any portion of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Ars Technica Addendum and Your California Privacy Rights . Ars Technica may earn compensation on sales from links on this site. Read our affiliate link policy . The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices | 2026-01-13T08:47:52 |
https://future.forem.com/t/ai | Artificial Intelligence - Future Forem Feed Follow new Subforems to improve your feed DEV Community Follow A space to discuss and keep up software development and manage your software career Future Follow News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Open Forem Follow A general discussion space for the Forem community. If it doesn't have a home elsewhere, it belongs here Gamers Forem Follow An inclusive community for gaming enthusiasts Music Forem Follow From composing and gigging to gear, hot music takes, and everything in between. Vibe Coding Forem Follow Discussing AI software development, and showing off what we're building. Popcorn Movies and TV Follow Movie and TV enthusiasm, criticism and everything in-between. DUMB DEV Community Follow Memes and software development shitposting Design Community Follow Web design, graphic design and everything in-between Security Forem Follow Your central hub for all things security. From ethical hacking and CTFs to GRC and career development, for beginners and pros alike Golf Forem Follow A community of golfers and golfing enthusiasts Crypto Forem Follow A collaborative community for all things Crypto—from Bitcoin to protocol development and DeFi to NFTs and market analysis. Parenting Follow A place for parents to the share the joys, challenges, and wisdom that come from raising kids. We're here for them and for each other. Forem Core Follow Discussing the core forem open source software project — features, bugs, performance, self-hosting. Maker Forem Follow A community for makers, hobbyists, and professionals to discuss Arduino, Raspberry Pi, 3D printing, and much more. HMPL.js Forem Follow For developers using HMPL.js to build fast, lightweight web apps. A space to share projects, ask questions, and discuss server-driven templating Dropdown menu Dropdown menu Skip to content Navigation menu Search Powered by Algolia Search Log in Create account Future Close Artificial Intelligence Follow Hide Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities found in humans and in nature. Create Post submission guidelines Posts about artificial intelligence. Older #ai posts 1 2 3 4 5 6 7 8 9 … 75 … 1769 Posts Left menu 👋 Sign in for the ability to sort posts by relevant , latest , or top . Right menu Therapeutic Nihilism: The Dark Side of Evidence-Based Medicine Thinking Healer Thinking Healer Thinking Healer Follow Jan 12 Therapeutic Nihilism: The Dark Side of Evidence-Based Medicine # ai # medical Comments Add Comment 5 min read MCP Hit 97 Million Downloads in One Year. Security Researchers Say It Wasn't Ready. Bilal Saeed Bilal Saeed Bilal Saeed Follow Jan 7 MCP Hit 97 Million Downloads in One Year. Security Researchers Say It Wasn't Ready. # mcp # ai # productivity Comments Add Comment 3 min read Beyond Generic Generation: AI Content Strategy in 2026 Del Rosario Del Rosario Del Rosario Follow Jan 6 Beyond Generic Generation: AI Content Strategy in 2026 # ai # productivity # marketing # contentmarketing Comments Add Comment 3 min read Harvard just proved AI tutors beat classrooms. Now what? Kevin Campbell Kevin Campbell Kevin Campbell Follow Jan 5 Harvard just proved AI tutors beat classrooms. Now what? # ai # productivity Comments Add Comment 2 min read Trust: The Invisible Architecture of Healing Thinking Healer Thinking Healer Thinking Healer Follow Jan 5 Trust: The Invisible Architecture of Healing # ai Comments Add Comment 11 min read Navigating the AI Legal Minefield: Your Business Guide tanvir khan tanvir khan tanvir khan Follow Dec 31 '25 Navigating the AI Legal Minefield: Your Business Guide # ai # privacy # security Comments Add Comment 8 min read Tesla's 4680 battery supply chain collapses as partner writes down deal by 99% Aman Shekhar Aman Shekhar Aman Shekhar Follow Dec 30 '25 Tesla's 4680 battery supply chain collapses as partner writes down deal by 99% # ai # machinelearning # techtrends Comments Add Comment 5 min read Your Morning AI Briefing: Latest Developments in ChatGPT, Enterprise Adoption, and Image Generation Ethan Zhang Ethan Zhang Ethan Zhang Follow Dec 30 '25 Your Morning AI Briefing: Latest Developments in ChatGPT, Enterprise Adoption, and Image Generation # news # ai # chatgpt # machinelearning Comments Add Comment 5 min read I want people to document their entire lives from childhood to adulthood. hushuai wang hushuai wang hushuai wang Follow Dec 29 '25 I want people to document their entire lives from childhood to adulthood. # ai # productivity # education Comments Add Comment 5 min read Ethics and Governance in AI adoption for Indian Businesses PHD Chamber PHD Chamber PHD Chamber Follow Dec 30 '25 Ethics and Governance in AI adoption for Indian Businesses # ai # autonomy # privacy Comments Add Comment 7 min read DeSantis Declares War on AI: 'Rejecting the Unthinkable' Malik Abualzait Malik Abualzait Malik Abualzait Follow Dec 29 '25 DeSantis Declares War on AI: 'Rejecting the Unthinkable' # have # reject # that # ai Comments Add Comment 2 min read How Smart PCs Could Change Daily Workflows Amelia Hebrew Amelia Hebrew Amelia Hebrew Follow Dec 29 '25 How Smart PCs Could Change Daily Workflows # ai # science Comments Add Comment 1 min read AI Research Survey Hemanth Kumar Reddy Malle Hemanth Kumar Reddy Malle Hemanth Kumar Reddy Malle Follow Dec 28 '25 AI Research Survey # ai # machinelearning # contentwriting # programming Comments Add Comment 1 min read Tech Pulse – Weekly Tech Digest January 11, 2026 Om Shree Om Shree Om Shree Follow Jan 11 Tech Pulse – Weekly Tech Digest January 11, 2026 # ai # blockchain # security # science 15 reactions Comments Add Comment 4 min read the modern full stack choice THIYAGARAJAN varadharajan THIYAGARAJAN varadharajan THIYAGARAJAN varadharajan Follow Dec 28 '25 the modern full stack choice # ai # privacy # productivity Comments Add Comment 1 min read Experts explore new mushroom which causes fairytale-like hallucinations Aman Shekhar Aman Shekhar Aman Shekhar Follow Dec 27 '25 Experts explore new mushroom which causes fairytale-like hallucinations # ai # machinelearning # techtrends Comments Add Comment 5 min read AI Just Cracked a 99-Year Problem artificialintelligenceee artificialintelligenceee artificialintelligenceee Follow Dec 29 '25 AI Just Cracked a 99-Year Problem # news # ai # programming 1 reaction Comments Add Comment 4 min read From Project Manager to AI-Orchestrator: Leading in a world where decisions are made by machine Swatantra Kumar Swatantra Kumar Swatantra Kumar Follow Dec 27 '25 From Project Manager to AI-Orchestrator: Leading in a world where decisions are made by machine # ai # aiorchestrator # digitaltransformation # pmo Comments Add Comment 4 min read The New CFO Toolkit: Data, AI, and Cyber Risk in U.S. Corporate Finance Md Tauhid Hossain Rubel Md Tauhid Hossain Rubel Md Tauhid Hossain Rubel Follow Dec 27 '25 The New CFO Toolkit: Data, AI, and Cyber Risk in U.S. Corporate Finance # ai # fintech # security Comments Add Comment 5 min read AI News Roundup: What You Need to Know This Week Over Your Morning Coffee Ethan Zhang Ethan Zhang Ethan Zhang Follow Dec 29 '25 AI News Roundup: What You Need to Know This Week Over Your Morning Coffee # news # ai # technology # machinelearning Comments Add Comment 5 min read How we lost communication to entertainment Aman Shekhar Aman Shekhar Aman Shekhar Follow Dec 28 '25 How we lost communication to entertainment # ai # machinelearning # techtrends Comments Add Comment 5 min read Coffee Break AI Update: 5 Game-Changing AI Developments You Need to Know About Today Ethan Zhang Ethan Zhang Ethan Zhang Follow Dec 25 '25 Coffee Break AI Update: 5 Game-Changing AI Developments You Need to Know About Today # news # ai # technology # machinelearning Comments Add Comment 6 min read AI Strategy Isn’t About Automation. It’s About Decision Advantage Vipul Gupta Vipul Gupta Vipul Gupta Follow Dec 26 '25 AI Strategy Isn’t About Automation. It’s About Decision Advantage # aistrategy # automation # ai # aicounsluting Comments Add Comment 3 min read How to Create Christmas Videos with AI: Complete Holiday Content Guide ayi ayi ayi Follow Dec 25 '25 How to Create Christmas Videos with AI: Complete Holiday Content Guide # sorastats # sora # ai # openai 1 reaction Comments Add Comment 7 min read The Future of AI Agents Isn’t What You Think — Here’s What Actually Matters Jefree Sujit Jefree Sujit Jefree Sujit Follow Dec 23 '25 The Future of AI Agents Isn’t What You Think — Here’s What Actually Matters # ai # agents # technology # development 1 reaction Comments 1 comment 4 min read loading... trending guides/resources How to Use Character.AI: A Step-by-Step Guide for Beginners ChatGPT Opens to Erotic Conversations Dobot unveils $1,000 Rover X1 AI robot dog with smart tracking and multi-rolehome support 2026: The average developer's year disappears and the most will struggle 99% of Users Don’t Know About These 10 ChatGPT Secret Codes How AI Will Transform CAD Software in the Next 5 Years (Autodesk, SolidWorks, CATIA & Beyond) AI Content Marketing: 2025 Strategies That Actually Work 7 AI SEO Strategies for SaaS Growth in 2026 How fintech will disappear into daily life and completely change how money works AI's $1B Problem: Can Human Labor Be Replaced for Profit? Are we living in simulated world?INVU hypothesis The AI Hype Reckoning: A 2025 Retrospective on the Bubble That Burst Expectations Tech Pulse – Weekly Tech Digest January 11, 2026 Building a Cloud-Based Crypto Mining Dashboard App for Android Grok AI: A Deep Dive into xAI’s Maverick Chatbot Inside the Latest Tech Breakthroughs Shaping Our Future ChatGPT : mon lutin numérique Jeff Su: 4 Next-Level ChatGPT Techniques Alchemy Reimagined: AI-Powered Atom Creation for Novel Materials Harvard just proved AI tutors beat classrooms. Now what? 💎 DEV Diamond Sponsors Thank you to our Diamond Sponsors for supporting the DEV Community Google AI is the official AI Model and Platform Partner of DEV Neon is the official database partner of DEV Algolia is the official search partner of DEV Future — News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Home About Contact Code of Conduct Privacy Policy Terms of Use Built on Forem — the open source software that powers DEV and other inclusive communities. Made with love and Ruby on Rails . Future © 2025 - 2026. Stay on the cutting edge, and shape tomorrow Log in Create account | 2026-01-13T08:47:52 |
https://www.reddit.com/r/minnesota/ | Reddit - The heart of the internet Skip to main content Open menu Open navigation Go to Reddit Home r/minnesota Get App Get the Reddit app Log In Log in to Reddit Expand user menu Open settings menu :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> r/minnesota You Betcha members online Create Post Feed About Best Open sort options Best Hot New Top Rising Change post view Card Compact Community highlights /r/Minnesota Monthly FAQ / Moving-to-MN / Simple Questions Thread - January 2026 :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> votes • comments Omar from way downtown :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> u/HeavyVeterinarian350 • Omar from way downtown High Risk Saint Cloud u/EveningAd6434 • Saint Cloud Politics 👩⚖️ Sorry, something went wrong when loading this video. View in app ICE in Minneapolis abducted and disappeared a mother, while she was taking her daughter to school this morning. (1/12/26) :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> u/I_may_have_weed • ICE in Minneapolis abducted and disappeared a mother, while she was taking her daughter to school this morning. (1/12/26) High Risk Sorry, something went wrong when loading this video. View in app You Betcha Created May 8, 2008 Public Anyone can view, post, and comment to this community 2.1M 181K r/minnesota Rules 1 Minnesota-Related Posts Only All posts must be clearly and substantially related to Minnesota and relevant to a large portion of the state. Posts that have no relevance/interest beyond a local community, have only a tangential or incidental connection to Minnesota, or are national or international news items without unique relevance to Minnesota are not permitted. 2 Content Must Be Fresh & Relevant Posts about current events must be timely and relevant to ongoing discussion. Outdated news or commentary on past events that no longer have current significance may be removed. Posts on topics of cultural or historical interest are not precluded by this rule. 3 Follow Site-Wide Rules & Reddiquette It is the responsibility of every user to be familiar with and follow the Site-Wide Rules and Reddiquette when participating in the subreddit. 4 No Discrimination or Personal Attacks Personal attacks, harassment, or content that targets individuals or groups based on protected characteristics are not permitted. This includes the use of any slurs. Critique ideas and actions, not people or their identity. 5 No Spam or Low-Quality Content Posts must show genuine effort and relevance to the community. Karma-farming, low-effort memes, recycled content, AI-generated submissions without meaningful human input, surveys, petitions, buy/sell/trade requests, crowdfunding, service/business recommendations, job openings, etc. are not allowed. 6 No Trolling Engaging content for the primary purpose of trolling, rage-baiting, harassing, annoying, or attacking other users is not allowed. 7 No Adult Content This is a SFW community with users of all ages. Do not post content containing nudity, pornography, excessive profanity, or other content that a reasonable user would not want to be seen accessing in a public setting such as a workplace. 8 No Unverified or Unreliable Information We recognize information moves quickly. However, users may not post false information, manipulated content, unsubstantiated rumors, unverified claims, or news content from disreputable sources. 9 Follow Post Title Guidelines Post titles that are misleading, exaggerated, or sensationalized to provoke clicks at the expense of accuracy or context are not allowed. When sharing a titled work, the title of the post must be the original title with or without a properly punctuated quote from the work. 10 No Duplicate or Substantially Similar Posts Do not submit duplicate or substantially similar content. This includes reposting the same story, event, or opinion from different sources. New posts on the same subject are permitted only when they add substantial new context, information, or developments. 11 No Social Media or Paywalled Links Direct links to social media are not allowed. This includes (but is not limited to) Twitter/X, Facebook, Instagram, TikTok, and Threads. Video and image sites like YouTube and Imgur are exempted from this rule. Likewise, links to news articles or blog posts that require a subscription or other payment to view are not permitted without providing an alternative way to view the content for free, such as gift links, archive links, or pasting the text of the article into the post. 12 FAQ Topics May Only Be Discussed in the Pinned FAQ Thread There are several topics that are asked about very frequently in the community. We have compiled these subjects into a monthly pinned post. Discussion of any topic listed in the monthly pinned post may only be discussed in the comment section of that post. Any new posts made on these topics will be removed. Featured Minnesota Subreddits :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> r/Minneapolis 220,268 members :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> r/saintpaul 41,083 members :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> r/duluth 37,633 members :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> r/TwinCities 227,399 members :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> r/TWINCITIESHOUSING 3,879 members :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> r/twincitiessocial 32,268 members :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> r/MNJobs 3,395 members :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> r/MinnesotaCamping 14,377 members :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> r/BWCA 14,679 members :first-child]:h-full [&>:first-child]:w-full [&>:first-child]:mb-0 [&>:first-child]:rounded-[inherit] h-full w-full [&>:first-child]:overflow-hidden [&>:first-child]:max-h-full"> r/MNHistory 849 members Moderators Moderator list hidden. Learn More View all moderators Installed Apps Remove Macro Modmail Quick User Summary Hive Protector Admin Tattler Trending Tattler Bot Bouncer Reddit Rules Privacy Policy User Agreement Accessibility Reddit, Inc. © 2026. All rights reserved. Expand Navigation Collapse Navigation | 2026-01-13T08:47:52 |
https://replit.com/pricing | Pricing - Replit Skip to content Products Agent Design Databases Publish Apps Security Integrations Mobile For Work Teams Replit for teams to build together Enterprise Replit with Enterprise-grade security & controls Use Cases Business Apps Rapid Prototyping Roles Enterprise PM Designers Operations Software Developers Small Businesses SMB Owners Founders Resources Documentation Community Expert Network Customer Stories Gallery Blog News Pricing Careers Contact sales Log in Create account Products Agent Design Databases Publish Apps Security Integrations Mobile For Work Teams Replit for teams to build together Enterprise Replit with Enterprise-grade security & controls Use Cases Business Apps Rapid Prototyping Roles Enterprise PM Designers Operations Software Developers Small Businesses SMB Owners Founders Resources Documentation Community Expert Network Customer Stories Gallery Blog News Pricing Careers Contact sales Log in Create account Pricing Autonomy for all. Choose the best plan for you. Monthly Yearly Save $60 Starter Free Explore the possibilities of making apps on Replit. Sign up Replit Agent trial included 10 development apps (with temporary links) Private and public apps Limited build time, without long full autonomy Replit Core $20 per month billed annually Make, launch, and scale your apps. Join Replit Core Full Replit Agent access $25 of monthly credits Private and public apps Access to latest models Publish and host live apps Pay-as-you-go for additional usage Autonomous long builds Teams $35 per user , per month billed annually Bring the power of Replit to your entire team. Join Replit Teams Everything included with Replit Core $40/mo in usage credits included Credits granted upfront on annual plan 50 Viewer seats Centralized billing Role-based access control Private deployments Pay-as-you-go for additional usage Enterprise Custom pricing Meet your security and performance needs. Contact us Everything in Teams Custom Viewer Seats SSO/SAML SCIM Advanced privacy controls Custom pricing Dedicated support Compare plans Starter Core Teams Enterprise Replit AI Agent Limited Autonomy Basic Advanced Advanced Advanced Code Completion Code Generation Basic Advanced Advanced Advanced Debugger Basic Advanced Advanced Advanced Development vCPUs 1 4 8 Up to 64 vCPUs Memory (GiB) 2 8 16 Up to 128 GiB RAM Outbound data transfer (GiB) 1 100 1,000 Custom SSH access Apps 10 Unlimited Unlimited Unlimited Private Apps Collaborators 1 3 All team members All team members Development Time (minutes) 1200 Unlimited Unlimited Unlimited Storage Storage per app (GiB) 2 50 256 Custom Replit Database PostgreSQL storage (GiB) Custom PostgreSQL compute (hours) Custom App Storage App Storage data transfer (GiB) App Storage advanced operations App Storage basic operations Deployments Outbound data transfer (GiB) 10 100 1,000 Custom Reserved VM deployments Autoscale deployments Autoscale compute units Autoscale requests Scheduled deployments Scheduled compute units Static deployments 1 Private deployments Security & Compliance Role-based access control SSO Single-tenant with VPC Coming soon Custom invoicing Member Support Member Support Member-only events Early access to new features Member community Onboarding support Get started with Replit Teams Get enhanced security and compute for professional developers and teams shipping to production. Get started "The rapid prototypes we build on Replit shift the dialog from 'Should we?' to 'How should we?' and that's a world of difference when driving substantive change." Chris Stevens, CMO of Spot Hero Handy Links About us Vibe Coding 101 Help How to guides Import from GitHub Status Additional resources Brand kit Partnerships Legal Terms of service Commercial agreement Privacy Subprocessors DPA Report abuse Connect X / Twitter Tiktok Facebook Instagram Linkedin Scroll to top All rights reserved. Copyright © 2026 Replit, Inc. | 2026-01-13T08:47:52 |
https://claude.com/product/claude-code | Claude Code - AI coding agent for terminal & IDE | Claude -------> Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Product Product / Claude Code Explore here Ask questions about this page Copy as markdown ✽ Debugging... Claude Code: AI-powered coding assistant for developers Built for developers Work with Claude directly in your codebase. Build, debug, and ship from your terminal, IDE, Slack, or the web. Describe what you need, and Claude handles the rest. Get Claude Code On the web VS Code JetBrains Slack curl -fsSL https://claude.ai/install.sh | bash Copy command to clipboard irm https://claude.ai/install.ps1 | iex Copy command to clipboard Or read the documentation Try Claude Code Try Claude Code Try Claude Code Developer docs Developer docs Developer docs Use Claude Code where you work Terminal IDE Web and iOS Slack Active ╭───────────────────────────╮ │ │ │ ✶ Welcome to Claude Code │ │ │ ╰───────────────────────────╯ > Think harder... while(curious) { question everything(); dig_deeper(); connect_dots(unexpected); if (stuck) { keep_thinking(); } } * Brewing… Terminal Work with Claude directly in your terminal. Claude explores your codebase context, answers questions, and make changes. It can even use all your CLI tools. Get Claude Code On the web VS Code JetBrains Slack curl -fsSL https://claude.ai/install.sh | bash Copy command to clipboard irm https://claude.ai/install.ps1 | iex Copy command to clipboard Or read the documentation Try Claude Code Try Claude Code Try Claude Code Developer docs Developer docs Developer docs Prompt My colleagues recently published the attached single-cell dataset that describes gene expression differences between adult and pediatric liver samples with a focus on the immune system. I would like to explore these samples but focus on the parenchymal cells and differences between adult and pediatric liver. Can you help me first go through the differentially expressed genes and create a heatmap and then also identify pathways or sets of genes that are enriched in each sample? VS Code and JetBrains IDEs Run Claude Code directly in your IDE and see Claude's changes as visual diffs. Native extensions are available for VS Code, VS Code forks like Cursor and Windsurf, and JetBrains. VS Code VS Code VS Code JetBrains JetBrains JetBrains View prompt View prompt View prompt Prompt My colleagues recently published the attached single-cell dataset that describes gene expression differences between adult and pediatric liver samples with a focus on the immune system. I would like to explore these samples but focus on the parenchymal cells and differences between adult and pediatric liver. Can you help me first go through the differentially expressed genes and create a heatmap and then also identify pathways or sets of genes that are enriched in each sample? Web & iOS research preview Delegate tasks to Claude from your browser or the Claude iOS app. Great for bug fixes, routine tasks, and kicking off the work while on-the-go. Open in browser Open in browser Open in browser View prompt View prompt View prompt Prompt My colleagues recently published the attached single-cell dataset that describes gene expression differences between adult and pediatric liver samples with a focus on the immune system. I would like to explore these samples but focus on the parenchymal cells and differences between adult and pediatric liver. Can you help me first go through the differentially expressed genes and create a heatmap and then also identify pathways or sets of genes that are enriched in each sample? Bring Claude to Slack Beta Ask your Slack workspace admin to approve the Claude app from the Slack App Marketplace , then use your existing Claude account to get started. Add to Slack Add to Slack Add to Slack Get started with Claude Code Individual Team & Enterprise Active Pro Claude Code is included in your Pro plan. Perfect for short coding sprints in small codebases with access to both Sonnet 4.5 and Opus 4.5. $17 Per month with annual subscription discount ($200 billed up front). $20 if billed monthly. Try Claude Try Claude Try Claude Max 5x Claude Code is included in your Max plan. Great value for everyday use in larger codebases.
$100 Per person billed monthly Try Claude Try Claude Try Claude Max 20x Even more Claude Code included in your Max plan. Great value for power users with the most access to Claude models. $200 Per person billed monthly Try Claude Try Claude Try Claude Claude API Pay as you go with standard Claude API pricing. Deploy to unlimited developers with no per-seat fee or platform charges. Start building Start building Start building Team Claude Code is included with Team plan premium seats. Includes self-serve seat management and additional usage at standard API rates, plus access to both Sonnet 4.5 and Opus 4.5. $150 Per person / month. Minimum 5 members. Get the Team plan Get the Team plan Get the Team plan <path d="M240.04 456.37C239.59 437.27 240.37 437.26 239.92 418.16C239.48 399.08 239.67 399.02 239.58 379.89C239.54 370.33 239.34 365.56 239.11 360.8C238.87 356.05 238.7 351.25 238.46 341.85C238.42 340.49 238.37 339.23 238.31 338.11C238.28 337.55 238.25 337.02 238.22 336.51C238.2 336.26 238.19 336.02 238.17 335.79V335.69C238.13 335.5 238.11 335.51 238.07 335.47C238.01 335.45 237.96 335.47 237.91 335.47C237.87 335.47 237.91 335.48 237.82 335.49C237.36 335.48 236.91 335.47 236.47 335.45C234.66 335.43 232.89 335.45 231 335.49C227.21 335.57 222.88 335.72 216.14 335.94C197.1 336.57 196.9 335.43 177.82 335.64C170.37 335.73 165.86 335.88 161.8 336.11C159.77 336.22 157.85 336.36 155.78 336.55C154.76 336.65 153.67 336.76 152.6 336.92L152.4 336.95H152.33L152.19 336.99C152.08 337.01 152.07 337.02 152.01 337.03C151.91 337.06 151.81 337.09 151.72 337.14C151.66 337.17 151.57 337.32 151.55 337.53C151.55 337.58 151.55 337.64 151.53 337.7C151.53 337.83 151.52 337.96 151.51 338.1C151.48 338.88 151.46 339.77 151.47 340.76C151.52 345.3 151.76 348.92 151.9 351.89C152.05 354.89 152.17 357.28 152.29 359.68C152.49 364.49 152.75 369.32 152.69 379.04C152.64 381.44 152.6 383.54 152.57 385.42C152.53 387.28 152.49 388.91 152.45 390.4C152.36 393.38 152.29 395.76 152.22 398.15C152.06 402.92 151.92 407.69 151.89 417.25C151.87 436.35 152.37 436.36 152.47 455.44C152.57 469.52 150.43 471.4 147.5 471.49C144.61 471.58 142.63 469.66 142.52 455.51C142.42 436.39 141.43 436.4 141.45 417.29C141.47 407.73 141.78 402.95 142.1 398.17C142.25 395.78 142.42 393.39 142.55 390.4C142.61 388.9 142.67 387.25 142.74 385.38C142.8 383.49 142.86 381.4 142.89 379.06C142.96 369.65 142.79 364.93 142.67 360.19C142.59 357.82 142.5 355.44 142.4 352.47C142.29 349.48 142.08 345.94 142.01 340.96C142.01 340.07 142.01 339.2 142.03 338.35C142.03 338.14 142.04 337.92 142.05 337.71C142.06 337.45 142.08 337.2 142.09 336.95C142.12 336.3 142.22 335.68 142.28 335.06C142.48 333.86 142.73 332.72 143.2 331.79C143.62 330.82 144.37 330.1 145.05 329.47C146.01 328.83 147.06 328.39 148.13 328.07C149.23 327.78 150.29 327.58 151.18 327.43C152.48 327.21 153.62 327.05 154.72 326.9C156.9 326.61 158.83 326.38 160.9 326.18C165.04 325.77 169.71 325.47 177.57 325.37C187.13 325.26 191.87 325.43 196.6 325.53C201.35 325.64 206.11 325.7 | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netsec/best/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://forge.rust-lang.org/triagebot/pr-assignment.html | PR Assignment - Rust Forge Keyboard shortcuts Press ← or → to navigate between chapters Press S or / to search in the book Press ? to show this help Press Esc to hide this help Auto Light Rust Coal Navy Ayu Rust Forge PR Assignment Triagebot handles automatic and manual assignment of GitHub PRs. It also handles welcoming new users when they post a PR. Contributors to the rust-lang/rust repository can track and manage their own work queue using Zulip integration. See Review queue tracking . You can check which pull requests in the rust-lang organization are assigned to you at this GitHub URL . Usage Automatic assignment of new PRs is handled by the configuration in the triagebot.toml , described below . Manual assignment can be done by posting a comment on the PR with the text: r? @octocat — Assigns a specific user. r? octocat — The @ is optional. r? libs — Chooses a random person from the libs ad-hoc group defined in triagebot.toml . For example, for the rust-lang/rust repository, see triagebot.toml for a list of ad-hoc group names. r? rust-lang/libs — The rust-lang/ org name prefix is optional. r? rustdoc — Chooses a random person from the rustdoc team. See the teams database for a list of team names. r? rust-lang/rustdoc — The org name prefix is optional. It is strongly recommended that you do not use @ , as that will subscribe and notify the entire team to the PR. When choosing a user from a team, triagebot only looks at direct team members (it ignores subteams). When looking up a name, triagebot will first look at ad-hoc groups, then rust-lang teams, and if it doesn’t match either of those it assumes it is a GitHub user. PRs can only be assigned to users with write permissions to the repo, any rust-lang org members with read permissions, or anyone who has commented on the PR. To enable the ability for users to post a comment with r? name to set the assignment to a specific user, add a [assign] table to triagebot.toml . Ghost Using r? ghost in the initial PR top-level comment when opening a PR will disable triagebot’s auto-assignment. ghost is GitHub’s placeholder account for deleted accounts. It is used here for convenience. This is typically used for rollups or experiments where you don’t want any assignments or noise. Rerolling If you want to assign the pull request to a different reviewer based on its file diff (in other words, if you want to replicate what happens when you open a PR without an explicit r? ), you can use the @rustbot reroll command. Configuration PR assignment is enabled on the repository by having an [assign.owners] table in triagebot.toml : # These are ad-hoc groups that can be referenced in `r?` and the `owners` table below. # The values may contain GitHub usernames, other groups, or rust-lang teams. # The `@` is optional. # Group names should be lowercase. [assign.adhoc_groups] libs = ["@joshtriplett", "@Mark-Simulacrum", "@kenntytm", "@m-ou-se", "@thomcc"] # Can reference other groups. compiler = ["compiler-team", "compiler-team-contributors"] compiler-team = ["cjgillot", "estebank"] compiler-team-contributors = ["compiler-errors", "jackh726"] # Can reference rust-lang teams. libs = ["rust-lang/libs-api"] # This is a special group that will be used if none of the `owners` entries matches. fallback = ["@Mark-Simulacrum"] # This specifies users, groups, or teams to assign for different paths. # Triagebot will pick one person to assign. # Paths are gitignore-style matches. [assign.owners] # Examples of assigning individuals. "Cargo.lock" = ["@Mark-Simulacrum"] "/library/std/src/sys/windows" = ["@ChrisDenton"] # Example of assigning to a group. "/library/std" = ["libs"] # Supports gitignore patterns. "*.js" = ["@octocat"] # If you want to match all files, `*` should be sufficient. "*" = ["@octocat"] # Can use teams from the rust-lang teams database. "/src/tools/cargo" = ["@rust-lang/cargo"] If the owners map is configured, then triagebot will automatically select a reviewer based on which files were modified in the PR. Vacation If a reviewer wants to temporarily prevent themselves from being assigned (automatically or manually) they can add themselves to the special assign.users_on_vacation group. [assign] users_on_vacation = ["jyn514", "ChrisDenton"] On rust-lang/rust , you can also configure vacation using Zulip integration . Additional new PR trigger options Triagebot will also post a welcome message to the user. Its behavior depends on a few factors: PR authors who have not previously made any commits will get a more detailed welcome message. PR authors who have made commits will get an abbreviated message. If the initial PR comment has an r? command, then no welcome will be posted. There are several options in triagebot.toml for controlling its behavior on new PRs: [assign] # If set, posts a warning message if the PR is opened against a non-default # branch (usually main or master). warn_non_default_branch = true # If set, the welcome message to new contributors will include this link to # a contributing guide. contributing_url = "https://rustc-dev-guide.rust-lang.org/contributing.html" Additionally, triagebot will post a comment with a warning if the PR modifies any submodules. Exceptions to default branch warning Some PRs may have a different default branch than the rest of the PRs, in these cases it is possible to add exceptions based on the PR title, which will therefore warn if the PR is targeting a different branch than specified. [assign] warn_non_default_branch.enable = true [[assign.warn_non_default_branch.exceptions]] title = "[beta" # title contains "[beta" in it branch = "beta" Custom messages Some repositories may want to use custom messages instead of the preconfigured ones. It is possible to customize the message shown when auto-assigning (or not) a reviewer. If provided, the contributing_url will still be used. [assign.custom_messages] auto-assign-someone = "Thanks for the contribution, assigning {assignee}!" # only required if auto-assign (`[assign.owners]` is configured auto-assign-no-one = """ Thanks for the contribution! Unfortunately, no reviewer could be found at the moment. """ The messages content are given as-is to GitHub (modulo {assignee} ), the content can therefore use whatever GitHub supports. Implementation See parser/src/command/assign.rs and src/handlers/assign.rs . | 2026-01-13T08:47:52 |
https://share.transistor.fm/s/494ca018 | APIs You Won't Hate | Stigg: Infrastructure for pricing models with Anton Zagrebelny APIs You Won't Hate 40 ? 30 : 10)" @keyup.document.left="seekBySeconds(-10)" @keyup.document.m="toggleMute" @keyup.document.s="toggleSpeed" @play="play(false, true)" @loadedmetadata="handleLoadedMetadata" @pause="pause(true)" preload="none" @timejump.window="seekToSeconds($event.detail.timestamp); shareTimeFormatted = formatTime($event.detail.timestamp)" > Trailer Bonus 10 40 ? 30 : 10)" class="seek-seconds-button" > 40 ? 30 : 10"> Subscribe Share More Info Download More episodes Subscribe newValue ? setTimeout(() => copied = false, 2500) : null)" @click="copied = copyFeedUrl()" class="form-input-group" > Copied to clipboard Apple Podcasts Spotify Pocket Casts Overcast Castro YouTube Goodpods Goodpods Metacast Amazon Music Pandora CastBox Anghami Anghami Fountain JioSaavn Gaana iHeartRadio TuneIn TuneIn Player FM SoundCloud SoundCloud Deezer Podcast Addict Share newValue ? setTimeout(() => copied = false, 2500) : null)" @click="copied = copyShareUrl()" class="form-input-group" > Share Copied to clipboard newValue ? setTimeout(() => copied = false, 2500) : null)" @click="copied = copyEmbedHtml()" class="form-input-group" > Embed Copied to clipboard Start at Trailer Bonus Full Transcript View the website updateDescriptionLinks($el))" class="episode-description" > Chapters March 7, 2023 by APIs You Won't Hate View the website Listen On Apple Podcasts Listen On Spotify Listen On YouTube RSS Feed Subscribe RSS Feed RSS Feed URL Copied! Follow Episode Details / Transcript Stigg: https://www.stigg.io/ - API-first pricing and packaging Stigg is Hiring: https://jobs.lever.co/stigg Find Anton Zagrebelny onlin: Linkedin - GitHub — Thanks for listening to APIs You Won't Hate Creators and Guests Host Mike Bifulco Cofounder and host of APIs You Won't Hate. Blogs at https://mikebifulco.com Into 🚴♀️, espresso ☕, looking after 🌍. ex @Stripe @Google @Microsoft Guest Anzon Zagrebelny Co-founder and CTO at Stigg.io What is APIs You Won't Hate? A no-nonsense (well, some-nonsense) podcast about API design & development, new features in the world of HTTP, service-orientated architecture, microservices, and probably bikes. Mike Bifulco: Hello and welcome back to APIs you won't hate. My name is Mike Bi Folco. Your APIs you won't hate co-hosts talking about APIs you won't hate with some of our friends from around the world who are building great APIs and tools for it. I'm joined today by my new friend Anton from Stig Anton, how are you this morning? Anton: I'm great, Mike. How are you? mike_bifulco: I'm doing really well. Thanks. It's super nice to get a chance to talk to you. I definitely want to dig into kind of what you're working on at Stig . First I'd like to know a little bit about you. Okay. So can you tell me a bit about yourself, maybe some of your background and the things you did before coming to Stig? Anton: Yeah, sure, of course. I'm Anton cio, co-founder of Stig. A little bit of background on from my end is that I'm in software engineering for. I think more than a decade now. Actually, like that's, that's the official number, but I think I started programming like from a younger age. I think my first programming book was visual Basic. I think I got it in the fourth grade. Mike Bifulco: That's, that's how I started too. Anton: Yeah. Good times. Good times. So since then I was hooked and I, you know, really enjoyed programming and spending a lot of time on. . Yeah, so I've been serving also in the idf, being in tele processing corpse. So that's how like my official career started, I think you can say that. And since then I've been rolling into a few FinTech companies, local companies here in Israel as a software engineer for a few years. I even thought, Like my specific domain expertise was work building trading platforms, like for stock brokers and, and everything around, you know, the tooling that requires to manage do trading platforms for also institutional investors and also for retail, retail investors. So I kinda categorize myself as an expert in trading platforms. And then like, there's was a. Change like from my end when I decided I wanna start having like being my own my own boss. And then I started open the software company and then hired a bunch of people and we made like kind of a lot of different projects and product, built a lot of products for like a variety of customers with was small startups, both big enterprises. And then I was like exposed to many different industries and. You know, many different kind of type of products. And afterwards I had the opportunity to join New Relic as a senior software engineer. And this is actually where I met my co-founder do and together we co-founded Stig. So, yeah, it was a a very interesting experience for me also working at like a big enterprise. Working on a new product that new Relic has acquired a startup company here in Israel. And then we help them together to build this new type of product, which called Lops. This is like a product line that involves everything that is related to machine learning, monitoring and observability around these areas. So it was very interesting to. . Yeah, so that's, that's, that's a brief history. Mike Bifulco: Yeah, sure. Really, really fascinating. So cool to hear that this isn't necessarily the first company you've started, although maybe the first product company you're building. And I, I guess all of that history of, of you know, working with startups and doing consulting and then working at New Relic kind of brings you to where you are today. So obviously that's building tig. Can you tell us a little bit about Stig? What's the audience? What's your value proposition? Who's, who's your user? What does that look like? Anton: Yeah, sure. So basically, I'm just gonna start with what Stig is and how we see it and what you're trying to do. So STIG is basically an, an infrastructure product. Okay. That's, that means that we developing APIs and tools that allow develop. To manage their and rollout new pricing packaging let's call constructions. So basically what we do is we sit as a product. We sit somewhere in the middle between like bunch of different areas. It includes also the product itself, also different types of billing systems, also different types of CRMs, and we like basically tie all those together. But if I need to say like, You know, what, what do you do, do best? Because that sounds like a little bit of vague. So basically, STIG is a, at it core, at at its core is an entitlement management system, which I think this is the foundation for any flexible or agile pricing, packaging tooling or . And to bring our software this is our centerpiece. And from there we evolved. Different areas such as usage based pricing and pricing, experimentation, and a testing. And on top of that is basically what allows us to do that is basically this entitlement piece. For, let's say from the the companies that we work with are basically the ones. or they want to try like the small segments, or they want to try out new price. Like they wanna roll the first pricing okay. For a software product. So they, they don't know where to start. So they usually reach out to us and try to figure out like what's the base based way to do that? What, what's the best pricing strategy for their specific product or industry. Then we try to help out give them some little advice or connect them to other pricing experts that might help a little bit. Information can help them do something more intelligent rather than try to guess that what's the best pricing for them. And the second, second type I think of of customers that work with us are the ones who already has some, like a, already has some pricing strategy in place, and then after like few years of running with that, they figure out that they wanna change that because. You know there's usually, there's a saying that if you don't iterate or change your pricing strategy over time, you basically living money on the floor. That's, and that's natural because usually the companies when they start, you know, where their initial pricing is, something that they decide on very on, very early on. And then, And they just wanna build a user base. They just wanna get traction. But after a year or two and they start to evolve and they start to grow and they want to increase revenue, I think the first thing they thinking of, okay, let's change our pricing. Cause that pricing is obsolete, it's legacy. We need to update it accordingly. We build so much for those two or three, four years and it's, it's insane if we price it the same, you know, the same in the same way we did when we just started. . So this is, I think that's that's the tipping point where they start looking for like, how we do that, how we plan that, how, which tools are out there that can help us to do this type of change. So I guess that's, that's also the point where we where we can help them and enable enable them to do these changes without, you know, rebuilding their own infrastructure all over. And also prevent them from doing that again in the future. Mike Bifulco: Sure. Yeah. It feels like there's a whole lot that goes into even just the, the couple of customer types you've described. I should definitely preface this entire discussion by giving the caveat and the I don't know, asterisk that in a past life I worked for Stripe. I no longer work for Stripe. I don't have ties to Stripe anymore. But probably worth saying, just for the sake of of clarity here I've spent a lot of my time working with and thinking about companies and, and customers and. And how pricing strategies work. So this is something that's definitely very interesting to me. Man, I have a lot of questions from here. So, l let's talk a little bit about companies trying to figure out their initial pricing strategy. I, I feel like, and a part of that is just for many companies who I'd imagined, well actually let's even start a step further back. So does Stig primarily work with subscription-based pricing, or do you do like one-off purchases and things like that as well? Anton: So I think that like at stake, because we are, we are the source of truth of how your pricing packaging looks like, like this is where we position ourself. We basically support mo different types of pricing strategies, like subscription is one of them. We also support usage based pricing, and we also have this concept of you know, enterprise pricing, which just. There are some enterprise customers that have some custom pricing tailored for them. And we also, some, this is also something that we support. But we, like from technical standpoint we don't see ourself as a billing system. Basically, we sit like between your product and the billing system. It means that the configuration. Of how your pricing should look like and how you wanna, how you wanna like charge your customers something that you define and stick, but the actual, the actual billing, like the actual invoicing is happens in the bearing system. Mike Bifulco: sure Anton: so we, we kind of, we, we are a little bit limited to what your billing system support, but. Our vision is to support and multiple different billing systems. So basically, once you use Stick, you're no longer vendor locked into a single billing system. Like if you use Stripe and you decided to switch over to God knows what, and we support this kind of integration, you can do that by having, by, by doing a, a few clicks, like in our, in our No Code user interface, and then you migrate all your customers to a different billing. Mike Bifulco: Right. Okay. Yeah, so I, I guess for further clarification, more of the distinction I'm, I'm looking for is you're, you're generally working with SaaS companies and enterprise flavored companies, and not so much like e-commerce stores that sell, I don't know, mechanical keyboards and things like that. Right? Anton: So basically our focus is on SaaS companies. Mike Bifulco: Yeah. Okay Anton: Like the, the pain that we felt is that SaaS companies like the existing tools are not sufficient enough for SaaS companies. I think that because every SaaS company is considered itself as a snowflake usually, and they have, like, I have my own vision of how I want to price my product, but still I want to check out the competitors do that and then align to that. But, you know, they always want to like invent something special of their own. . So basically I think that's because our focus is on the SaaS companies, we try, we try to bring the best like the best capabilities that suits their needs. I think we go like for the best practices that are in the SaaS industry and trying to like, consolidate all those different types of, of, you know, companies are trying to figure out what they need to do into like what are the best practices and how you should price your product based on certain. And factors, so, so we like our pure focus is basically on SaaS companies in that area. Mike Bifulco: Sure. Okay. Yeah, I think if you haven't built a, if you haven't plugged payments, pricing, subscriptions into a product before, I think it can be easy to think that, like it's simple, oh, you, you just charge $39 a month or whatever, a static price per month, and you know, that's how you work with your users. But then if you think about it a little longer, I think probably everyone has seen some pricing page on the internet that has a three, you know, a table with three prices on it, with a list of features below it. And even. Seems simple at first blush, but the process of building that out and even designing that interface in a way that people understand what's there and that it's clear and that you set up pricing correctly, there's a lot that goes into that. And then it gets even like more wildly complex when you talk about things where enterprises might have a graduated pricing that gets cheaper per seat after certain tiers, or they might have usage based. That's like for all of these AI products where you're charging per API call based on tokens, right? Like the, the can be more expensive and things like that. And it gets wildly complicated from there. And I think a lot of people don't realize that that is such an intense problem space and that, like you said, all of these companies are in their own way. You know, they consider themselves unicorns because they're trying to figure out the best way to, to provide value to people to make money. it strikes me that there's a lot to explain there from a, hey, like, STIG can help you do this perspective. And then there's sort of the implementation step of, it sounds like you plug into lots of payment services, so maybe something like Stripe and Adian and PayPal and all these places that can take payments. And from, from jumping into your webpage and looking at you know, STIGs homepage, there's some pretty intense diagrams of plugging in and out to SDKs and widgets and all kinds of things there. How, how do you explain, The placement of STIGs sort of integration service to, to companies looking to build, like where, what do you start with? How do you say, you know, what's your hello world for Stig look like? Anton: Cool. That's a, that's a great question, Mike. I think like the first thing that I just wanna address the the thing that you started with is like, there are a lot of variety of, you know, different. pricing strategies and you need to figure out how you build an, like a platform to support all those different use cases. But if you try to break it down like into what are the building blocks and that that you, that a com, a software company can use in order to build their pricing. All those types of different pricing model, pricing models. I think that the building blocks are quite the same, like across all those companies. As you said, there's like this token based pricing. There is this subscription based with a flat fee and there's this. Types of plans with different limits maybe, or there's a, like a one, one value metric or two value metrics. But at the baseline, if you take all that and try to find a common denominator between those two, you can actually build some, like an intelligent pro platform that is still flexible enough and build using those building and using those building blocks. You can model all those. Pricing models and supported end to end. So regarding your question of like how this Hello World application looks like. So basically Stig is, as I said before, is, is basically allows you to, you know roll out pricing changes faster if, if it was a very complex and. Complicated product with many integration points and, and you have to invest a lot of time in order to get value at stake. Wouldn't work, that wouldn't like be our core value that we provide to our customers. So basically from day zero focus was how you reduce the integration time, how you make things more simple. What, what is the immediate value that you can get the developer can get by using Stick. Like what we, what we're trying to, what pain do we, you know we sooth. So basically, I think that the whole low world example would be like the first thing that a developer usually starts work on when he gets this pricing test. Like usually there's a ticket in your trailer or Jira. That's, we need to roll out our pricing. Let's start with the pricing page. So basically , you know, let's not wire they that behind the scenes. Let's just put our pricing out there and see how the, how our customers will react to that. And, and this is basically what our like things that we gave give out out of the box are there's pricing plan widgets that you can an embedable widgets that can just simply drag and drop into your website, into your applic. and based on the pricing configuration and Stig, you get this magically pricing plans, everything dynamic according to your to the configuration that you set according to pricing strategy and Stig. And it's already functional. You already got the value. You didn't have to build it, you didn't have to break your head. How I model this, you know, different plans, how I style them, configure them, everything. There's no code solution in stick that allows you even to style and theme this type of. So that's the, the hello world that that I think that's the, that's the most simple thing that can get from stag, like the most straightforward one. And once you are ready and you wanna, you know, switch gears, then get, take it to the next level. And you wanna have pays inside your application. You wanna have a customer portal in the new application so customers can upgrade and downgrade their plans in self. So, This is where it gets interesting. We have widgets also for those pieces, but we also need to make it effective, we need to do this kind of backend integration with Stig, where you need to, first of all start reporting usage to Stig. Whenever a customer adds a seeds, remove the seed. If you want to have that enforced by Stig, that is something that is also required to do. And then later on you can. You know, start feature gating, start limiting those based on the usage and start billing on certain metrics if you choose to. And everything will be no code since that point. So basically, once you integrate the stick one, you won't have to do this integrations. So over again, whenever you choose to or decide to change your pricing model. Mike Bifulco: Yeah. Wow. Yeah, again, I feel like that's one of those things that sounds like you saying it sounds very simple. Having lived through building a few different pricing strategies for a few different products it can take quite a bit of work. And a, a good concrete example of that for. For APIs you won't hate. Phil, my, my co-host and co-founder here has authored a few books that we sell on the site and right now, if you went to buy books on the site, we sell them through Amazon and through Lean Pub and through a couple of different places. Shopify is, is one of our providers and we have few times thought about trying to make it so that it's easier for us to manage all of those things centrally and playing around. selling digital products for a set price or doing something like our own Patreon ish thing for won't hate. And the thought of trying that out and having it not work and having to rip it out or having to change it or something like that, is essentially as the, the, you know, Two to three person, developer team for the site is an intense amount of work. And essentially one of those things that just becomes a non-starter from the beginning. And if you think about, you know, maybe, I don't know let's say Anton, you and I were building a dating app, right? And we wanted to charge 10 bucks a month and we decided next month that we needed to split it out to three plans. That's 10 bucks a month, 20 bucks a month, and 50 bucks a month. It's so much work. You have to plum that in through every part of your application. , there's a lot of thought to, into gating off features and functionalities and all of that requires code changes, or at least as it sounds like all of that did require code changes on some level. so it's, it's an a very interesting i, I guess value proposition for people building Anton: I think also like the, like the, the example he gave, like, it starts very simple, but once you, you know, trying to. To run changes on that pricing or like, as you said, adding plans? It started like becoming a very not straightforward engineering problem because usually when people see like you know, you, you, you wanna start pricing, you think of, okay, I'll just go to Stripe, I'll drop in their their APIs, I'm gonna use their embedded checkout hosted page, and then everything is simple and I'm done. But it's not that accurately true, but, while Tribe does the, handles the payments, and handle the handles, the checkout experience, there's a, a lot of uncovered area there, which is around provisioning. Like provisioning is what happens after the checkout. How like, okay, so our customer has purchased this problem for $10 a month, and right now we need to provisioning access to the feature. He's paying for it. And this is where things started to get complicated. He started looking for, okay, how I need to listen to this WebBook from Stripe. I need to understand the subscription lifecycle, the subscription started renewed, canceled, all this type of events. You need to handle that on your backend. And how do you reflect that in, in the app itself? You know, like the subscription ended, we downgrade the user to the flip plan. We block evoke all access to the, to all the features in the application, this type of decision. Are very, are very fluid. They change over time. Like it's a, it's a business decision. Business decisions change and it's when developers and engineers start building this type of solutions, they, they have this like tunnel vision on what you need right now. Like the, the management told me this is our pricing. And they know, like in their standpoint of point of view, it's like this never gonna change and it's just gonna. I just wanna get over with it and I want to continue on my life and building more interesting features and, you know, wiring up all this building side into my application. And this is actually the first the first event when you start gathering and aggregating this. Technical depth regarding those, you know, pricing and packaging stuff inside your application. And then this depth hinders you from, or at least cost you a lot once you try to, you know, to ang it later on. So this is something that engineers don't see at the first, like when they first approach this problem. So this, that's why we at stake, we're trying to educate and to trying to, you know talk about this, like how our approach, the entitlement approach simplifies things in that, in those areas that once you integrate with start con the concept of entitlement, similar to feature flex, like there's you, you start working in it. It's very natural to you once you see the value of using that. Mike Bifulco: Yeah. Yeah. I think it's an interesting problem space too, because. All of our listeners are engineers. Most of our listeners are engineers. I guess I shouldn't make such a broad assumption, but you know, we, we have a lot of software developers that listen to the show and every single one of them, I'm sure can identify with the feeling of having to go and rebuild something that they finished and thought they were done with forever. but I think the other interesting side of this too is that product creators, the, the sort of product side of. Doesn't often have a full understanding of the amount of work engineers need to do to rework something fundamentally like that. And at the same time, engineers often don't understand that product. People need to be able to make sweeping, iterative changes to, to keep the product alive as well. So it's an interesting challenge for sure. I wanna shift gears a little bit understanding that the, what the product does and what it is and who you're talking to. Let's talk a little bit about how it's built, right? So your, your CTO. Dig. How is the platform built? What tools do you use? What li languages and libraries do you support? Anton: Yeah, sure. So so basically our current offering isn't like stickers an API product, like from the get-go. So basically we have craft, QL based api and we also have. Four is the case. I think for now we support no gs, Ruby, Python go and working more in SD case in the near future. But I think, like besides the APIs themselves, the API itself, I think that the more the main the main value is actually using in SD case because R SDKs are not just a wrapper around the api Rsdk. Are built specifically to handle the entitlement's problem, which, which means, which me directs me to this conversation. What is the entitlement's problem? And generally speaking of what entitlements are. So basically if you think of entitlements, it's something related to permissions in some way. Okay. So basically permissions are. Like definitions of what a user can do according to its role or its certain set of attributes and entitlements, on the other hand, are set of permissions that a customer is assigned to that can decide what, which features in the application. The customer subscribe to, like part of this license model, if you want to compare that and use those terms, which is a little bit outdated terms, but I think it's like a trend that's coming, coming back again. But So, yeah, so these are type of permissions. There need to be evaluated quickly and very often because every time the user interacts with your application, they probably, you need to do this type of check if the user subscribe according to its plan to use this feature. So the variation itself, it has to be like super fast, low latency, like and every. every bump in doing this decision in like in the process of making this decision can affect the, the overall like experience, user experience, and the latency of the, your API product or whatever you're building. So like our focus is basically allowing building the best as the case we can that evaluates with almost zero latency, those entitle checks, and you can safely use them within your product without. Even breaking or thinking of how you gonna, you know, what's the best way of implementing, then just do it, be a drop in and that's it. The problem is solved. So there's a lot of logic being going on in there, which, like, there's several factors like, you know caching and prefetching data or real time updates of this environment whenever they change this type of, you know, problems is something that is the case. And regarding our api, so basically there's a, that's as I mentioned, our main API is a Graph Q based api, which serves we, we call it a management api basically because it's usually the the API that our, like user interface is using our application. And we have another set of APIs, which we call them the Edge APIs. And those APIs are basically a build. On, we're using as a lot of AWS services as we can. So the Edge API leverages the cloud front, lambda edge type of distribution, which means our code executed at the closest region. To the user that invokes that api. And we also using dynamo DB's Global tables feature, which means that all data is replicated across multiple regions so that those lamb, that functions run on the edge can access their data closest to them, basically from the same region that they're rely on. And that's how we. The minimum latency we can globally regarding to all this mission critical data, which involves the usage, the entitlements and we also gained the uptime guarantee of AWS for the services. So we, so cus our customers can feel much more safer depending, you know, on the, on the giants like aw. To handle this type of failures if there, if there were any failures in it, Mike Bifulco: Sure, yeah. are using a lot of hardened infrastructure and a lot of, a lot of devs will be interested in hearing about edge APIs as well. That's something that seems to be a, a hot ticket lately too. Didn't think to ask this before. Do you do your APIs or your libraries support mobile use cases at the moment? Anton: So our focus is not mobile right now. Our focus is basically on like non-mobile SaaS companies, but that's something that we are also starting looking at. Mike Bifulco: Yeah. Got it. Yeah. Thi this is another one of those like scars I have from, from a past life. But mobile stuff is really complicated because a lot of it is governed pricing and all that is governed by apple or Google. and then even that changes depending on the country and what features you can enable and disable are really complicated too. But I think the The idea of entitlements is something that, you know, is, is fairly universal there. so support Node, ruby, Python and go at the moment. How many engineers do you have working on that? Anton: So currently we're a team of AI engineers. , so yeah, everyone, like basically working like from day zero, I think at stake, my most, my, like, my vision was to hire the best people and all, do the best engineers I know in order to, you know, build a solid foundation that we can grow up. So like from, even from the day one, I think all the engineers that we are, were always full stack versatile. They can go through, you know, build one day they build our web application. Then the next day they build this dk. Next day they work on the Edge API. And like this this like multi, you know, multifunctional team can Work much more efficient than having this type of, you know, usually like separation between that there's a front end engineer, a back engineer, and then they, it's hard to, you know coordinate the work together with along them. So basically having a team of full stacks for a startup at the early stage is a very big advantage. Mike Bifulco: Yeah. Yeah. Wow. Sounds like a lot of very talented and very busy folks working hard on your product. Well, what are the things that you're thinking about next? Like what are sort of the, the next features or problems that you're interested in addressing? Anton: So I think that our current focus right now is building as I said, the best, like out for world class entitlements, infrastructure and pricing, packaging infrastructure. And going forward, I think that our focus will be simply improving the dev tool set around this problem. I think that's the most critical part. Okay. If you need to ask me what is your edge? Like what, what, what, what's your focus? I can, you know, there's a lot, there are probably some companies that are near your you know, in those areas or outside this area. Never. , like, how do you stand out? I think that the way things stand out is basically focusing on the developer experience in a deaf persona and trying to reduce the work that those engineers that are tasked to do to work on the pricing for a company. Trying to retake the, the, as much work as we can from them to us and to enable them to move faster. If it's improving our tools, improving APIs supporting more different problems and different use cases that they face, I think that's, that, that that's the thing that we truly believe will make a difference. And in general, make our customers more happy. So yeah. Mike Bifulco: Yeah, no doubt. Are you hiring at the moment? Anton: Yeah, actually we do we are in a position of growing and we are looking for the first thing that we are looking, the most thing that is in demand right now is a dev position, like looking for a dev to join us. So basically every developer that loves. Working with different, with APIs, with this is the case and love to help other developers and getting feedback, feedback from other developers on those type of tools. This is something I think will be a, a great addition to our team. And there's a full description in our careers page in our website and state I. So so anyone who's interested can jump in and read more about it. Mike Bifulco: Cool. Yeah, that's great. I'll make sure I put a link in the show notes here too. So okay. My final question is maybe a bit of a curve ball, but so you've explained fairly well the problem of pricing and the approach you're taking to building out these APIs to help people work on their pricing and iterate on pricing plans and make changes quickly. how is Stig using Stig to to work on your own pricing and to, to tests and evaluate what you're doing? Anton: Yeah, so basically our, our own pricing is Bill using our own components, our own widget, like our, if you go to a pricing page, you'll see those pricing plans and it's there's a badge of power by stick that's basically one of our widget that we that we are using our own. And I think that like a stake the core concept of pricing is basically the ability to. . So we are modeling our own pricing using Stig, and we also leveraging our capabilities of experimenting with this pricing. So this is something, a topic that we didn't talk before, but it's also very interesting. So when we tried and, you know, started playing with our own pricing, I think that what we felt comfortable most is that because we are using stick, we don't have to. Commit to the pricing. know, we can always make the op made the decision to change it, and it'll not cost us any engineering effort in this, in this process. So so like if you ask a company like why you don't change your pricing often, they usually tell you that it's because it's hard. We don't change it because it's hard and over how like we. Talk with a bunch of different teams and get one on board, and then talk with the engineering and run those, all these changes. And then that's why they do it like once a year with the best. but if you, if you break that paradigm and start using the flexible infrastructure that allows you to do these changes more often. , then you won't have this problem. You can change pricing twice, three times a week, So yeah, so that's, that's basically how we also leverage in Stig inside Stig. Mike Bifulco: Sure. Yeah. It's, it's surprising the amount of difference that can make for an early stage business too, being able to hone in on exactly the right price strategy and, and price levels that your customers are willing to pay for. A lot of it can be based on feedback and things like that, but experimentation helps too. Anton: Yeah, I think experimentation will, will be like a, a core feature in price and packaging solutions. I think that experimentation allows you to make mistakes and mistake those mistakes won't be as costly as, as a mistake that you can often undo. Like every time, like even, you know When we build software, there's like, usually there's bugs. Like it's, it's an in available, so basically even if you deploy something and it doesn't work, what you do, you, you roll, you, you have the ability to roll back, or at least you, you add disability like in your c i CD, orchestrations or what whatsoever. Without it, you're, You're helpless. You need to, to, you know, to fix it and re-deploy it. And, and this process takes much more time than the, if you had the ability to just roll back your change. So stake in some way is, is, is that rollback? Like this is, we grant give you the ability to, to regret Mike Bifulco: Yeah, I can see that for sure. Anton it's been really great chatting with you today. One of the things I wanna make sure I ask is, where can people find you? Where's the best place to chase you down if people have thoughts or questions for you? Anton: Yeah, sure. So you can find me on LinkedIn. I think like also pretty trying to be active on GI as well. I'm not a big Twitter user unfortunately. I know that's missing something, but I don't have an Instagram, so yeah, I'm not a good Mike Bifulco: Got it. Anton: Another, a good example of being to into social platforms, but I think that LinkedIn and GI are, Mike Bifulco: Yeah, well, Anton: the Mike Bifulco: you're a focused man. There's no, no need to apologize there. That's that's good stuff I've also Twitter recently, so you know, people have heard me endlessly complaining about I dislike Twitter. Yeah. That's wonderful. I'll, I'll make sure I link to your LinkedIn and, and GitHub profiles in the show notes as well. Yeah. Thanks so much for joining today, Anton. I really appreciated chatting with you. This was Anton from Stig there'll be a link in the show notes to both the, the product page as well as jobs for Stig and contact information for Anton. Anton, thanks so much for hanging out. I really appreciate it. Anton: Yeah, me too. Thanks for having me. I had a good time. Mike Bifulco: course. Yeah, thanks. All audio, artwork, episode descriptions and notes are property of APIs You Won't Hate, for APIs You Won't Hate, and published with permission by Transistor, Inc. Broadcast by | 2026-01-13T08:47:52 |
https://ruul.io/blog-categories/grow?4400bacc_page=2 | grow Product Payment Requests Get paid anywhere. Sell Services Make your services buyable Sell Products Create once sell forever Subscriptions Get paid on repeat Ruul Space Your personel storefront. One link for everything you offer. Learn more Pricing Resources Partner Programs Referral Program Get 1% for life. Seriously. Affiliate Program Bring users, get paid Partners Let’s grow together. More Blog About us Support Brand Kit For Customers Log in Sign up For Businesses Login Sign up All articles Get Paid Sell Grow Work News Trends grow Best Contra Alternatives for Freelancers in 2025 Explore 12 top Contra alternatives for freelancers in 2025. Find the platform that fits your style, goals, and way of working. Contra vs Upwork vs Fiverr Compare Contra, Upwork, and Fiverr for freelancers—fees, client quality, ease of use & payout speed in 2025. What Is Contra and How Can Freelancers Use It? Discover how Contra works as a freelance platform. Learn its features, pricing, and real use cases. All in one place. Top Alternatives To Linktree For Freelancers Selling Services Take a look at the top 16 Linktree alternatives you can switch to better market your service. What Is Linktree And How Freelancers Use It To Get Paid? Discover how Linktree helps content creators monetize their audience and why freelancers are switching to Ruul Space for invoicing, payments, and tax compliance. How to Use Your TikTok Bio Link to Get Clients Learn how to optimize your TikTok bio link, attract new clients, and drive traffic to your business with this step-by-step guide. MORE THAN 120,000 Independents Over 120,000 independents trust Ruul to sell their services, digital products, and securely manage their payments. FROM 190 Countries Truly global coverage: trusted across 190 countries with seamless payouts available in 140 currencies. PROCESSED $200m+ of Transactions Over $200M successfully processed, backed by an 8-year legacy of secure, reliable transactions trusted by independents worldwide. FREQUENTLY ASKED QUESTIONS Everything you need to know. Get clear, straightforward answers to the most common questions about using Ruul. hey@ruul.io What is Ruul? Ruul is a merchant-of-record platform helping freelancers and creators globally sell services, digital products, subscriptions, and easily get paid. Who is Ruul for? Ruul is designed for freelancers, creators, and independent professionals who want a simple way to sell online and get paid globally. How does Ruul work? Open an account, complete a quick verification (KYC), and link your payout account. Then, start selling through your store or send payment requests to customers instantly. How does pricing work? Signing up is free. There are no subscription or hidden fees. Ruul charges a small commission only when you sell or get paid through the platform. What is a Merchant of Record? A merchant of record is the legal seller responsible for processing payments, handling taxes, and managing compliance for each transaction. What can I sell on Ruul? You can sell services, digital products, license keys, online courses, subscriptions, and digital memberships. How do I get paid on Ruul? Add your preferred bank account, digital wallet, or receive payouts in stablecoins as crypto. Funds arrive within 24 hours after a payout is triggered. OPEN AN ACCOUNT START MAKING MONEY TODAY ruul.space/ Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Trustpilot Product Payment Requests Sell Services Sell Products Subscriptions Ruul Space Pricing For Businesses Resources Blog About Contact Support Referral Program Affiliate Program Partner Program Tools Invoice Generator NDA Generator Service Agreement Generator Freelancer Hourly Rate Calculator All Rights Reserved © 2025 Terms Of Use Privacy Policy | 2026-01-13T08:47:52 |
https://www.reddit.com/r/technology/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netsec/?f=flair_name%3A%22Digital%20Forensics%22 | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://www.anthropic.com/news | Skip to main content Skip to footer Research Economic Futures Commitments Learn News Try Claude Newsroom Press inquires press@anthropic.com Non-media inquiries support@anthropic.com Media assets Download press kit Introducing Claude Opus 4.5 Announcements Nov 24, 2025 The best model in the world for coding, agents, and computer use, with meaningful improvements to everyday tasks like slides and spreadsheets. Claude Opus 4.5 delivers frontier performance and dramatically improved token efficiency. Announcements Sep 29, 2025 Introducing Claude Sonnet 4.5 Claude Sonnet 4.5 sets new benchmark records in coding, reasoning, and computer use while being Anthropic's most aligned model, accompanied by the release of the Claude Agent SDK for building capable agents Product Oct 15, 2025 Introducing Claude Haiku 4.5 Claude Haiku 4.5 matches state-of-the-art coding capabilities from months ago while delivering unprecedented speed and cost-efficiency for complex tasks. Announcements Sep 2, 2025 Anthropic raises $13B Series F at $183B post-money valuation Anthropic raised $13 billion in a Series F round at a $183 billion valuation to expand enterprise offerings, safety research, and international growth as revenue grew from $1 billion to over $5 billion in eight months. Policy Jul 23, 2025 Thoughts on America’s AI Action Plan Anthropic's response to the White House AI Action Plan supports infrastructure and safety measures while calling for stronger export controls and transparency requirements to maintain American AI leadership. News Search Date Category Title Jan 11, 2026 Announcements Advancing Claude in healthcare and the life sciences Dec 19, 2025 Policy Sharing our compliance framework for California's Transparency in Frontier AI Act Dec 18, 2025 Announcements Working with the US Department of Energy to unlock the next era of scientific discovery Dec 18, 2025 Announcements Protecting the well-being of our users Dec 9, 2025 Announcements Donating the Model Context Protocol and establishing the Agentic AI Foundation Dec 9, 2025 Announcements Accenture and Anthropic launch multi-year partnership to move enterprises from AI pilots to production Dec 3, 2025 Announcements Snowflake and Anthropic announce $200 million partnership to bring agentic AI to global enterprises Dec 3, 2025 Announcements Anthropic acquires Bun as Claude Code reaches $1B milestone Dec 2, 2025 Announcements Claude for Nonprofits Nov 24, 2025 Announcements Introducing Claude Opus 4.5 See more Products Claude Claude Code Claude in Chrome Claude in Excel Claude in Slack Skills Max plan Team plan Enterprise plan Download app Pricing Log in to Claude Models Opus Sonnet Haiku Solutions AI agents Code modernization Coding Customer support Education Financial services Government Healthcare Life sciences Nonprofits Claude Developer Platform Overview Developer docs Pricing Regional Compliance Amazon Bedrock Google Cloud’s Vertex AI Console login Learn Blog Claude partner network Connectors Courses Customer stories Engineering at Anthropic Events Powered by Claude Service partners Startups program Tutorials Use cases Company Anthropic Careers Economic Futures Research News Responsible Scaling Policy Security and compliance Transparency Help and security Availability Status Support center Terms and policies Privacy policy Consumer health data privacy policy Responsible disclosure policy Terms of service: Commercial Terms of service: Consumer Usage policy © 2025 Anthropic PBC Newsroom \ Anthropic | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netsec/comments/1q15fud/rnetsec_monthly_discussion_tool_thread/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://forem.com/new/architecture | New Post - Forem Forem Feed Follow new Subforems to improve your feed DEV Community Follow A space to discuss and keep up software development and manage your software career Future Follow News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Open Forem Follow A general discussion space for the Forem community. If it doesn't have a home elsewhere, it belongs here Gamers Forem Follow An inclusive community for gaming enthusiasts Music Forem Follow From composing and gigging to gear, hot music takes, and everything in between. Vibe Coding Forem Follow Discussing AI software development, and showing off what we're building. Popcorn Movies and TV Follow Movie and TV enthusiasm, criticism and everything in-between. DUMB DEV Community Follow Memes and software development shitposting Design Community Follow Web design, graphic design and everything in-between Security Forem Follow Your central hub for all things security. From ethical hacking and CTFs to GRC and career development, for beginners and pros alike Golf Forem Follow A community of golfers and golfing enthusiasts Crypto Forem Follow A collaborative community for all things Crypto—from Bitcoin to protocol development and DeFi to NFTs and market analysis. Parenting Follow A place for parents to the share the joys, challenges, and wisdom that come from raising kids. We're here for them and for each other. Forem Core Follow Discussing the core forem open source software project — features, bugs, performance, self-hosting. Maker Forem Follow A community for makers, hobbyists, and professionals to discuss Arduino, Raspberry Pi, 3D printing, and much more. HMPL.js Forem Follow For developers using HMPL.js to build fast, lightweight web apps. A space to share projects, ask questions, and discuss server-driven templating Dropdown menu Dropdown menu Skip to content Navigation menu Search Powered by Algolia Search Log in Create account Forem Close Join the Forem Forem is a community of 3,676,891 amazing members Continue with Apple Continue with Facebook Continue with GitHub Continue with Google Continue with Twitter (X) OR Email Password Remember me Forgot password? By signing in, you are agreeing to our privacy policy , terms of use and code of conduct . New to Forem? Create account . 💎 DEV Diamond Sponsors Thank you to our Diamond Sponsors for supporting the DEV Community Google AI is the official AI Model and Platform Partner of DEV Neon is the official database partner of DEV Algolia is the official search partner of DEV DEV Community — Your community HQ Home About Contact Code of Conduct Privacy Policy Terms of Use Built on Forem — the open source software that powers DEV and other inclusive communities. Made with love and Ruby on Rails . DEV Community © 2016 - 2026. We're a blogging-forward open source social network where we learn from one another Log in Create account | 2026-01-13T08:47:52 |
https://www.stigg.io/ | Stigg | SaaS Monetization & Entitlements API --> Miro launched AI pricing in <6 weeks ⚡ Here’s how → Docs Developers What are entitlements? Modern billing stack Status page Trust center Changelog Under the hood Example project Pricing Customers Blog About Careers Hiring! Login Login Try Stigg Get a demo You don’t need another billing system to ship faster new pricing models AI monetization credits & top-ups add-ons & bundles usage-based pricing localized pricing Flexible entitlements and composable infrastructure: MonetizationOS by Stigg. There’s a better way. The first scalable monetization platform, for the modern billing stack. Eliminate risk. Retain focus. Power more pricing and packaging options with less code. Try for free Get a demo Trusted by Deploy once, sync changes everywhere with a unified monetization platform What is a MonetizationOS ? Many companies bury pricing logic inside billing systems or product code, making every change slow, brittle, and risky. A MonetizationOS like Stigg centralizes pricing, packaging, entitlements, and usage into one programmable system of record. This lets you run experiments, launch new SKUs, and monetize AI features without touching fragile billing code. Catalog Modeling Consolidate pricing and packaging models to create a single source of truth for product catalog definitions. Streamline workflows with flexible building blocks. Learn more Entitlements & Provisioning Centralize entitlements and provisioning, offering flexible access management, streamlined operations, and customer experiences for growth at scale. Learn more Usage Metering Meter usage in real-time, compute metrics, and ingest events at large scale. Enable usage-based pricing and consumption limits, while ensuring billing accuracy and cost efficiency. Learn more Subscription Management Robust subscription management capabilities to streamline your billing processes and enhance customer experiences for both self-service and direct channels. Learn more Versioning, Linage & Migrations Maintain consistency with plan versions, automate price migrations gracefully. Adapt swiftly to market changes with minimal disruption for customers. Learn more Embedded UIs Easily embed customizable widgets that enhance user interfaces and enrich user experience, ensuring a fluid and cohesive user journey. Learn more Why Stigg ? 7x faster to deploy Pricing and Packaging changes. 98% faster time to market. +100s days saved on building internally. “All things are possible through the power of Stigg”. Modern monetization infrastructure
starts with Entitlements What are Entitlements? Entitlements define the value your customers receive; the features, limits, usage, and credits in every plan. They are the foundation of modern monetization. When this logic is hardcoded into product or billing systems, every change is slow, fragile, and risky. With Stigg, entitlements become a flexible, programmable system of record. You can define, update, and experiment with packaging instantly, while Stigg keeps product, billing, CRM, CPQ, and data warehouses in sync automatically. Read more One API. Every monetization model. Move from - “It will take 2 quarters”
to - “We’re ready when you are” Expand with Multi Products Layer usage-based pricing Role-based pricing Overages Geo-fenced pricing & localization Seats & subscriptions Hybrid pricing A-la-carte Budget caps & cut-offs Self-service MSP portal Introduce an AI Add-on Credit-based pricing Feature-level trials Plan overrides Feature and price dependencies Dynamic offers & experiments Bundles Soft & hard usage limits Custom enterprise plans True-ups & top-ups Multi-resource pricing Stigg replaces augments your existing billing stack Untangle tight coupling, undo billing vendor lock. Take back control over your usage and subscription data. Enable more without a risky and costly billing vendor migration. Re-platform and scale-up your legacy homegrown internal infrastructure. Natively integrate with your existing billing stack with a bi-directional sync. Never again be the victim of your billing vendor roadmap. Get started with Stigg the way you want. SDKs frameworks API controls for every feature, incl. API playground. Easy-to-integrate SDKs in multiple languages. See our SDKs Sidecar Sidecar service provices low latency entitlement checks, caching, and real-time updates. See our Sidecar integration Use your own DB Down-stream data into your local database by reading from a dedicated queue or webhooks. See our advanced deployment methods The most powerful entitlement infrastructure
you will never build Multiple development environments Audit log Reliable notifications using webhooks or a dedicated queue Developer observability & environment health monitors Embedded UIs Manage pricing changes as code with Stigg’s CLI Migrate millions of subscriptions changes in seconds, not weeks Plan versioning & grandfathering Merge and promote changes between environments Built for speed & scale with an always-on architechture Highly Available Core API services are deployed across multiple regions to ensure high availability with automated failover. Asynchronous data replication across regions achieves redundancy and low latency, with an uptime SLA of 99.99%. Low-latency caching layer Stigg offers a local cache to minimize network dependency and support offline operations. An external persistent store option enhances data durability across restarts and reduces cache misses in large or transient environments. Delivered over the Edge Network Edge API leverages a CDN with over 300 global PoPs for scalability and high availability. It executes code at the nearest regional edge to minimize latency and efficiently manages large volumes of concurrent requests with its auto-scaling FaaS architecture. Metering at scale Metering API handles high-volume, real-time events, processing thousands per second from a single source. Built-in idempotency prevents duplicates, and aggregated data are distributed across regions to minimize network latency. Fault tolerant Stigg is built on a reliable integration architecture that utilizes durable queues, webhook notifications, and retries for errors, along with alerts for failures. API calls are audited, logged, and monitored for effective data reconciliation. Highly Available Core API services are deployed across multiple regions to ensure high availability with automated failover. Asynchronous data replication across regions achieves redundancy and low latency, with an uptime SLA of 99.99%. Low-latency caching layer Stigg offers a local cache to minimize network dependency and support offline operations. An external persistent store option enhances data durability across restarts and reduces cache misses in large or transient environments. Delivered over the Edge Network Edge API leverages a CDN with over 300 global PoPs for scalability and high availability. It executes code at the nearest regional edge to minimize latency and efficiently manages large volumes of concurrent requests with its auto-scaling FaaS architecture. Metering at scale Metering API handles high-volume, real-time events, processing thousands per second from a single source. Built-in idempotency prevents duplicates, and aggregated data are distributed across regions to minimize network latency. Fault tolerant Stigg is built on a reliable integration architecture that utilizes durable queues, webhook notifications, and retries for errors, along with alerts for failures. API calls are audited, logged, and monitored for effective data reconciliation. Fully extensible. Connect Stigg with
the rest of your stack Browse integrations Web Productivity LLMs Infrastructure Developer Over the last 1 month, all kinds of crazy ideas have been thrown at me and I’m like “yes we can do that” .
1yr ago, a request for addons came or just redoing our packaging and I gave a conservative timeline of 4 months. Utkarsh Sengar VP of Engineering Collaborating with the team at Stigg is great, they have deep knowledge of the SaaS monetization domain , and have been a great partner. With Stigg's product integrated, we plan to evolve our offering at a higher pace. Reducing the time to introduce new plans , price points or products from months to days. Matthisk Heimensen Engineering Manager We evaluated other options and selected Stigg as our Monetization platform, as it was the only solution that could support both the needs of AI21 Studio (B2B) and Wordtune (B2C) combined, while keep adding more options for us to price and package as we scale. Yaron Sternbach Director of Engineering Flexibility in pricing & plans is critical for the success of SaaS companies. Even harder when catering for both Enterprise and PLG sales . You don't want these operational considerations to become an obstacle for success. Tal Lev-Ami Co-Founder & CTO Not consulting, but if you're looking for a product to help with your PLG pricing, you should check out Stigg . Bill staples CEO Monetize at the speed of product Try for free Get a demo Developers Documentation Changelog Status page Trust center Under the hood Example project Resources Blog Customer Stories Modern Billing Stack Unbundled Monetization Company About Pricing Careers Partners Privacy policy Terms of use support@stigg.io SOC 1 Type 2 compliant SOC 2 Type 2 compliant ISO27001 certified All systems normal Stigg's Linkedin profile Stigg's X profile Stigg's Youtube Channel | 2026-01-13T08:47:52 |
https://developers.reddit.com/apps/sub-stats-bot | Subreddit Statistics | Reddit for Developers Readme A Devvit app to store subreddit statistics for moderators and users. This app was heavily inspired by AssistantBOT, but restores metrics that AssistantBOT became unable to report on due to Pushshift restrictions. Statistics are updated on wiki pages each day at 01:00 UTC. All dates are in UTC. Note : If your sub has opted in to the new wiki experience, you will not see the wiki pages update. However, you can navigate to the equivalent on Old Reddit to see statistics, even after you have opted in. Unfortunately, there is no API support for the new wiki experience and so it is not possible to update new wiki pages yet. Once support is available, it will be added. Monthly Subreddit Statistics This app captures the number of posts and comments made each day, the top posters and commenters, and the top posts made in the subreddit. This information is displayed on wiki pages on your subreddit, broken down by month. Posts and comments that were filtered to the mod queue and not approved, removed by a mod, Reddit, Automod, or deleted by the user are not included in the statistics. The per-month statistics are stored in the wiki page sub-stats-bot/{year}. Sample output . Subscriber Statistics Subscriber statistics are stored in a separate wiki page at sub-stats-bot, which also provides an index of monthly statistics. Subscriber milestones show when the subreddit passes certain subscriber increase milestones after the app is installed. Milestones track when the most significant digit rolls over (e.g. 999->1000, 9,999->10,000) and once a subreddit surpasses 1000 subscribers, it also tracks each half way point (e.g. 1,499->1,500, 14,999->15,000). It also predicts when the next milestone will be reached based on recent subscriber growth. A table of subscriber numbers is also maintained, initially with daily increases. As the table grows larger, it will show weekly or monthly changes instead. Sample output . Source Code and Licence Subreddit Statistics is open source. The code is available on GitHub here . Version History v1.2.11 Update Dev Platform version and README. No public facing changes in this release. v1.2.10 Fixed an issue with the display of "next milestone date" being inaccurate soon after install Change how wiki pages are generated to improve reliability v1.2.2 Fixed an issue that prevents install from working on some subreddits v1.2.0 Fixed milestone display once more than one milestone has passed Fixed estimated milestone cross date where the milestone is due to be crossed within 24 hours v1.1.0 Post votes are now shown correctly on wiki pages for posts made right at the end of a month Number of posts/comments and distinct users are now shown on both year summary and per-month summaries Fix bug that prevents index wiki page from updating if subscriber counts are unchanged Fix bug that will prevent 2024 year wiki page from emptying in early January v1.0.8 /u/ tags are correctly added on "top posts of year" section Increase number of days that sub stats are reported for before going weekly/monthly Prevent "0 posts" from appearing in the "top days" lists when a user deletes the only post of the day v1.0.5 Calculate post/comment averages correctly on install month Add option to prepend usernames with /u/ on wiki page Add navigation back to summary page on each year's wiki page Fix formatting on subscriber counts table after day 20 About this app fsv Creator App identifier sub-stats-bot Version 1.2.11 Send feedback Company Reddit, Inc. Reddit for Business Careers Press Contact Blog Community Reddit.com Reddit for Community Content Policy Help Center Moderator Code of Conduct Privacy & Safety Privacy Policy User agreement Transparency Report r/redditsecurity Other Terms and Policies Copyright 2026 Reddit Inc. All rights reserved. Company Reddit, Inc. Reddit for Business Careers Press Contact Blog Community Reddit.com Reddit for Community Content Policy Help Center Moderator Code of Conduct Privacy & Safety Privacy Policy User agreement Transparency Report r/redditsecurity Other Terms and Policies Copyright 2026 Reddit Inc. All rights reserved. | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netsec/hot/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netsec/comments/1qb3w0l/a_common_denominator_in_ai_agent_framework_cves/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://future.forem.com/t/privacy | Privacy - Future Forem Feed Follow new Subforems to improve your feed DEV Community Follow A space to discuss and keep up software development and manage your software career Future Follow News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Open Forem Follow A general discussion space for the Forem community. If it doesn't have a home elsewhere, it belongs here Gamers Forem Follow An inclusive community for gaming enthusiasts Music Forem Follow From composing and gigging to gear, hot music takes, and everything in between. Vibe Coding Forem Follow Discussing AI software development, and showing off what we're building. Popcorn Movies and TV Follow Movie and TV enthusiasm, criticism and everything in-between. DUMB DEV Community Follow Memes and software development shitposting Design Community Follow Web design, graphic design and everything in-between Security Forem Follow Your central hub for all things security. From ethical hacking and CTFs to GRC and career development, for beginners and pros alike Golf Forem Follow A community of golfers and golfing enthusiasts Crypto Forem Follow A collaborative community for all things Crypto—from Bitcoin to protocol development and DeFi to NFTs and market analysis. Parenting Follow A place for parents to the share the joys, challenges, and wisdom that come from raising kids. We're here for them and for each other. Forem Core Follow Discussing the core forem open source software project — features, bugs, performance, self-hosting. Maker Forem Follow A community for makers, hobbyists, and professionals to discuss Arduino, Raspberry Pi, 3D printing, and much more. HMPL.js Forem Follow For developers using HMPL.js to build fast, lightweight web apps. A space to share projects, ask questions, and discuss server-driven templating Dropdown menu Dropdown menu Skip to content Navigation menu Search Powered by Algolia Search Log in Create account Future Close # privacy Follow Hide Create Post Older #privacy posts 1 2 3 Posts Left menu 👋 Sign in for the ability to sort posts by relevant , latest , or top . Right menu I Almost Fell for a “Last Wish” Scam : Here’s What You Need to Know Om Shree Om Shree Om Shree Follow Jan 12 I Almost Fell for a “Last Wish” Scam : Here’s What You Need to Know # discuss # scam # security # privacy 23 reactions Comments Add Comment 4 min read Navigating the AI Legal Minefield: Your Business Guide tanvir khan tanvir khan tanvir khan Follow Dec 31 '25 Navigating the AI Legal Minefield: Your Business Guide # ai # privacy # security Comments Add Comment 8 min read Ethics and Governance in AI adoption for Indian Businesses PHD Chamber PHD Chamber PHD Chamber Follow Dec 30 '25 Ethics and Governance in AI adoption for Indian Businesses # ai # autonomy # privacy Comments Add Comment 7 min read the modern full stack choice THIYAGARAJAN varadharajan THIYAGARAJAN varadharajan THIYAGARAJAN varadharajan Follow Dec 28 '25 the modern full stack choice # ai # privacy # productivity Comments Add Comment 1 min read AI-Powered Android Browsers That Boost Productivity with ChatGPT Integration Proditive Proditive Proditive Follow Nov 13 '25 AI-Powered Android Browsers That Boost Productivity with ChatGPT Integration # android # ai # productivity # browser Comments Add Comment 8 min read Google’s Private AI Compute: A New Chapter in Privacy-First AI? Michael Keller Michael Keller Michael Keller Follow Nov 13 '25 Google’s Private AI Compute: A New Chapter in Privacy-First AI? # ai # privacy # security Comments Add Comment 1 min read Linus Tech Tips (LTT): YouTube Is Making People B̶l̶o̶o̶d̶y Mad - WAN Show October 31, 2025 Future YouTube Future YouTube Future YouTube Follow Nov 4 '25 Linus Tech Tips (LTT): YouTube Is Making People B̶l̶o̶o̶d̶y Mad - WAN Show October 31, 2025 # productivity # privacy Comments Add Comment 1 min read From Zero to Gemini Multi-Agint: How I built a Cognitive Firewall in 5 Days Sonia Al-Ra'ini Sonia Al-Ra'ini Sonia Al-Ra'ini Follow Dec 5 '25 From Zero to Gemini Multi-Agint: How I built a Cognitive Firewall in 5 Days # ai # security # privacy # brainhacking 15 reactions Comments 2 comments 4 min read ⚙️ Digital Drive, Data Theft: The Hidden Danger Inside Your Car Syber Secure Syber Secure Syber Secure Follow Nov 5 '25 ⚙️ Digital Drive, Data Theft: The Hidden Danger Inside Your Car # cybersecurity # privacy # technology # dataprivacy 1 reaction Comments Add Comment 3 min read Facebook launches AI feature to suggest your best photos and videos for sharing from camera roll Saiki Sarkar Saiki Sarkar Saiki Sarkar Follow Oct 18 '25 Facebook launches AI feature to suggest your best photos and videos for sharing from camera roll # ai # privacy # productivity Comments Add Comment 2 min read Daily Artificial Intelligence Digest - Oct 19, 2025 Antony Brahin Antony Brahin Antony Brahin Follow Oct 19 '25 Daily Artificial Intelligence Digest - Oct 19, 2025 # ai # aigovernance # privacy # surveillance Comments Add Comment 1 min read Free Resilient Web Manifesto frw community frw community frw community Follow Nov 15 '25 Free Resilient Web Manifesto # sovereignty # privacy # freedom # web Comments Add Comment 7 min read Digital Ethics: The Dark Reality of Deepfakes Sumit Shingole (BTech CSE 2025-29) Sumit Shingole (BTech CSE 2025-29) Sumit Shingole (BTech CSE 2025-29) Follow Oct 4 '25 Digital Ethics: The Dark Reality of Deepfakes # ai # privacy # security Comments Add Comment 2 min read Google faces backlash as Taylor Swift fans allege AI use in promotional scavenger hunt videos Saiki Sarkar Saiki Sarkar Saiki Sarkar Follow Oct 7 '25 Google faces backlash as Taylor Swift fans allege AI use in promotional scavenger hunt videos # ai # privacy Comments Add Comment 2 min read Udio allows users to download AI songs for 48 hours after backlash over UMGlegal settlement Saiki Sarkar Saiki Sarkar Saiki Sarkar Follow Nov 1 '25 Udio allows users to download AI songs for 48 hours after backlash over UMGlegal settlement # ai # privacy Comments 1 comment 2 min read Neuromarketing in Practice: Strategies to Tap into Subconscious Consumer Decisions Aditya Aditya Aditya Follow Sep 17 '25 Neuromarketing in Practice: Strategies to Tap into Subconscious Consumer Decisions # biotech # privacy # science Comments Add Comment 7 min read Truth Social's new AI search engine basically just pushes Fox News AI News AI News AI News Follow Aug 12 '25 Truth Social's new AI search engine basically just pushes Fox News # ai # privacy # security # science Comments Add Comment 1 min read Bipartisan Bill to Create a National Quantum Computing Cybersecurity Strategy Quantum News Quantum News Quantum News Follow Aug 12 '25 Bipartisan Bill to Create a National Quantum Computing Cybersecurity Strategy # quantum # security # science # privacy 3 reactions Comments Add Comment 1 min read ChatGPT will ‘better detect' mental distress after reports of it feeding people's delusions AI News AI News AI News Follow Aug 8 '25 ChatGPT will ‘better detect' mental distress after reports of it feeding people's delusions # ai # healthtech # security # privacy Comments Add Comment 1 min read ChatGPT will ‘better detect' mental distress after reports of it feeding people's delusions AI News AI News AI News Follow Aug 7 '25 ChatGPT will ‘better detect' mental distress after reports of it feeding people's delusions # ai # healthtech # science # privacy Comments Add Comment 1 min read Grok generates fake Taylor Swift nudes without being asked AI News AI News AI News Follow Aug 7 '25 Grok generates fake Taylor Swift nudes without being asked # ai # privacy # security # science Comments Add Comment 1 min read Nvidia rejects US demand for backdoors in AI chips AI News AI News AI News Follow Aug 7 '25 Nvidia rejects US demand for backdoors in AI chips # ai # security # privacy # manufacturing Comments Add Comment 1 min read Doge reportedly using AI tool to create ‘delete list' of federal regulations AI News AI News AI News Follow Jul 29 '25 Doge reportedly using AI tool to create ‘delete list' of federal regulations # ai # productivity # privacy # security Comments Add Comment 1 min read Trump's Anti-Bias AI Order Is Just More Bias AI News AI News AI News Follow Jul 29 '25 Trump's Anti-Bias AI Order Is Just More Bias # ai # privacy # security # science Comments Add Comment 1 min read Amazon buys Bee AI wearable that listens to everything you say AI News AI News AI News Follow Jul 28 '25 Amazon buys Bee AI wearable that listens to everything you say # ai # wearables # privacy # iot Comments Add Comment 1 min read loading... trending guides/resources Google’s Private AI Compute: A New Chapter in Privacy-First AI? the modern full stack choice I Almost Fell for a “Last Wish” Scam : Here’s What You Need to Know From Zero to Gemini Multi-Agint: How I built a Cognitive Firewall in 5 Days Udio allows users to download AI songs for 48 hours after backlash over UMGlegal settlement Navigating the AI Legal Minefield: Your Business Guide Free Resilient Web Manifesto ⚙️ Digital Drive, Data Theft: The Hidden Danger Inside Your Car Linus Tech Tips (LTT): YouTube Is Making People B̶l̶o̶o̶d̶y Mad - WAN Show October 31, 2025 💎 DEV Diamond Sponsors Thank you to our Diamond Sponsors for supporting the DEV Community Google AI is the official AI Model and Platform Partner of DEV Neon is the official database partner of DEV Algolia is the official search partner of DEV Future — News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Home About Contact Code of Conduct Privacy Policy Terms of Use Built on Forem — the open source software that powers DEV and other inclusive communities. Made with love and Ruby on Rails . Future © 2025 - 2026. Stay on the cutting edge, and shape tomorrow Log in Create account | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netsec/comments/1qaw4t6/pwning_claude_code_in_8_different_ways/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netflix/comments/1pcfokw/stranger_things_x_netflix_puzzled_puzzles_just/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://claude.com/pricing/max | Max plan | Claude -------> Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Pricing Pricing / Max Explore here Ask questions about this page Copy as markdown The Max plan The Max plan combines Claude desktop and mobile apps and Claude Code in one subscription, with up to 20x more usage per session than Pro. That’s a lot of deep work potential. Get started Get started Get started People are using Claude to
develop Amazon ad testing strategies Download the desktop app: macOS macOS macOS Windows Windows Windows Windows (arm64) Windows (arm64) Windows (arm64) Try Claude on mobile: Apple Apple Apple Google Play Google Play Google Play A thought partner for your
most ambitious work Enable every team to spark new ideas,
achieve more, and collaborate better. Tackle complex projects Handle sophisticated, multi-dimensional challenges—the kind that require a true thinking partner. Do real work well Launch features, complete analyses, publish content, and more with Claude. Claude works alongside you Claude shows its thinking, seeks clarification, and collaborates thoughtfully. One plan for all your work Marketers Developers Sales Analysts Founders Creators Active Note Interact with the data—hover and toggle views to uncover patterns View prompt View prompt View prompt Prompt Create a multi-line trend chart showing the performance of three key business metrics over the past 12 months: marketing campaign ROI (pink line), sales conversion rate (blue line), and market share growth (green line). Display clear trend intersections and mark significant performance changes with data points. Include a legend and show month-over-month progression. Attachments Quarterly Performance 1,283 lines csv Market Analysis 921 kb json Marketers Create compelling content and build campaign dashboards in Claude apps. View prompt View prompt View prompt Prompt > claude fix the authentication error in our login flow I'll investigate the auth error. Let me look at the relevant files. Examining auth-related files... * src/services/authService.js * src/components/Login.jsx * src/store/authSlice.js Running the login flow... Error detected: "401 Unauthorized: Token expired" Root cause: * Token refresh mechanism not handling expired tokens correctly * Refresh token missing from request header * Improper error handling for 401 responses Updating authService.js with proper refresh logic... Updating request interceptor for 401 handling... Testing the fix... * Login successful ✓ * Token refresh working ✓ * Proper redirection on expired tokens ✓ Authentication error fixed! The login flow now properly handles token expiration. Developers Plan project implementation with Claude apps, then execute with Claude Code in the terminal. View prompt View prompt View prompt Prompt Conduct a comprehensive win/loss analysis of the Q4 2024 enterprise sales pipeline using the attached CRM data, sales call transcripts, and win/loss interview summaries. I need a strategic business report. Attachments CRM Data 7,126 lines csv Sales Calls Transcripts 479 kb txt Q4 2025 Enterprise Deal Win/Loss Analysis Executive Summary Overall Performance: Win Rate: 54.5% (6 wins out of 11 completed deals) Total Pipeline Value: $8.27M across 20 deals Won Deal Value: $1.97M (average $328K per win) Lost Deal Value: $1.44M (average $288K per loss) Active Pipeline: $4.86M across 9 in-progress deals Key Findings What’s Working: Primary Win Drivers Industry-Specific Expertise Compliance Leadership: Won deals consistently highlighted superior compliance capabilities (TechCorp security, AutoManuf automotive certs, EnergyPlus sustainability) Technical Fit: All wins featured strong technical alignment with existing infrastructure Industry References: Successful deals leveraged relevant customer case studies effectively Speed to Value Fast Implementation: Won deals averaged 75 days vs 121 days for lost deals Quick ROI: Winners showed immediate business impact (RetailMax Black Friday readiness, CloudFirst rapid scaling) Sales Team Performance Sarah Johnson: 3 wins, 3 in-progress (50% of total wins) David Rodriguez: 3 wins, 2 in-progress (strong enterprise focus) Top performers brought in technical experts and leveraged references effectively Critical Loss Factors Pricing Competitiveness 60% of losses cited cost as primary factor Total Cost of Ownership: Competitors offered 20-40% lower TCO Budget Constraints: Especially impactful in education and government sectors Implementation Timeline Seasonal Deadlines: FoodChain and EduTech lost due to timing misalignment Resource Constraints: Lost deals averaged 40% longer implementation times Industry-Specific Gaps Feature Deficits: Food safety (FoodChain), government compliance (GovServices), consulting templates (ConsultPro) Reference Shortage: Lacked sufficient industry-specific case studies Detailed Analysis Industry Performance High-Performing Industries achieved perfect win rates across the board. Technology deals (100% win rate across 2 deals) succeeded through superior technical fit and security-focused positioning. Retail and Sports sectors also delivered 100% success rates, with scalability and real-time performance capabilities driving wins. Energy and Automotive industries maintained perfect records through industry-specific compliance expertise and sustainability-focused solutions. Struggling Industries present significant challenges requiring strategic intervention. Manufacturing deals failed due to cost sensitivity and ERP integration complexities. Education sector losses stemmed from budget constraints and seasonal timing misalignment. Consulting industry struggles centered on ROI timeline concerns and extensive customization requirements. Food & Beverage deals were lost primarily due to industry-specific compliance gaps. Government sector challenges included complex procurement processes and vendor pre-approval requirements. Deal Size Impact Enterprise deals over $300K delivered a 50% win rate with 5 wins out of 10 completed opportunities, while mid-market deals under $300K achieved a perfect 100% win rate though represented only 1 completed deal. The average won deal value reached $328K compared to $288K for lost deals, indicating that higher-value opportunities are actually slightly more likely to close successfully despite their complexity. Competitor Analysis Uncontested deals represent the strongest opportunity with 6 total encounters resulting in 5 wins for an 83% success rate, demonstrating clear market fit when not facing direct competition. Competitor A appeared in 4 deals with only 1 win achieved against them (25% win rate). Their primary strengths include lower cost positioning and faster implementation timelines that appeal to budget-conscious and time-sensitive prospects. Competitor B proved most challenging with 5 encounters resulting in zero wins (0% win rate). They excel through industry-specific feature sets and superior integration capabilities with existing customer systems. Competitor C also maintained a perfect defensive record with 4 encounters and zero losses to our solution (0% win rate). Their key advantages center on significant cost advantages and strong compliance capabilities that resonate particularly well in regulated industries. Pipeline Risk Assessment High-Risk Deals (Likely to be Lost) FinanceFirst Bank (D003) - $680K Risk Level: 🔴 HIGH Issues: Security audit delays, complex approval process, integration concerns Timeline: 125+ days in cycle LogiCorp International (D007) - $750K Risk Level: 🔴 HIGH Issues: Resource constraints, quarterly decision cycles, competitive evaluation Timeline: 134+ days in cycle BioPharm Research (D011) - $610K Risk Level: 🔴 HIGH Issues: FDA validation needs, merger uncertainty, 90-day regulatory review Timeline: 143+ days in cycle Medium-Risk Deals TelecomMax Inc (D017) - $690K Risk Level: 🟡 MEDIUM Issues: Acquisition talks pausing decisions, architecture review delays Action: Provide technical POC to advance architecture review InsureTech Ltd (D013) - $480K Risk Level: 🟡 MEDIUM Issues: Q2 regulatory deadlines, build vs buy decision pending Action: Accelerate sandbox testing, provide regulatory compliance package Promising Deals MediaWorks Global (D009) - $380K Risk Level: 🟢 LOW Issues: Change management concerns, timing with Q1 workflow changes Action: Provide training timeline, phase implementation approach Strategic Recommendations Immediate Actions (Next 30 Days) Pricing Strategy Review Develop competitive pricing tiers for education, government, and manufacturing Create TCO calculators showing long-term value proposition Consider flexible payment terms for budget-constrained sectors Implementation Acceleration Create phased implementation options to reduce resource burden Develop rapid deployment packages for time-sensitive industries Build seasonal implementation calendars for education and retail Industry Specialization Develop food safety compliance package for F&B sector Create government-specific security documentation and pre-approval materials Build manufacturing-specific ERP integration templates Medium-Term Initiatives (Next Quarter) Reference Program Enhancement Recruit case study participants from each target industry Develop industry-specific ROI calculators and business cases Create peer reference networks for prospects Sales Team Optimization Replicate Sarah Johnson and David Rodriguez's best practices Provide industry-specific training for underperforming reps Develop technical expert engagement playbooks Competitive Intelligence Deep-dive analysis of Competitor B and C's industry-specific advantages Develop competitive battle cards for each major competitor Create differentiation messaging for key competitive scenarios Long-Term Strategic Shifts Product Development Priorities Food safety and traceability features for F&B market Government compliance and security certifications Manufacturing-specific ERP integration capabilities Market Focus Refinement Double down on high-win-rate industries (Technology, Energy, Automotive) Develop specialized go-to-market strategies for challenging sectors Consider partnership strategies for government market entry Success Metrics to Track Win rate improvement: Target 65% win rate by Q1 2025 Sales cycle reduction: Target 15% decrease in average cycle time Competitive win rate: Improve win rate against top competitors to 40% Pipeline conversion: Focus on advancing high-value, high-probability deals — Analysis based on Q4 2024 CRM data, sales call transcripts, and win/loss interviews. Last updated: December 2024 Sales Write personalized outreach and analyze customer feedback in Claude apps. Note Interact with the data—hover and toggle views to uncover patterns View prompt View prompt View prompt Prompt Create a scatter plot matrix showing business performance vs opportunity analysis. Plot data points by Current Performance Score (x-axis, 0-100) vs Growth Opportunity Score (y-axis, 0-100). Include quadrant divisions with labels: "Optimize" (top-right), "Develop" (top-left), "Maintain" (bottom-right), "Divest" (bottom-left). Color code by business category and size points by revenue/impact potential. Attachments Quarterly Performance 977 lines csv Strategic Metrics 92 kb json Analysts Research in Claude apps, then build data pipelines and query data with Claude Code. Note Interact with the data—hover and toggle views to uncover patterns View prompt View prompt View prompt Prompt Create an interactive time series chart showing performance trends over time from my uploaded data. Include: – Multiple metrics as different colored trend areas – Hover details showing exact values and dates – Legend to toggle metrics on/off – Trend analysis summary below the chartMake it visually clear which metrics are improving or declining. Attachments Industry Trends 522 lines csv Growth Analysis 442 kb xlsx Founders Use Claude apps for strategic planning, then prototype with Claude Code—even without coding experience. View prompt View prompt View prompt Prompt Analyze my content performance and audience data. What patterns should guide my content strategy? Attachments Audience Insights Report 8.10 kb txt Content strategy analysis: Performance patterns and strategic recommendations Key performance patterns Top performing content types Case studies dominate conversions Customer success stories achieve 15.4-16.8% conversion rates Generate highest revenue attribution ($4,560-$5,240 per piece) Strong engagement across all audience segments Pattern: Real-world proof points resonate universally Product tools and resources excel ROI calculator achieved 25.3% conversion rate (highest overall) Templates and guides average 21.4% conversion Technical tutorials: 24.6% conversion with engaged audiences Pattern: Actionable, practical content drives decisions Video content shows mixed performance Technical tutorials: 24.6% conversion rate Product demos: 18.9% conversion rate General webinars: 6.8% conversion rate Pattern: Specific, educational video content outperforms general presentations Channel performance insights Website content drives revenue Averages 13.2% conversion rate across content types Captures high-intent audiences seeking solutions Long-form content performs best (8.9-15.6 minutes average time) LinkedIn balances reach and conversion Professional audience aligns with your segments Moderate conversion rates (4.2-7.4%) but consistent performance Strong sharing behavior supports organic reach YouTube technical content opportunity Advanced tutorials achieve exceptional conversion (24.6%) Currently underutilized for your technical audience segment Long-form educational content shows promise Instagram and Twitter underperform Company culture content generates minimal business impact Low conversion rates (0.9-3.1%) for business goals Resource reallocation opportunity identified Audience alignment analysis Content gaps vs. audience needs Marketing practitioners (42% of audience) Need: Campaign optimization, ROI proof, workflow efficiency Gap: Insufficient how-to guides and process optimization content Opportunity: Your templates perform well (21.4% conversion) but production volume low Business leadership (28% of audience) Need: Competitive advantage, revenue impact, strategic planning Strength: Case studies and industry reports perform well Gap: Limited executive-focused content formats Technical implementers (8% of audience) Need: Implementation guides, security considerations, troubleshooting Major opportunity: 24.6% conversion rate but minimal content volume Gap: Only 2 technical pieces in sample vs. high demand Content consumption patterns Peak engagement alignment Tuesday-Thursday content performs best Morning publication (9-11 AM) drives higher engagement Video content optimal on Wednesdays Format preferences match performance Marketing practitioners prefer actionable guides → templates convert at 21.4% Business leaders prefer case studies → convert at 15.4-16.8% Technical implementers prefer detailed guides → convert at 24.6% Strategic recommendations Immediate content optimization (next 90 days) Expand high-converting formats Double case study production (currently 2/month, target 4/month) Create monthly interactive tool or calculator Develop technical implementation guide series Channel reallocation Reduce Instagram/Twitter investment by 60% Increase YouTube technical content production Expand LinkedIn thought leadership posting Content calendar optimization Publish primary content Tuesday-Thursday mornings Reserve Mondays for content promotion and distribution Use Fridays for community engagement and social listening Strategic content expansion (next 6 months) Technical audience development Current 8% audience generates 24.6% conversion rates Potential revenue impact: 3x current technical content ROI Target: Monthly technical tutorial series, API documentation updates Industry-specific content tracks Create vertical content for healthcare, manufacturing, financial services Develop industry-specific case studies and use cases Customize messaging for different compliance and regulatory needs Video content strategy Focus on educational, problem-solving content vs. general presentations Create customer interview series (combines case study + video strengths) Develop technical implementation video library Long-term positioning (next 12 months) Community building initiative Leverage high-engagement technical audience for peer discussions Create user-generated content programs Develop customer advisory board for content input International expansion 29% of audience outside North America presents localization opportunity Adapt high-performing content for international markets Consider regional compliance and regulatory content needs Competitive differentiation Current content volume below industry average (20 vs. 31 pieces/month) Quality metrics above average (4.8% vs. 3.9% engagement) Strategy: Maintain quality while strategically increasing volume in high-converting categories Success metrics and targets 90-day targets Increase technical content from 10% to 25% of monthly output Achieve 15%+ average conversion rate across all content Generate 1,500+ leads monthly (vs. current 1,342) 6-month targets Expand video content to 30% of production Reach 15,000+ monthly website visitors through organic content Achieve $120,000+ monthly revenue attribution 12-month targets Build technical community of 2,500+ engaged members Establish thought leadership in 3 industry verticals Generate $200,000+ monthly revenue through content marketing Implementation priority matrix High impact, quick wins Expand case study production Create monthly interactive tools Reallocate social media resources to high-performing channels High impact, medium effort Develop technical content series Launch customer interview video program Build industry-specific content tracks Strategic investments International content localization Community platform development Advanced video production capabilities Your content strategy should focus on amplifying what's already working (case studies, technical guides, practical tools) while strategically expanding into underutilized high-conversion opportunities, particularly technical content and video education formats. Creators Plan content strategy in Claude apps, then handle website updates with Claude Code. Why people choose Max Some use it all for Claude apps—writing, research, analysis. Others live in Claude Code. Most discover they need both. The capacity to do more With up to 20x more usage per session, you can finally pursue every thread, explore every possibility, and complete ambitious projects. More room for Claude’s best features Run multiple [[research|Research|Build research reports in minutes, complete with easy-to-check citations.]] sessions daily. Build complex [[artifacts|Artifacts|Turn ideas into shareable creations. Build tools, visualizations, and experiences by simply describing what you need.]] iteratively. [[Create files, analyze data|Code execution and file creation|Claude executes code to quickly analyze data and create ready-to-use documents, spreadsheets, slides, PDFs, and more.]] and pull context from all your integrated [[tools|Tools|Connect Claude to your favorite tools like JIRA, Zapier, and Intercom, or build your own.]] freely. Access to the latest and greatest New features and models often launch on Max first, before they expand to other plans. How can I help? I have tons of messy data and need to find meaningful patterns. What questions should I be asking to surface insights I wouldn't think to look for? Ask Claude Ask Claude Ask Claude How can I help? My app performance is inconsistent and I can't pinpoint why. Help me think through a systematic debugging approach that goes beyond the obvious metrics. Ask Claude Ask Claude Ask Claude Prev Prev Next Next Prev Prev Next Next Choose your Max plan <path d="M44.9536 33.9053C45.1266 34.0368 45.2555 34.1361 45.3641 34.2179C45.4178 34.2582 45.4674 34.2958 45.5131 34.3306L45.5466 34.3561L45.5708 34.3722L45.6177 34.4031C45.7479 34.4823 45.8928 34.5695 46.2228 34.6781C46.5583 34.7815 46.7488 34.7573 46.9232 34.7439C47.0131 34.7291 47.1003 34.7251 47.2103 34.7063C47.2653 34.6996 47.3257 34.6929 47.3942 34.6862C47.4626 34.6755 47.5391 34.6674 47.6276 34.658C47.7148 34.6419 47.7926 34.6325 47.8624 34.6258C47.9322 34.6191 47.9939 34.607 48.0516 34.603C48.167 34.5963 48.2609 34.5883 48.3562 34.5802C48.4045 34.5762 48.4528 34.5722 48.5038 34.5681C48.5547 34.5601 48.6071 34.548 48.6661 34.5346C48.7251 34.5198 48.7895 34.5024 48.8607 34.4782C48.9304 34.4487 49.0082 34.4138 49.0955 34.3709C49.1894 34.328 49.243 34.2904 49.3007 34.2582C49.3557 34.2246 49.4 34.1898 49.443 34.1602C49.5235 34.0958 49.5852 34.0422 49.6429 33.9831C49.7556 33.8637 49.871 33.7443 50.0427 33.4438C50.2051 33.1338 50.2332 32.946 50.2614 32.7675C50.2856 32.5851 50.3084 32.4053 50.3419 32.0323C50.3701 31.6579 50.3768 31.4647 50.3862 31.2715C50.3889 31.0797 50.3969 30.8797 50.3164 30.5027C50.2332 30.127 50.1554 29.954 50.0843 29.7889C50.0454 29.7071 50.0092 29.6266 49.9528 29.534C49.926 29.487 49.8951 29.4361 49.8616 29.377C49.8227 29.3207 49.7784 29.2576 49.7287 29.1852C49.6201 29.047 49.5315 28.9463 49.443 28.8766C49.4 28.8403 49.3625 28.8081 49.3249 28.78C49.2846 28.7545 49.2471 28.7303 49.2095 28.7062C49.1719 28.682 49.1357 28.6579 49.0955 28.6324C49.0539 28.6109 49.0096 28.5867 48.9626 28.5586C48.8714 28.4982 48.7533 28.4418 48.6044 28.3533C48.5252 28.3171 48.4568 28.2835 48.3964 28.2527C48.336 28.2205 48.2783 28.2057 48.2287 28.1829C48.1777 28.1614 48.1334 28.144 48.0905 28.1252C48.0462 28.1118 48.0046 28.0984 47.963 28.0849C47.8799 28.0568 47.7967 28.0286 47.688 28.0125C47.6343 28.0018 47.5739 27.991 47.5069 27.9776C47.4384 27.9722 47.3606 27.9669 47.2734 27.9602C47.1862 27.9481 47.107 27.9602 47.0373 27.9561C46.9675 27.9561 46.9058 27.9521 46.8508 27.9561C46.7381 27.9642 46.6482 27.9669 46.5569 27.9682C46.3758 27.9883 46.1893 28.0018 45.8324 28.1225C45.658 28.1896 45.5318 28.2513 45.4299 28.3063C45.3346 28.3694 45.2608 28.4244 45.1884 28.4781C45.0515 28.5961 44.916 28.7088 44.6638 28.9343C44.6047 28.9946 44.551 29.0456 44.5027 29.0912C44.4585 29.1395 44.4196 29.1838 44.3847 29.2227C44.3082 29.2965 44.2599 29.3663 44.2035 29.432C44.0962 29.5649 43.9916 29.7071 43.8681 30.0358C43.7527 30.3685 43.7111 30.5457 43.6655 30.7228C43.6467 30.8113 43.6226 30.9012 43.6145 31.0166C43.6078 31.0743 43.6011 31.1374 43.6025 31.2085C43.6025 31.2796 43.6011 31.3601 43.6105 31.45C43.6454 31.8136 43.738 31.988 43.8225 32.153C43.9124 32.3181 44.0036 32.4791 44.1633 32.8091L44.1713 32.8252L44.1888 32.8574C44.2009 32.8802 44.2143 32.9031 44.2264 32.9259C44.2505 32.9701 44.2733 33.0131 44.2961 33.0547C44.3458 33.1392 44.4008 33.2224 44.4464 33.2948C44.4142 33.539 44.39 33.7228 44.3672 33.8865C44.3646 33.9174 44.3525 33.9751 44.3431 34.0207C44.3337 34.0677 44.3243 34.1146 44.3136 34.1629C44.2934 34.2555 44.2733 34.3508 44.2505 34.4554C44.1351 34.5413 44.0036 34.6406 43.8453 34.7587C43.7407 34.8392 43.6186 34.9331 43.4736 35.0458C42.7853 35.5892 42.733 35.5234 42.0447 36.0655C41.3578 36.6075 41.4383 36.7109 40.7513 37.2542C40.4695 37.477 40.2938 37.5977 40.1355 37.701C40.0563 37.752 39.9812 37.8017 39.8993 37.8553C39.8591 37.8835 39.8161 37.9117 39.7692 37.9426C39.7464 37.9587 39.7222 37.9748 39.6981 37.9922C39.6672 38.015 39.6336 38.0392 39.6001 38.0646C39.5572 38.0915 39.5048 38.125 39.4431 38.1653C39.3908 38.2002 39.3318 38.2391 39.266 38.282C38.5401 38.7731 38.5737 38.8227 37.8492 39.3138C37.1233 39.8049 37.0495 39.6975 36.325 40.1886C35.5991 40.6797 35.6729 40.7883 34.9484 41.2794C34.2225 41.7705 34.1541 41.6698 33.4282 42.1609C32.9224 42.5004 32.646 42.6855 32.4165 42.8398C32.0945 42.6426 31.8275 42.4802 31.2385 42.1193C30.4885 41.6658 30.4764 41.6859 29.7277 41.2324C28.9777 40.7789 28.9884 40.7615 28.2384 40.308C27.4884 39.8545 27.4441 39.9283 26.6941 39.4748C25.9441 39.0213 25.987 38.9515 25.237 38.4967C25.1833 38.4645 25.1323 38.4336 25.1082 38.4202C25.0599 38.384 25.0129 38.3504 24.97 38.3182C24.9351 38.2941 24.9029 38.2699 24.8707 38.2485C24.8077 38.2055 24.7513 38.168 24.6976 38.1344C24.5916 38.0673 24.5017 38.015 24.4092 37.9613C24.2253 37.854 24.0375 37.7413 23.7088 37.489C23.0138 36.955 22.9574 37.0275 22.2624 36.4935C21.5674 35.9595 21.5996 35.9179 20.9046 35.3839C20.7315 35.2497 20.6014 35.1491 20.4927 35.0659C20.443 35.0257 20.3974 34.9908 20.3545 34.9572L20.3464 34.9478C20.3464 34.9478 20.3357 34.9344 20.3277 34.9264C20.3196 34.9223 20.3089 34.9331 20.2914 34.9411C20.2297 34.976 20.1747 35.0055 20.1264 35.0324C20.0526 35.0726 19.9855 35.1062 19.9251 35.1357C19.803 35.1947 19.7024 35.2363 19.6018 35.2792C19.5012 35.3222 19.4005 35.3638 19.2771 35.4228C19.2154 35.4523 19.1496 35.4859 19.0745 35.5261C19.0369 35.5462 18.998 35.5677 18.9564 35.5919C18.9121 35.6174 18.8652 35.6455 18.8142 35.6737C18.566 35.8226 18.3795 35.8951 18.2225 35.9541C18.0655 36.0132 17.9381 36.048 17.8119 36.0843C17.5583 36.1433 17.2994 36.205 16.7869 36.2117C16.6581 36.2158 16.548 36.2091 16.4487 36.2077C16.3495 36.2077 16.2622 36.2023 16.1831 36.1997C16.0234 36.197 15.8973 36.1916 15.7698 36.1849C15.5149 36.1728 15.256 36.15 14.7837 35.9836C14.6669 35.9394 14.565 35.8991 14.4764 35.8602C14.3892 35.8186 14.3141 35.7797 14.2456 35.7421C14.1142 35.6777 13.9921 35.5878 13.8794 35.5073C13.823 35.4671 13.7666 35.4255 13.7063 35.3826C13.6499 35.3329 13.5909 35.2819 13.5265 35.2242C13.4621 35.1652 13.3843 35.1088 13.3105 35.031C13.2353 34.9545 13.1521 34.8673 13.0555 34.7694C12.8838 34.5601 12.751 34.4004 12.6678 34.2582C12.5765 34.1173 12.5027 34.0059 12.4464 33.8879C12.3874 33.7711 12.3189 33.6558 12.2653 33.5041C12.2357 33.429 12.2035 33.3458 12.1673 33.2519C12.1391 33.1566 12.1083 33.0493 12.0734 32.9272C11.954 32.4375 11.9486 32.1879 11.9419 31.9437C11.9419 31.6982 11.9379 31.4567 11.9526 30.9763C11.9526 30.8556 11.9647 30.7509 11.9687 30.657C11.9728 30.5631 11.9781 30.4799 11.9862 30.4048C11.9969 30.2545 12.0063 30.1324 12.0224 30.0103C12.0264 29.9794 12.0291 29.9486 12.0331 29.9177L12.0385 29.8708C12.0425 29.8493 12.0466 29.8292 12.0506 29.8064C12.06 29.7634 12.0694 29.7178 12.0801 29.6709C12.0908 29.6252 12.1056 29.5836 12.1204 29.538C12.1794 29.3542 12.2679 29.1583 12.4088 28.9316C12.5484 28.7035 12.6718 28.5559 12.7778 28.4365C12.8851 28.3197 12.9764 28.2312 13.0703 28.1493C13.2595 27.9857 13.4433 27.8206 13.8351 27.5228C14.2309 27.2303 14.4429 27.0974 14.6562 26.9646C14.8749 26.8412 15.0923 26.703 15.5941 26.5607C15.7202 26.5272 15.8302 26.499 15.9322 26.4843C16.0328 26.4668 16.1227 26.4494 16.2045 26.444C16.2864 26.4373 16.3615 26.4306 16.4313 26.4239C16.5024 26.4239 16.5695 26.4226 16.6352 26.4212C16.9009 26.4279 17.1733 26.4293 17.6952 26.5581C17.824 26.5943 17.934 26.6319 18.0347 26.6627C18.1313 26.7016 18.2158 26.7352 18.2923 26.7674C18.4452 26.8304 18.5593 26.8962 18.6773 26.9539C18.9001 27.0867 19.1349 27.2155 19.5092 27.5563C19.8755 27.8931 20.0419 28.0635 20.219 28.2419C20.3035 28.3345 20.3934 28.4217 20.4887 28.5492C20.5879 28.6726 20.698 28.8283 20.8254 29.051C21.075 29.5031 21.134 29.7648 21.1864 30.0197C21.2333 30.276 21.2856 30.5296 21.3366 31.0407C21.3782 31.5533 21.342 31.8096 21.3084 32.0605C21.2669 32.31 21.2293 32.5623 21.0736 33.0426C20.9475 33.4116 20.7865 33.5981 20.6282 33.6652C20.4672 33.7322 20.3062 33.6813 20.1304 33.5685C19.9547 33.4545 19.8178 33.3458 19.7547 33.2023C19.6903 33.0574 19.7011 32.8829 19.7936 32.6132C19.9077 32.2617 19.9386 32.0792 19.9734 31.8981C20.0016 31.717 20.0325 31.5318 20.003 31.1669C19.9681 30.8019 19.9117 30.6262 19.8607 30.4491C19.8057 30.2733 19.748 30.0975 19.5669 29.7675C19.473 29.6038 19.3884 29.4884 19.3093 29.3971C19.2355 29.3046 19.159 2 | 2026-01-13T08:47:52 |
https://claude.com/pricing/enterprise | Enterprise plan | Claude -------> Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Pricing Pricing / Enterprise Explore here Ask questions about this page Copy as markdown Claude Enterprise Securely connect Claude to your company knowledge and give every team access to trusted AI. Designed for large organizations and enterprise-scale challenges. Contact sales Contact sales Contact sales 89% employee adoption, 800+ AI agents deployed, 10x app usage growth 65% of team members use AI to increase productivity and effectiveness either "everyday" or "often" 98% of team members surveyed reported to be satisfied or very satisfied with Claude for Work 90% reduction in work time for business proposals and bid responses 20% weekly time saved with Claude assistance on analytical and operational tasks Prev Prev 0 / 5 Next Next Tackle your most complex challenges Get work done faster Cut project timelines from days to hours, with 25–100% productivity gains that free up employees for more strategic work. Expand what your teams can do Give every department the tools they need to tackle complex challenges beyond their usual expertise. Scale your institutional knowledge Turn your organization’s expertise into something every team can access, so quality stays consistent as you grow. Play video Play video See how fully integrating Claude across their organization has revolutionized Quantium's workflows. Read more Read more Read more Next Next Prev Prev Next Next Transform how your teams work Enable every employee to spark new ideas, achieve more, and collaborate better. Projects Connectors Research Artifacts Claude Code Active Turn everyone into an expert Add text, code, and files to dedicated projects as context for your chats. Claude can reference large amounts of information for every task, including the equivalent of: Ten 30-minute sales transcripts 15 full financial reports 100K lines of code Connect to your most important tools Access your databases, CRM systems, project management tools, and development environments through secure, standardized integrations. Claude gains deep context about your workflows and can take actions across every surface. Create research reports in minutes Get comprehensive, cited reports from your internal data and the web. Claude conducts multiple searches that build on each other, automatically exploring different angles of your question. Bring ideas to life with artifacts See and build upon Claude’s output in real-time using dynamic, collaborative workspaces. Create and refine reports, visualizations, prototypes, and more—with secure sharing across your organization. ╭───────────────────────────╮ │ │ │ ✶ Welcome to Claude Code │ │ │ ╰───────────────────────────╯ ██████╗██╗ █████╗ ██╗ ██╗██████╗ ███████╗ ██╔════╝██║ ██╔══██╗██║ ██║██╔══██╗██╔════╝ ██║ ██║ ███████║██║ ██║██║ ██║█████╗ ██║ ██║ ██╔══██║██║ ██║██║ ██║██╔══╝ ╚██████╗███████╗██║ ██║╚██████╔╝██████╔╝███████╗ ╚═════╝╚══════╝╚═╝ ╚═╝ ╚═════╝ ╚═════╝ ╚══════╝ ██████╗ ██████╗ ██████╗ ███████╗ ██╔════╝██╔═══██╗██╔══██╗██╔════╝ ██║ ██║ ██║██║ ██║█████╗ ██║ ██║ ██║██║ ██║██╔══╝ ╚██████╗╚██████╔╝██████╔╝███████╗ ╚═════╝ ╚═════╝ ╚═════╝ ╚══════╝ Claude Code can now be used with your Claude subscription or billed based on API usage through your Console account. Select login method: ❯ 1. Claude account with subscription Pro, Max, Team, or Enterprise 2. Anthropic Console account API usage billing * Flibbertigibbetting… Code with AI right in your terminal Transform development workflows with an AI agent that understands your entire codebase. Execute routine tasks, build features, and handle Git workflows through natural language commands, with integrations to your existing development tools. Deploy with confidence Manage access with enterprise-grade controls, and rest assured that we don't train our models on your Claude for Work data. Single sign-on (SSO) and domain capture Role-based access with fine-grained permissioning System for Cross-domain Identity Management (SCIM) Protected company data Audit logs Data retention controls Compliance API Usage analytics Spend controls Self-serve seat management HIPAA-ready offering available Connectors Connect to Jira, Confluence, and other Atlassian tools to manage issues, access documentation, track sprints, create tickets, update project status, and coordinate development workflows. Learn more Learn more Learn more Connectors Manage Workers deployments, D1 databases, R2 storage, and KV stores directly through Claude. Learn more Learn more Learn more Connectors Manage customer conversations, access support tickets, retrieve customer profiles, analyze conversation patterns, and handle customer service workflows through Intercom’s messaging platform. Learn more Learn more Learn more Prev Prev Next Next Prev Prev Next Next Critical cross-functional work starts with Claude Engineering Marketing Sales Product Management Human Resources Legal Active View prompt View prompt View prompt Prompt > claude fix the authentication error in our login flow I'll investigate the auth error. Let me look at the relevant files. Examining auth-related files... * src/services/authService.js * src/components/Login.jsx * src/store/authSlice.js Running the login flow... Error detected: "401 Unauthorized: Token expired" Root cause: * Token refresh mechanism not handling expired tokens correctly * Refresh token missing from request header * Improper error handling for 401 responses Updating authService.js with proper refresh logic... Updating request interceptor for 401 handling... Testing the fix... * Login successful ✓ * Token refresh working ✓ * Proper redirection on expired tokens ✓ Authentication error fixed! The login flow now properly handles token expiration. Engineering Convert project requirements into technical specifications Design system architecture and component interactions Troubleshoot errors and runtime issues Identify code optimizations and performance improvements Note Interact with the data—hover and toggle views to uncover patterns View prompt View prompt View prompt Prompt Create a multi-line trend chart showing the performance of three key business metrics over the past 12 months: marketing campaign ROI (pink line), sales conversion rate (blue line), and market share growth (green line). Display clear trend intersections and mark significant performance changes with data points. Include a legend and show month-over-month progression. Attachments Quarterly Performance 1,283 lines csv Market Analysis 71 kb json Marketing Interpret market trends and consumer behavior patterns Brainstorm multi-platform content items Develop marketing campaign strategies Create post campaign performance reports Note Interact with the data—hover and toggle views to uncover patterns View prompt View prompt View prompt Prompt Create a scatter plot matrix showing business performance vs opportunity analysis. Plot data points by Current Performance Score (x-axis, 0-100) vs Growth Opportunity Score (y-axis, 0-100). Include quadrant divisions with labels: "Optimize" (top-right), "Develop" (top-left), "Maintain" (bottom-right), "Divest" (bottom-left). Color code by business category and size points by revenue/impact potential. Attachments Quarterly Performance 977 lines csv Strategic Metrics 92 kb json Sales Analyze sales calls to craft tailored account plans Develop objection handling strategies Build compelling and tailored pitches Interpret sales metrics and KPIs View prompt View prompt View prompt Prompt Based on the uploaded user feedback survey and analytics report, create a product requirements document for a new feature that addresses the main user pain points identified in the data. Include the product vision and measurable objectives, analysis of user feedback data, technical specifications and requirements, and key performance indicators and success metrics. Keep it concise and professional. Attachments User Feedback Results 2.1 mb pdf Product Analysis Dashboard 325 lines csv Product requirements document: Unified dashboard feature Product vision Create a centralized dashboard that provides users with immediate access to their most critical account information, usage data, and billing details in a single, intuitive interface. This dashboard will reduce user frustration, decrease support tickets, and improve overall product satisfaction by addressing the top three pain points identified in user feedback. Measurable objectives Primary objectives Reduce average time to find account information from 156 seconds to under 30 seconds Decrease billing-related support tickets by 40% within 3 months of launch Improve user satisfaction score from 3.2 to 3.8 within 6 months Increase task completion rate from current 70% to 85% Secondary objectives Reduce session duration variability by providing faster access to key information Improve feature discovery rate from 34% to 50% Decrease user churn rate by 15% through improved user experience Analysis of user feedback data Key pain points identified Account information access (68% of users affected) Users require too many clicks to access basic account details Current navigation structure creates confusion and frustration Lack of centralized information view increases task completion time Usage tracking visibility (52% of users affected) Users cannot easily monitor their monthly usage patterns Absence of trend analysis and limit visibility Poor understanding of consumption relative to plan limits Billing clarity issues (43% of users affected) Complex billing information presentation Difficulty locating payment due dates and charge breakdowns Users struggle to understand what they're paying for User segment analysis Power users (22%) : Need advanced analytics and quick access to detailed metrics Casual users (45%) : Require simplified, clear presentation of essential information New users (33%) : Need intuitive interface with guided discovery of key features Supporting analytics data Support tickets average 289 per reporting period, with billing and account access as top categories Mobile users (59% of sessions) experience more navigation difficulties Task completion rates remain consistently below 75% across all user segments Technical specifications and requirements Functional requirements Dashboard layout Single-page interface accessible from main navigation Responsive design optimized for both mobile and web platforms Customizable widget arrangement based on user preferences and behavior Account information widget Display current plan type and status Show account creation date and user profile summary Include quick access links to account settings and profile management Usage tracking widget Real-time usage metrics with visual progress indicators Monthly and weekly trend charts Comparison to plan limits with percentage utilization Historical data view for previous 12 months Billing information widget Current billing cycle information with next payment date Itemized charge breakdown for current month Payment history with downloadable invoices Quick payment method management Quick actions panel One-click access to most frequent user tasks Contextual actions based on account status and usage patterns Integration with existing feature set without duplication Technical implementation requirements Performance standards Page load time under 2 seconds on mobile devices Real-time data refresh capability with 30-second update intervals Offline capability for cached essential information Data integration Connect with existing user management system Integrate with billing and payment processing systems Link to usage tracking and analytics backend Maintain data consistency across all platform touchpoints Security and privacy Implement role-based access controls for sensitive information Ensure compliance with data protection regulations Provide audit trail for all dashboard interactions Secure API endpoints with appropriate authentication Platform compatibility Native mobile app integration (iOS and Android) Web browser compatibility (Chrome, Safari, Firefox, Edge) Tablet-optimized layout with touch-friendly interface API availability for potential third-party integrations Key performance indicators and success metrics User experience metrics Dashboard adoption rate : Target 80% of active users within 60 days Time to complete common tasks : Reduce by 60% compared to current flow User satisfaction score : Increase from 3.2 to 3.8 (19% improvement) Feature discovery rate : Increase from 34% to 50% Operational impact metrics Support ticket reduction : 40% decrease in account and billing related tickets Task completion rate : Increase from 70% to 85% Session efficiency : Reduce average session duration while maintaining engagement Mobile experience improvement : Achieve parity with web task completion rates Business impact metrics User retention : Reduce churn rate by 15% within 6 months User engagement : Increase daily active user percentage by 12% Customer lifetime value : Improve through reduced support costs and increased satisfaction New user onboarding : Improve completion rate from 67% to 80% Technical performance metrics Page load time : Maintain under 2 seconds across all devices System reliability : 99.5% uptime for dashboard functionality Mobile crash rate : Keep below 1% for dashboard-related crashes API response time : Average response under 200ms for dashboard data Success criteria and timeline Phase 1 (weeks 1-4): foundation development Complete technical architecture and database integration Develop core dashboard framework with basic widgets Implement responsive design for mobile and web platforms Phase 2 (weeks 5-8): feature implementation Build and integrate all dashboard widgets Implement customization capabilities Complete security and privacy compliance requirements Phase 3 (weeks 9-10): testing and optimization Conduct comprehensive user acceptance testing Performance optimization and load testing Security audit and penetration testing Phase 4 (weeks 11-12): launch and monitoring Gradual rollout to user segments starting with power users Monitor key performance indicators and user feedback Rapid iteration based on initial usage patterns Risk mitigation Technical risks Performance degradation under high load: Implement caching and load balancing Data integration complexity: Establish fallback mechanisms and error handling Mobile platform inconsistencies: Extensive cross-platform testing protocols User adoption risks Resistance to interface changes: Provide optional onboarding tour and help documentation Feature discoverability: Implement guided first-use experience Customization complexity: Start with smart defaults based on user behavior patterns Conclusion The unified dashboard feature directly addresses the primary pain points identified in user feedback while supporting broader business objectives of improved user satisfaction and reduced operational costs. Success metrics are designed to validate both immediate user experience improvements and long-term business value creation. Product Management Define product vision and objectives Analyze user feedback and usage data Create product specifications and requirements documents Interpret product usage metrics and KPIs View prompt View prompt View prompt Prompt Based on the uploaded marketing performance report and company growth strategy, create a job posting for a Growth Marketing Manager position that addresses the performance gaps and growth objectives identified in the documentation. Attachments Company Growth Strategy 2024 582 kb pdf Marketing Performance Report Q1 2024 1.3 MB pdf Growth Marketing Manager FlowTech | Full-time | Remote/Hybrid About FlowTech FlowTech is a fast-growing SaaS company positioned for explosive growth in 2025. With $12M in annual recurring revenue and 8,400 active customers, we're ready to double our revenue and expand internationally. Our platform has proven product-market fit in North America, and we're scaling through channel optimization, international expansion, and new customer segment penetration. The opportunity We're seeking a data-driven Growth Marketing Manager to join our team during a pivotal growth phase. You'll be responsible for optimizing our marketing performance, reducing customer acquisition costs, and driving our ambitious goal of acquiring 15,000 new customers in 2024. This role is critical to achieving our target of $24M revenue and expanding into international markets. What you’ll do Performance optimization and channel management Optimize our paid social campaigns (Meta, LinkedIn) to reduce CAC from current $204 and improve conversion rates from 1.8% Scale our top-performing Google Ads channel while maintaining current $130 CAC efficiency Develop and execute strategies to improve trial-to-paid conversion rate from 33% to 45% Reallocate marketing budget from underperforming channels (webinars, partnerships) to high-ROI opportunities International expansion leadership Launch and manage marketing campaigns in priority international markets (UK, Germany, Australia, Canada) Develop localized marketing materials and campaigns for international audiences Establish multi-currency pricing strategies and local payment method integration Collaborate with sales teams to provide time zone coverage for international prospects Growth experimentation and optimization Implement and manage A/B testing programs across all marketing channels Optimize onboarding experience to reduce time-to-first-value from 14 days to 5 days Develop product-led growth initiatives including viral sharing and team invitation features Create segment-specific campaigns for SMB (10-500 employees) and Enterprise (25,000+ employees) markets Analytics and attribution Implement comprehensive multi-touch attribution to reduce "direct/unknown" conversions from 23% Build dashboards and reporting systems to track key growth metrics (MRR growth, CAC, LTV) Conduct competitive analysis and market research to identify new growth opportunities Optimize customer acquisition funnel to improve overall conversion rates What we’re looking for Required experience 3-5 years of growth marketing experience at a B2B SaaS company Proven track record of managing $500K+ annual marketing budgets Experience scaling companies from $10M to $25M+ ARR Strong analytical skills with proficiency in Google Analytics, Facebook Ads Manager, and marketing automation platforms Technical skills Advanced knowledge of paid advertising platforms (Google Ads, Meta, LinkedIn) Experience with marketing automation tools (HubSpot, Marketo) Proficiency in analytics tools (Mixpanel, Segment, attribution platforms) Understanding of international marketing challenges and localization requirements Growth marketing expertise Experience improving trial-to-paid conversion rates in SaaS environments Track record of reducing customer acquisition costs while scaling volume Knowledge of product-led growth strategies and implementation Experience with multi-touch attribution and complex customer journey optimization International expansion experience Previous experience launching marketing campaigns in European and APAC markets Understanding of GDPR compliance and international data regulations Knowledge of local payment methods and currency considerations Experience with localization and cultural adaptation of marketing materials Success metrics (first 12 months) Performance improvements Reduce overall customer acquisition cost from $171 to $140 Increase monthly customer acquisition from 950 to 1,200 Improve trial-to-paid conversion rate from 33% to 45% Achieve LTV:CAC ratio above 8:1 Growth targets Generate $6M ARR from international markets (25% of total revenue) Acquire 5,400 new customers through optimized channels Launch successful campaigns in 4 international markets Increase organic traffic growth by 150% year-over-year Channel optimization Reduce paid social CAC by 30% while maintaining volume Scale Google Ads to deliver 36% of total new customers Launch and optimize new customer segments (SMB and Enterprise) Eliminate budget allocation to channels with CAC above $300 What we offer Compensation and benefits Competitive salary and meaningful equity stake in a fast-growing company Comprehensive health, dental, and vision insurance $2,000 annual learning and development budget Growth opportunities Direct impact on company growth during critical scaling phase Opportunity to build and lead a marketing team as we grow Work closely with CEO and executive team on strategic initiatives International travel opportunities for market expansion Work environment Remote-first culture with optional hybrid work Flexible working hours with core collaboration time Modern marketing stack and tools budget Quarterly team meetups and annual company retreat Ready to apply? Send us your resume along with a brief cover letter addressing: Your experience reducing CAC while scaling customer acquisition Specific examples of international marketing campaigns you've launched Your approach to improving trial-to-paid conversion rates Why you're excited about FlowTech's growth opportunity Apply to: [email protected] Subject line: Growth Marketing Manager - [Your Name] — FlowTech is an equal opportunity employer committed to diversity and inclusion. We welcome applications from all qualified candidates regardless of race, gender, age, religion, sexual orientation, or disability status. <path d="M243.286 0.207824C242.732 15.1717 246.542 31.5212 252.568 45.1689C275.359 96.7113 310.55 163.98 360.703 192.383C365.483 195.085 390.213 207.832 393.954 208.248C405.245 209.426 414.389 196.332 420.762 188.158C437.457 166.82 447.294 148.461 456.715 123.037C467.314 94.4251 478.744 66.0906 489.065 37.4791C493.499 25.217 496.547 12.4007 501.396 0.277116H512.202C505.344 11.8464 502.019 25.0091 497.032 37.3405C493.914 45.0303 489.827 52.3737 486.779 60.0635C478.397 81.1931 474.657 103.431 467.106 124.63C456.992 152.826 444.8 171.185 425.958 193.977C423.326 197.164 410.579 209.079 411.272 212.058C412.034 215.384 423.464 217.462 426.65 218.293C476.388 230.832 534.092 233.465 585.354 233.603C593.598 233.603 601.01 237.622 607.244 230.347C612.163 224.597 617.428 186.841 619.714 176.727C623.108 161.486 627.472 146.383 630.659 131.073C640.01 86.1118 641.604 39.0032 669.313 0.277116H678.734C651.925 40.5966 652.064 89.6449 641.465 135.16C634.191 166.543 621.722 196.748 615.488 228.546C615.28 231.872 617.081 233.742 620.406 234.158C627.264 234.92 649.501 231.248 657.329 229.862C675.27 226.745 696.606 219.124 713.37 211.781C728.125 205.269 741.633 194.462 756.25 187.95C769.135 182.2 786.037 178.182 798.506 172.224C821.505 161.209 849.629 137.031 871.312 122.413C882.257 115.001 892.856 109.389 903.177 100.383C906.987 97.127 920.773 83.2022 922.782 79.5304C923.959 77.3136 923.197 75.6509 921.327 74.1268C910.451 70.2473 898.328 66.3677 887.868 61.7262C865.285 51.7502 846.097 34.9851 827.67 18.8435C821.228 13.1627 814.37 6.71992 808.828 0.277116H819.634L861.752 35.2622C877.616 47.5243 900.406 56.8768 919.526 63.1117C923.336 64.3587 930.679 67.3377 934.004 64.0816C935.874 62.2111 940.862 50.434 943.356 46.8316C955.686 28.8194 976.883 17.1808 990.807 0.277116H1006.95C1002.93 3.94882 999.536 8.38255 995.518 12.0543C980.209 26.0483 958.942 36.8556 947.65 54.5213C946.126 56.8767 940.307 67.4069 941.693 69.5545C956.933 73.919 972.45 77.0364 987.69 81.1238C1027.18 91.7925 1064.58 101.214 1105.66 105.302C1131.08 107.865 1150.34 108.766 1175.07 117.425C1181.45 119.642 1202.85 130.38 1207.42 130.311C1208.46 130.311 1209.29 130.449 1210.12 129.549C1212.96 126.639 1209.36 109.666 1209.09 104.955C1207.15 70.4551 1213.52 40.0424 1220.93 6.92774C1221.49 4.57231 1222.04 2.28615 1223.29 0.207824H1230.01C1229.52 3.81025 1227.93 7.13554 1227.37 10.738C1222.11 46.7622 1216.5 75.0967 1220.65 112.299C1221.62 120.889 1222.66 136.199 1229.66 141.672C1232.29 143.751 1251.2 152.48 1255.15 153.934C1304.75 172.085 1366.68 185.941 1419.67 186.841C1433.39 187.049 1448.01 182.13 1461.79 181.438V191.552C1461.79 193.145 1433.18 193.561 1430.41 195.57C1367.51 194.254 1307.52 186.633 1248.64 163.772C1242.2 161.278 1236.31 156.636 1229.73 154.35C1228.27 153.865 1226.82 152.48 1225.92 154.142C1227.17 160.931 1226.96 168.067 1228.14 174.856C1231.95 197.787 1238.46 226.399 1244.21 249.052C1245.04 252.447 1247.19 261.314 1248.99 263.808C1249.54 264.64 1254.94 269.143 1255.64 269.281C1257.09 269.628 1278.77 261.73 1283.69 260.968C1328.79 253.555 1368.55 262.007 1411.99 271.983C1428.82 275.863 1446.07 278.01 1461.79 285.562L1461.52 293.875C1441.5 286.046 1421.82 280.574 1400.69 276.555C1373.68 271.36 1344.93 268.796 1317.29 269.558C1302.05 269.974 1274.13 271.637 1260.62 278.287C1257.44 279.811 1255.84 286.116 1256.47 289.302C1257.92 297.339 1263.88 310.501 1266.65 318.953C1274.96 344.794 1282.1 370.219 1287.71 396.96C1296.23 437.418 1300.94 478.499 1311.68 518.611C1312.86 520.551 1315.42 523.045 1317.91 522.837C1320.68 522.629 1335.51 516.671 1339.32 515.216C1369.17 503.785 1414.48 490.692 1446.34 487.436C1451.54 486.882 1456.8 487.436 1462 487.228V498.035C1457.5 498.243 1452.79 497.689 1448.28 498.105C1419.12 500.876 1386.91 512.584 1357.4 516.394C1345.9 521.659 1331.21 524.499 1319.99 529.557C1314.59 531.981 1314.31 536.069 1314.38 541.472C1314.52 554.289 1318.74 563.918 1321.45 575.487C1323.32 583.247 1321.03 591.698 1321.93 599.943C1323.45 613.867 1329.27 629.178 1333.36 642.41C1336.69 653.009 1338.83 663.955 1343.96 673.931H1334.19C1333.36 673.931 1329 663.123 1328.44 661.461C1322.28 644.141 1314.86 620.102 1312.37 602.09C1311.33 594.4 1313.06 587.195 1312.3 579.921C1311.33 571.262 1307.18 561.701 1306.28 550.963C1305.93 547.015 1308.08 535.93 1303.09 535.307C1301.98 535.168 1286.95 538.355 1284.87 538.978C1268.38 543.62 1251.97 556.852 1235.13 558.653C1223.08 559.969 1209.09 560.731 1196.82 561.494C1172.99 562.948 1143.41 565.096 1119.93 564.195C1101.64 563.503 1078.58 560.732 1060.01 558.792C1041.45 556.852 1023.92 552.418 1005.91 548.885C987.898 545.352 970.164 545.283 951.53 543.274C934.142 541.472 909.343 534.683 892.925 535.168C880.594 535.514 875.884 550.34 871.589 559.692C857.457 590.382 842.771 621.141 823.444 648.991C817.625 657.443 810.283 664.786 804.672 673.377L797.536 674C795.805 672.476 813.746 649.614 815.34 646.982C818.457 641.855 820.119 636.313 823.029 631.117C838.754 602.852 854.132 574.656 869.303 545.975C870.758 543.273 876.507 536.415 875.399 533.852C873.736 530.042 857.25 530.942 852.539 530.388C837.992 528.587 821.505 522.629 806.473 519.858C746.413 508.981 685.384 507.249 624.701 512.93C621.584 513.207 612.024 513.969 609.807 514.8C604.266 517.017 607.868 530.596 607.937 535.168C608.145 548.4 609.046 561.286 609.531 574.518C610.431 599.388 606.76 624.536 611.678 649.129C613.271 656.888 617.497 665.756 618.951 673.862H608.838C603.712 657.304 599.971 641.786 598.724 624.328C596.854 597.033 598.17 567.936 596.715 540.087C596.438 535.445 596.23 527.548 595.329 523.322C594.983 521.52 591.45 518.403 589.58 518.264C574.409 522.005 558.754 523.252 543.306 525.885C531.183 527.894 518.714 531.635 506.591 532.951C498.763 533.852 491.074 533.436 483.316 534.614C448.402 540.017 406.769 552.834 377.051 571.885C370.748 575.903 365.483 581.376 358.971 585.117C358.417 586.225 358.833 588.373 359.317 589.551C361.188 594.054 384.325 609.641 389.798 614.283C404.206 626.614 421.386 646.635 431.846 662.5C434.201 666.102 435.933 670.259 438.288 673.862H424.157C424.157 673.862 422.425 670.19 421.732 669.22C400.812 639.431 378.783 617.4 349.065 596.409C346.918 595.093 344.008 595.716 341.791 596.617C337.981 598.141 325.374 606.316 321.148 608.948C287.897 630.009 258.526 656.196 223.058 673.931H209.273C223.128 662.223 240.238 654.81 255.062 644.557C274.597 630.979 292.262 614.56 313.113 601.536C318.377 598.28 327.937 594.677 332.093 591.075C336.457 587.265 331.054 583.385 327.868 580.614C320.871 574.379 314.083 570.846 307.294 563.433C293.093 547.984 280.208 529.072 267.185 512.584C261.574 505.448 254.993 499.144 249.451 491.939C242.316 482.725 236.358 471.571 228.808 462.704C224.928 458.201 209.204 441.089 205.255 438.388C195.834 431.945 188.63 443.306 183.365 450.234C159.743 481.686 141.801 507.041 111.529 533.367C88.115 553.734 64.3545 566.135 38.7928 582.623C26.2545 590.729 14.963 602.506 0.346483 607.147V599.042C12.1921 593.153 21.5439 583.177 32.0734 575.834C38.5157 571.331 46.0665 568.283 52.5781 563.987C99.3372 533.09 148.036 492.701 179.417 446.216C181.702 442.821 189.738 434.092 189.738 430.906C189.807 425.156 177.2 419.406 172.351 417.189C121.297 393.842 65.6014 386.222 10.0447 382.758C6.85818 382.55 3.53306 381.511 0.277248 381.372V375.276C10.2525 375.414 20.2971 375.137 30.2723 375.276C57.1501 375.83 88.3922 380.056 114.854 386.36C135.775 391.348 159.812 401.878 178.862 411.923C186.759 416.08 194.726 425.918 202.415 417.327C212.459 406.104 221.534 390.17 231.44 378.324C248.066 358.372 269.125 342.646 288.036 325.119C299.327 314.658 307.779 301.703 317.685 290.065C339.921 264.085 368.254 243.995 392.776 220.302L392.984 215.73C374.073 206.239 353.568 196.817 336.527 184.209C295.24 153.657 262.474 95.0486 243.84 47.8014C238.16 33.3917 234.557 15.3796 236.081 0H243.494L243.286 0.207824ZM1214.9 146.522C1197.45 138.763 1179.92 129.064 1161.77 123.175C1127.97 112.16 1092.01 111.052 1057.1 105.232C1017.2 98.5818 979.585 86.7353 939.892 79.7383C928.254 80.431 919.041 100.729 911.49 108.696C901.93 118.88 889.946 125.115 879.001 132.805C860.367 145.76 842.217 159.269 822.405 170.561C797.121 184.971 768.996 188.435 743.573 202.221C701.732 225.013 679.011 234.158 631.074 241.986C622.692 243.372 612.925 241.085 608.283 249.468C605.028 255.357 601.356 272.814 599.347 280.296C594.083 299.971 588.956 320.962 585.216 340.983C576.834 385.598 581.96 418.505 592.766 461.734C595.052 470.809 599.209 491.731 602.672 499.005C603.088 499.837 604.889 502.469 605.513 502.885C607.729 504.201 622.484 501.638 626.433 501.499C637.101 501.014 651.025 500.252 661.554 500.806C708.937 503.3 756.735 505.379 803.632 513.069C827.739 517.017 854.686 525.054 879.209 523.114C886.275 522.56 893.271 512.653 897.774 507.249C900.891 503.508 903.454 498.59 906.849 494.779C952.499 443.722 1016.16 418.851 1069.22 376.869C1109.47 345.071 1152.14 312.372 1198.9 290.272C1210.96 284.592 1226.68 281.821 1238.18 276.348C1244.97 273.092 1243.79 269.558 1242.54 262.908C1236.79 233.465 1226.06 204.368 1219.48 175.48C1217.33 165.989 1216.29 156.221 1214.97 146.591L1214.9 146.522ZM598.308 245.588C597.408 245.103 586.67 245.311 584.592 245.381C531.044 247.32 476.25 240.808 424.434 227.022C418.615 225.498 405.522 219.679 400.465 221.688C375.527 247.667 344.839 268.381 322.534 296.715C310.065 312.51 303.137 324.565 288.659 339.321C264.899 363.499 241.346 384.213 219.733 410.884C215.092 416.634 206.294 424.255 208.788 43 | 2026-01-13T08:47:52 |
https://www.anthropic.com/claude/opus | Skip to main content Skip to footer Research Economic Futures Commitments Learn News Try Claude Claude Opus 4.5 Hybrid reasoning model that pushes the frontier for coding and AI agents, featuring a 200K context window Try Claude Get API access Announcements NEW Claude Opus 4.5 Nov 24, 2025 Claude Opus 4.5 is our most intelligent model to date. It sets a new standard across coding, agents, computer use, and enterprise workflows. Opus 4.5 is a meaningful step forward in what AI systems can do. Read more Claude Opus 4.1 Aug 5, 2025 Claude Opus 4.1 is a drop-in replacement for Opus 4 that delivers superior performance and precision for real-world coding and agentic tasks. It handles complex, multi-step problems with more rigor and attention to detail. Read more Claude Opus 4 May 22, 2025 Claude Opus 4 pushes the frontier in coding, agentic search, and creative writing. We’ve also made it possible to run Claude Code in the background, enabling developers to assign long-running coding tasks for Opus to handle independently. Read more Availability and pricing For business users and consumers who want to collaborate with our most powerful model on complex tasks, Opus 4.5 is available on Claude for Pro, Max, Team, and Enterprise users. For developers interested in building AI solutions that demand frontier intelligence, Opus 4.5 is available on the Claude Developer Platform natively, and in Amazon Bedrock, Google Cloud’s Vertex AI, and Microsoft Foundry. Pricing for Opus 4.5 starts at $5 per million input tokens and $25 per million output tokens, with up to 90% cost savings with prompt caching and 50% savings with batch processing . To learn more, check out our pricing page . To get started, use claude-opus-4-5 via the Claude API . Use cases Opus 4.5 is a premium model that works best for use cases no prior model has solved before and where performance matters most. It’s built for professional software engineering, complex agentic workflows, and high-stakes enterprise tasks. Opus 4.5 offers hybrid reasoning that allows for instant responses or extended thinking. API users have fine-grained controls for adjusting the overall effort it puts into a response, balancing performance with latency and cost. Popular use cases include: Advanced coding Opus 4.5 can confidently deliver multi-day software development projects in hours, working independently with the technical depth and taste to create efficient and straightforward solutions. It has improved performance across coding languages, with better planning and architecture choices—making it the ideal model for enterprise developers. In our own testing, it’s even able to pass our most challenging coding interviews. AI agents Opus 4.5, paired with our next wave of tool use improvements, enables more capable agents with new behaviors. It excels at complex, multi-step tasks that require sustained reasoning and adaptive decision-making—ideal for agentic workflows where reliability and autonomy matter most. Enterprise workflows Opus 4.5 can power agents that manage sprawling professional projects from start to finish. It better leverages memory to maintain context and consistency across files, alongside a step-change improvement in creating spreadsheets, slides, and docs. It delivers the sustained quality that ongoing enterprise projects demand. Benchmarks Claude Opus 4.5 is state-of-the-art on tests of real-world software coding and agentic capabilities. Opus 4.5 demonstrates strong performance across many domains. It achieves industry-leading results with 80.9% on SWE-bench Verified. It is also our best computer-using model, reaching 66.3% on OSWorld. Trust and safety Extensive testing and evaluation—conducted in partnership with external experts—ensures the release of Opus 4.5 meets Anthropic’s standards for safety, security, and reliability. The accompanying model card covers safety results in depth. Hear from our customers Opus models have always been “the real SOTA” but have been cost prohibitive in the past. Claude Opus 4.5 is now at a price point where it can be your go-to model for most tasks. It’s the clear winner and exhibits the best frontier task planning and tool calling we’ve seen yet. Jeff Wang CEO Claude Opus 4.5 delivers high-quality code and excels at powering heavy-duty agentic workflows with GitHub Copilot. Early testing shows it surpasses internal coding benchmarks while cutting token usage in half , and is especially well-suited for tasks like code migration and code refactoring. Mario Rodriguez Chief Product Officer Claude Opus 4.5 beats Sonnet 4.5 and competition on our internal benchmarks, using fewer tokens to solve the same problems . At scale, that efficiency compounds. Michele Catasta President Claude Opus 4.5 delivers frontier reasoning within Lovable's chat mode , where users plan and iterate on projects. Its reasoning depth transforms planning—and great planning makes code generation even better. Fabian Hedin CTO & Co-founder Claude Opus 4.5 excels at long-horizon, autonomous tasks , especially those that require sustained reasoning and multi-step execution. In our evaluations it handled complex workflows with fewer dead-ends. On Terminal Bench it delivered a 15% improvement over Sonnet 4.5, a meaningful gain that becomes especially clear when using Warp’s Planning Mode. Zach Lloyd Founder & CEO Claude Opus 4.5 achieved state-of-the-art results for complex enterprise tasks on our benchmarks, outperforming previous models on multi-step reasoning tasks that combine information retrieval, tool use, and deep analysis. Kay Zhu CTO Claude Opus 4.5 delivers measurable gains where it matters most : stronger results on our hardest evaluations and consistent performance through 30-minute autonomous coding sessions. Scott Wu CEO Claude Opus 4.5 represents a breakthrough in self-improving AI agents . For office automation, our agents were able to autonomously refine their own capabilities—achieving peak performance in 4 iterations while other models couldn’t match that quality after 10. Yusuke Kaji General Manager of AI for Business Claude Opus 4.5 is a notable improvement over the prior Claude models inside Cursor , with improved pricing and intelligence on difficult coding tasks. Michael Truell CEO & Co-founder Claude Opus 4.5 is yet another example of Anthropic pushing the frontier of general intelligence . It performs exceedingly well across difficult coding tasks, showcasing long-term goal-directed behavior. Eno Reyes CTO & Co-founder Claude Opus 4.5 delivered an impressive refactor spanning two codebases and three coordinated agents. It was very thorough, helping develop a robust plan, handling the details and fixing tests. A clear step forward from Sonnet 4.5 . Paulo Arruda Staff Engineer, AI Productivity Claude Opus 4.5 handles long-horizon coding tasks more efficiently than any model we’ve tested . It achieves higher pass rates on held-out tests while using up to 65% fewer tokens, giving developers real cost control without sacrificing quality. Sean Ward CEO & Co-founder We’ve found that Opus 4.5 excels at interpreting what users actually want, producing shareable content on the first try . Combined with its speed, token efficiency, and surprisingly low cost, it’s the first time we’re making Opus available in Notion Agent. Sarah Sachs AI Lead Engineer Claude Opus 4.5 excels at long-context storytelling , generating 10-15 page chapters with strong organization and consistency. It's unlocked use cases we couldn't reliably deliver before. Djay Lee CPO & Co-founder Claude Opus 4.5 sets a new standard for Excel automation and financial modeling . Accuracy on our internal evals improved 20%, efficiency rose 15%, and complex tasks that once seemed out of reach became achievable. Nico Christie Co-founder Claude Opus 4.5 is the only model that nails some of our hardest 3D visualizations . Polished design, tasteful UX, and excellent planning & orchestration - all with more efficient token usage. Tasks that took previous models 2 hours now take thirty minutes. Madhav Jha CTO Claude Opus 4.5 catches more issues in code reviews without sacrificing precision . For production code review at scale, that reliability matters. David Loker Director of AI Based on testing with Junie, our coding agent, Claude Opus 4.5 outperforms Sonnet 4.5 across all benchmarks . It requires fewer steps to solve tasks and uses fewer tokens as a result. This indicates that the new model is more precise and follows instructions more effectively — a direction we’re very excited about. Andrew Zakonov VP of Business, Junie & Kineto The effort parameter is brilliant. Claude Opus 4.5 feels dynamic rather than overthinking , and at lower effort delivers the same quality we need while being dramatically more efficient. That control is exactly what our SQL workflows demand. AJ Orbach CEO & Co-founder We’re seeing 50% to 75% reductions in both tool calling errors and build/lint errors with Claude Opus 4.5 . It consistently finishes complex tasks in fewer iterations with more reliable execution. Nicholas Charriere Founder & CEO Claude Opus 4.5 is smooth, with none of the rough edges we've seen from other frontier models. The speed improvements are remarkable. Quinn Slack CEO 01 / 21 Frequently asked questions When should I use Claude Opus 4.5? We offer Claude models across the spectrum of speed, price, and performance. Opus 4.5 is our most intelligent model to date. We recommend Opus 4.5 for your most demanding use cases where you need frontier intelligence—particularly production-ready code, sophisticated AI agents, and complex document creation. How much does it cost to use Claude Opus 4.5? Pricing depends on how you want to use Opus 4.5. To learn more, check out our pricing page . When should I use extended thinking? Opus 4.5 is both a standard model and a hybrid reasoning model in one. You can pick when you want the model to answer normally and when you want it to use extended thinking. Extended thinking mode is best for use cases where performance and accuracy matter more than latency. It significantly improves response quality for complex reasoning tasks, extended agentic work, multi-step coding projects, and deep research, and the thinking summaries help you understand key aspects of the model’s reasoning process. Products Claude Claude Code Claude in Chrome Claude in Excel Claude in Slack Skills Max plan Team plan Enterprise plan Download app Pricing Log in to Claude Models Opus Sonnet Haiku Solutions AI agents Code modernization Coding Customer support Education Financial services Government Healthcare Life sciences Nonprofits Claude Developer Platform Overview Developer docs Pricing Regional Compliance Amazon Bedrock Google Cloud’s Vertex AI Console login Learn Blog Claude partner network Connectors Courses Customer stories Engineering at Anthropic Events Powered by Claude Service partners Startups program Tutorials Use cases Company Anthropic Careers Economic Futures Research News Responsible Scaling Policy Security and compliance Transparency Help and security Availability Status Support center Terms and policies Privacy policy Consumer health data privacy policy Responsible disclosure policy Terms of service: Commercial Terms of service: Consumer Usage policy © 2025 Anthropic PBC Claude Opus 4.5 \ Anthropic | 2026-01-13T08:47:52 |
https://ruul.io/blog/strategies-to-improve-cash-flow-for-freelancers | Strategies to improve cash flow for freelancers - Ruul Product Payment Requests Get paid anywhere. Sell Services Make your services buyable Sell Products Create once sell forever Subscriptions Get paid on repeat Ruul Space Your personel storefront. One link for everything you offer. Learn more Pricing Resources Partner Programs Referral Program Get 1% for life. Seriously. Affiliate Program Bring users, get paid Partners Let’s grow together. More Blog About us Support Brand Kit For Customers Log in Sign up For Businesses Login Sign up work Strategies to improve cash flow for freelancers Discover effective strategies to boost cash flow for freelancers. Manage finances, secure payments, and thrive financially! Canan Başer 5 min read RUUL FOR INDEPENDENCE You chose independence.We make sure you keep it. Sell your time, your talent, whatever you create or build always on your terms. Get started See Example This is also a heading This is a heading Key Points Making sure that you have money in your pocket should be priorities one, two, and three when you work as a freelancer. The problem is that all the responsibility for dealing with customers, sending invoices, chasing down payments, managing budgets, and more falls on your shoulders.For many people, being their own boss is the main benefit of freelance work, but it can be daunting for others. Inconsistent clients, irregular pay, and slow periods are all things that can derail your finances. That's why this guide will give you the tips necessary to manage and improve your cash flow. How important is cash flow for a freelancer? Cash flow is the movement of money in and out of your company or wallet. When you’re self-employed, you often don’t have the luxury of regular pay. That means you need to strategize ways to keep more money coming in than out. Failing to do so will see your business struggle to stay afloat.Managing your cash flow will ensure: Growing your business Staying out of debt Balancing your budget The best cash flow management tips for freelancers Use contracts wisely Using your contract wisely means using it to your advantage. It’s essential to go over the crucial details of a contract to work out important details and negotiate any changes that work in your interests. You should make sure that the contract is mutually benefitting so that you get: fair pay reasonable expectations about the work you’re doing enough time to deliver your services good payment terms You should never feel like you are chained to your contract. Instead, work with your client to draw a contract that both of you feel good about. The contract should be like a map, detailing the important bits of information and avoiding any sort of mistakes or obstacles. It’s always easier to negotiate a contract before the ink is put on paper, so use that time wisely. Set aside money for your estimated taxes It’s important to always set aside money as a freelancer to cover the taxes you will have to pay. Estimated taxes are paid quarterly, and because you are self-employed, you will have to pay a little extra. The tax you’ll be paying is technically tied to Medicare and Social security, something that your employer would split with you 50/50, but since you employ yourself, you pay the whole thing. To cover these costs, you should set aside between 20%-30% of your income at the end of every month or pay period in a separate account that you can use to pay these taxes. Also, there are ways to possibly lessen your tax burden by claiming deductibles for running your own business. This includes things like office supplies and travel expenses. Always keep an eye on cash flow It’s important to always keep an eye on your cash flow when you’re self-employed. Besides obvious tips like budgeting correctly and watching your spending, one way to manage your cash flow is by setting up a cash flow forecast. A cash flow forecast is a system that shows you the money that’s flowing in and out of your business. You can use it: to identify your financial position as a reference for loan applications To keep track of your payment schedule. To do this, you’ll need to keep track of your income streams like sales and rent, and you’ll track your expenditure like material costs and potential travel costs. After you take these into account, then you stay on top of it by constantly responding to changes in your business and adding them to the forecast. It’s a great way to track your finances and plan for the future. Plan ahead for periods of low income As we discussed before, one of the drawbacks of being a freelancer is inconsistent pay. It’s going to happen at some point, so it’s best to have a solution for it before it happens. Save a portion of every bit of income that you earn so that you can create a buffer. One common bit of advice is to create a buffer of 3 months, meaning having enough money set aside to pay for your expenses for 3 months. These funds should keep you afloat during lulls in your business; however, it may be essential to map out potential expenses. If need be, consider cutting expenses that aren’t essential. Do your best to keep up with important payments and find ways to improve your revenue streams. Accurately record all income & expenditure Accurately recording your income and expenditure is one of the most important things you can do as a freelancer. It is mandatory in some instances, such as paying your taxes, but it’s vital for keeping track of your finances and cash flow. You should constantly update your numbers, tracking changes in your income flow as frequently as possible so that you can stay on top of any potential problems. Establish reasonable payment terms Establishing sensible payment terms is a key ingredient in getting paid on time. A common issue that springs up for freelancers is that they find themselves short on cash in the middle of their invoice terms.Imagine having an unexpected expense pop up, but you can’t expect to be paid for another week. That is why you should find and develop reasonable payment terms that see you paid as quickly as possible. Frequently, freelancers have to deal with payment terms of 30, 45, and even 60 days, so negotiating shorter terms is a good step to alleviate these concerns. Other methods you can use include offering discounts on the price if clients pay early or asking for a down payment before work begins. Be sure to clearly state your expectations are and communicate them with your customers.Also, keep track of important information regarding your invoices like: who the client is the price the payment terms project details whether they have paid or not. Analyze data frequently It’s not just important to record and track your finances. You must also analyze your financial data frequently. Digging into your financial records gives you the ability to find shortfalls in your income, unnecessary expenditures, and planning for future business activities. Analyzing your data will allow you to stop ineffective programs, invest more into beneficial ones, and become more surgical when using your money and time.When it’s time to do so, send your invoices early. ALWAYS! There are no real benefits to delaying sending your invoices. Your delay can lead to your client delaying, and you are not getting paid. Even if your customer isn’t trying to take advantage of you, waiting to send the invoice simply means you’re preventing yourself from getting your hard-earned money. The faster you send your bill, the faster you get your money. Simplify payment processes When it comes to payment processes, it’s always in your interest to keep it simple. You always want your clients to have an easy time giving you money, so it literally pays to find a simple way to process payments. Having complicated or messy processes just wastes time and can lead to miscommunications or frustration.That's why it would be best to learn more about Ruul's invoicing and payment features to facilitate the payment flow between you and your clients, receive payments on time, and follow up on your financials. How to increase your cash flow as a freelancer? Now that you’ve found ways to effectively manage your cash flow, we’ll take a look at ways that you can improve it. Train for growth Once you’ve mastered managing your cash flow, the next step that you can take is planning for growth. Knowing the ins and outs of your cash flow is the first step. The next step is being an expert in the business that you’re in.You need to know what your clients expect and what they’re looking for, so you can tailor your business to meet these needs. You want to be the first person your clients think of when they want something, so knowing what they want is key.The next key is to maintain and grow your organizational skills. Don’t get complacent with success. Keeping track of your cash flow will mean that you’re better able to respond to any problems or opportunities that come up. Maintaining a good cash flow and staying organized will make any plans for growth easier. Avoid debt Debt is the horror movie villain lurking behind every corner. One of the most common hurdles that every freelancer must avoid is debt. So, it may seem obvious, but avoiding debt is a great way to improve your cash flow. The key to avoiding debt is to plan and save accordingly. You should always maintain some form of safety net for emergencies that have to be addressed.But, you should also maintain savings for your taxes and extra business expenses. It seems like a lot to handle because it is. That’s why you should consider software programs that can help manage your accounts or look for professional accountants.Once you know your cash flow, you can suss out potential problems long before they cause serious harm. By saving appropriately and looking to cut any extra expenses, you’ll be well on your way to avoiding debt. Track your spending Tracking your spending is the glue that holds all these bits of advice together. It’s the main way that you can assess your business and where it stands. You should always be asking yourself, “What’s my spending like?” and “How much do I need to make a profit?”. The only way to answer these questions is by following the money flow in and out of your accounts.When you understand how much you are spending, you can decide to raise your rates or cut down on certain expenses. If you want to improve your cash flow, then you have to know it like the back of your hand. FAQs What are some early signs of cash flow problems? Some signs of cash flow problems can include: Delays in receiving your payments It’s always a hassle to chase people down for money but not appropriately handling your invoices is one sure sign that you’re going to have future cash flow problems. Running out of capital There’s the saying that you need to spend money to make money, and while some people believe it too much, there is some truth to it. You need the assets on hand to fund your business’s growth or to handle unexpected expenses. Growing debt Growing debt means that you are not making enough profits to sustain your business. While some debt should be expected, continued debt is a sign that you should assess what’s going on in your finances. Slowing down business sales When your business slows down, it can be hard to pinpoint the exact reason why. It could be the economy, a lack of exposure, bad pricing, or just the holidays. You need to be able to find whatever it is that’s causing this problem and adjust.When business is slow, you should change your strategy and market your services to new clients as a freelancer. If you want to learn how to market your freelance business, check out the article here. What is the difference between net income and cash flow? Net income is the profit that you and your business have earned over a certain period, but cash flow is the measure of the money flowing in and out of your business on a day-to-day business. So your net income is how much money you get to pocket, while the cash flow looks more like your operating activities. Why is cash flow important for my business? The cash flow of your business is important because it is one of the best ways to measure the financial health of your business. Usually, when more cash flows in than out, it’s good. Having a good grasp of your cash flow can help you navigate the ups and downs of your business by giving you the means to make sound plans. What is after-tax cash flow? According to Investopedia, “Cash flow after taxes (CFAT) is a measure of financial performance that shows a company's ability to generate cash flow through its operations. It is calculated by adding back non-cash charges such as amortization, depreciation, restructuring costs, and impairment to net income.” How do I do a cash flow forecast? First, you need to set a period that you want to measure such as a month. Next list all possible forms of income that you can find: sales, rent, loans, or investments. Then take all the expenses that you can find such as operating costs, travel, or paying off debt.Finally, take the costs and subtract them from your income to get the result (income-costs) and chart them for the time measure that you want. So for one month, you could break it down into weekly snapshots of your forecast. This is a good and simple way to create a forecast. What is levered free cash flow? Levered free cash flow or “LFCF” is the measure of how much money you have after paying off all your financial obligations. So, looking back at our forecast, it’s the money you get from taking your expenditures from your income. What happens when cash flow is negative? Negative cash flow means you are spending more money on your business than it is making. While having a negative cash flow may sound scary sometimes it should be expected when first starting as you work your way to earning profits.Often it can be just a temporary imbalance caused by something like a significant expenditure or adjusting prices. But continued negative cash flow is a sign that you can find ways to manage your business’s assets better and look for ways to improve your business’s cash flow. ABOUT THE AUTHOR Canan Başer Developing and implementing creative growth strategies. At Ruul, I focus on strengthening our brand and delivering real value to our global community through impactful content and marketing projects. More 25 Financial Terms Every Freelancer and Employee Needs to Know The Foundation of financial literacy is knowing basic financial terms. This piece looks into 25 every freelancer and employee needs to know. Read more What are Traditional Payment Methods for Freelancers? Curious about how freelancers get paid? Discover the most reliable traditional payment methods and why they remain a top choice for many! Read more What does “YOLO economy” stand for? Discover how the YOLO Economy is reshaping work culture as young professionals prioritize flexible, impact entrepreneurship on the labor market, purposeful careers over traditional jobs. Read more MORE THAN 120,000 Independents Over 120,000 independents trust Ruul to sell their services, digital products, and securely manage their payments. FROM 190 Countries Truly global coverage: trusted across 190 countries with seamless payouts available in 140 currencies. PROCESSED $200m+ of Transactions Over $200M successfully processed, backed by an 8-year legacy of secure, reliable transactions trusted by independents worldwide. FREQUENTLY ASKED QUESTIONS Everything you need to know. Get clear, straightforward answers to the most common questions about using Ruul. hey@ruul.io What is Ruul? Ruul is a merchant-of-record platform helping freelancers and creators globally sell services, digital products, subscriptions, and easily get paid. Who is Ruul for? Ruul is designed for freelancers, creators, and independent professionals who want a simple way to sell online and get paid globally. How does Ruul work? Open an account, complete a quick verification (KYC), and link your payout account. Then, start selling through your store or send payment requests to customers instantly. How does pricing work? Signing up is free. There are no subscription or hidden fees. Ruul charges a small commission only when you sell or get paid through the platform. What is a Merchant of Record? A merchant of record is the legal seller responsible for processing payments, handling taxes, and managing compliance for each transaction. What can I sell on Ruul? You can sell services, digital products, license keys, online courses, subscriptions, and digital memberships. How do I get paid on Ruul? Add your preferred bank account, digital wallet, or receive payouts in stablecoins as crypto. Funds arrive within 24 hours after a payout is triggered. OPEN AN ACCOUNT START MAKING MONEY TODAY ruul.space/ Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Trustpilot Product Payment Requests Sell Services Sell Products Subscriptions Ruul Space Pricing For Businesses Resources Blog About Contact Support Referral Program Affiliate Program Partner Program Tools Invoice Generator NDA Generator Service Agreement Generator Freelancer Hourly Rate Calculator All Rights Reserved © 2025 Terms Of Use Privacy Policy | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netflix/?f=flair_name%3A%22Recommendation%22 | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://claude.com/solutions/nonprofits | Nonprofits | Claude -------> Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Solutions Solutions / Nonprofits Explore here Ask questions about this page Copy as markdown Accelerate the work that matters most Claude helps nonprofits turn limited resources into lasting impact. Generate grant proposals in hours, track program outcomes across hundreds of participants, and free your team to focus on serving your community. Get started Get started Get started "At a time when AI could divide or unite communities, we're choosing to lead with our values—using Claude to strengthen human connection and advance wellbeing for all communities." Carlos Sanvee, World YMCA Secretary General "With global health funding shrinking, smart targeting is essential. Claude helped us build an interactive geospatial tool in three days versus weeks, mapping at-risk populations to identify where Guatemala's Ministry of Health could most cost-effectively deploy dengue prevention." Justin Cohen, VP Malaria & NTDs "Claude enables 4× faster implementation, helping MyFriendBen connect families to unclaimed benefits and tax credits. Our Claude-powered agents track up to 40+ programs per state, identifying over $1.2 billion in value for 70,000+ households." Sekhar Paladugu, CEO "With AWS and Claude, we built Sage—an AI companion trained on 25,000+ pages of epilepsy expertise, now available 24/7 in 5 languages to 3.4 million Americans living with epilepsy. It embodies our promise that no one should ever have to face epilepsy alone." David Jost, Chief Technology Operations Officer "With Claude Enterprise, we're equipping teams to work more efficiently—from streamlining data analysis to accelerating support for local partners building lasting, community-led solutions to humanitarian crises." Jeannie Annan, Chief Research & Innovation Officer "With more than 2 million New Yorkers living in poverty, we and our partners need to move at the speed of crisis. Claude helps us build that muscle—to move through grant recommendations more efficiently and to direct resources where they'll make the greatest difference when every day matters." Matt Klein, Chief Program & Impact Officer "IDinsight helps global development leaders use data and evidence to maximize social impact. With Claude, our teams get surveys field-ready 16× faster, prototype dashboards in hours instead of weeks, and draft documentation 5× faster—spending less time on tedious tasks and more time driving impact that matters." Rob Sampson, Senior Director of Transformation "We've deployed Claude across strategic finance—lease analysis, reporting, reconciliations, audit summarization. Claude excels at strategic analysis compared to other LLMs, making it uniquely suited to our mission-critical work." Rebecca Glover, Global Director, Finance "From tracking financial services pricing across 18 countries to helping ministries in Rwanda, Peru, and the Philippines make sense of siloed data, Claude is integral to how we support governments in delivering more impactful services to their citizens." Niall Keleher, Senior Director of Global Research and Data Science "SkillUp is building complex AI systems a normal company would need 20+ engineers for. Claude Code helps level the playing field for organizations that must be efficient, allowing them to build more with the team theywe have." Steve Lee, CEO "Our partnership with Anthropic has enabled our team and grantees to use AI to better understand the impacts of our grants, get more done faster, and explore new ways to tell our story to donors and the community." Andrew Dayton, Founder and CEO Prev Prev 0 / 5 Next Next Made for mission-driven work Enterprise AI at nonprofit pricing Choose from the Claude Team and Enterprise plans at rates built for nonprofit budgets. Plans include collaborative workspaces, advanced permissions, and enterprise-grade security. Built for your workflows Claude connects directly to the platforms you rely on, like Blackbaud, Benevity, and Candid. Pull donor data, generate reports, and research foundations without switching systems. Security for sensitive work We offer plans that are configurable to meet SOC 2 Type II, ISO 27001, ISO 42001, and CSA Star compliance needs. AI Fluency for your whole team Our free AI Fluency for nonprofits course helps every team member, from executive directors to program coordinators, use AI confidently. Learn more Learn more Learn more Prev Prev Next Next How nonprofits use Claude Grantwriting Fundraising Program design Volunteer management Data visualization Active View prompt View prompt View prompt Prompt Generate a proposal for a youth innovation grant ($75,000). Include an executive summary, problem statement with community data, program approach, budget narrative, and evaluation metrics. Emphasize “innovation” and “youth voice” to align with funder priorities. Attachments Community needs data 850 KB PDF Program budget 52 kb CSV Youth Innovation Lab Empowering young people as architects of community change Proposal to the Westbrook Foundation Youth Innovation Grant Program Requested amount: $75,000 Submitted by: Community Pathways Initiative 123 Community Drive, Metro City, ST 12345 Contact: Maria Rodriguez, Executive Director [email protected] | (555) 234-5678 March 15, 2025 Executive summary Community Pathways Initiative requests $75,000 from the Westbrook Foundation to launch the Youth Innovation Lab —a transformative program empowering 150 young people ages 14-19 to design and deploy community solutions using human-centered design and emerging technologies. Metro County youth face compounding barriers: 42% unemployment among 16-19 year olds, 67% lacking reliable technology access, and limited pathways to leadership. Yet these same young people possess intimate knowledge of their communities and untapped capacity for innovation. The Youth Innovation Lab transforms this potential into action. Our youth-driven model distinguishes this program from traditional youth services. Participants don't simply receive programming—they design it. Youth hold 50% of advisory committee seats, co-facilitate workshops, and make decisions about resource allocation. Over nine intensive months, they progress from community researchers to solution architects to change agents. Innovation is embedded throughout: Youth learn ethnographic research methods, prototype with 3D printers and digital tools, and iterate solutions based on community feedback. Last year's pilot yielded twelve youth-designed projects including a multilingual resource app and peer mental health platform—concrete innovations addressing real needs. With Westbrook Foundation support, we will scale this proven approach, engage diverse youth populations, and create a replicable model demonstrating that young people aren't just the future—they're essential partners in solving today's challenges. Problem statement: The youth opportunity crisis The compounding challenge Metro County's young people stand at a critical juncture where economic, educational, and social barriers converge to limit their potential and silence their voices. The data paints a stark picture: Bureau of Labor Statistics reports 42% unemployment among 16-19 year olds—triple the adult rate and the highest in our region's history. This isn't simply an employment problem; it's a symptom of systemic exclusion from opportunity pathways. The Metro Digital Equity Study (2024) reveals that 67% of low-income youth lack reliable internet access at home. In an increasingly digital economy, this gap doesn't just limit homework completion—it excludes young people from the tools, platforms, and networks that drive modern innovation. Perhaps most troubling is the leadership vacuum. Our Youth Voice Survey (n=450) found that 78% of young people desire leadership opportunities but see no viable pathways in their communities. The cycle of exclusion These barriers create a devastating cycle. Without early exposure to problem-solving methodologies, technology tools, and professional networks, young people enter adulthood without competitive advantages. They lack professional soft skills, technical competencies, social capital, and a sense of agency that comes from seeing their ideas valued and implemented. The innovation imperative What's needed isn't another youth program—it's a fundamental shift in how we engage young people. Stanford Social Innovation Review's recent analysis found that youth-led initiatives achieve 47% higher community adoption rates than adult-designed programs addressing identical issues. Proposed program: The Youth Innovation Lab Program overview The Youth Innovation Lab is a nine-month intensive program that positions 150 diverse young people ages 14-19 as community innovators. Through rigorous training in design thinking, technology tools, and collaborative problem-solving, participants identify pressing neighborhood challenges and develop evidence-based solutions. Three-phase curriculum Phase 1: Discovery (Months 1-3) — Youth become community researchers, learning ethnographic methods to deeply understand neighborhood challenges. Activities include conducting resident interviews, asset mapping, data visualization workshops, and ethics training. Phase 2: Design (Months 4-6) — Armed with community insights, youth enter our Innovation Studio equipped with 3D printers, coding workstations, and digital fabrication tools. Using human-centered design principles, they generate and test solution concepts with mentor guidance. Phase 3: Deployment (Months 7-9) — Solutions move from prototype to implementation. Youth pilot solutions with community partners, collect impact data, iterate based on testing, and present at the annual Community Solutions Showcase. Innovation through youth governance Central to our approach is the Youth Advisory Committee, where participants hold 50% of seats on the program governance body. Youth voice directly shapes curriculum modifications, mentor selection, resource allocation, and community partnership development. Budget narrative The requested $75,000 represents a strategic investment in youth capacity-building, with 78% of funds supporting direct program delivery. Personnel: $32,500 (43% of total) Fringe benefits: $8,125 (11% of total) Technology & supplies: $11,500 ($15 of total) Participant stipends: $13,500 (18% of total) Indirect costs: $9,375 (13% of total) Total request: $75,000 Personnel (43%): Includes 0.5 FTE Program Director providing strategic oversight and 1.0 FTE Program Coordinator managing daily operations. Participant stipends (18%): Youth receive $200 stipends recognizing their labor as community researchers and innovators. Evaluation plan Our evaluation framework measures both individual youth development and community-level impact. Theory of change If we provide young people with design thinking skills, technology tools, mentorship, and authentic decision-making power, then they will develop agency, technical competencies, and community connections that translate to academic success and career readiness. Outcome metrics Program completion: 90% of enrolled youth complete all three phases Leadership development: 85% report increased confidence in problem-solving abilities Technical skill acquisition: 80% demonstrate proficiency in design thinking methodology Community impact: Minimum 10 youth-designed solutions advance to implementation Long-term pathways: 70% of graduates pursue STEM, social innovation, or civic engagement within 12 months Conclusion The Youth Innovation Lab represents more than a program—it's an investment in redefining how communities engage their youngest members. With Westbrook Foundation support, we will demonstrate that young people aren't problems to be solved but essential partners in building more resilient, innovative, and equitable communities. We welcome the opportunity to discuss this proposal further and thank the Westbrook Foundation for considering this partnership in youth-driven community innovation. Grant proposals Draft foundation proposals in hours instead of days. Claude pulls from your existing content, customizes language to funder priorities, and creates budgets, logic models, and evaluation plans. Learn more Learn more Learn more View prompt View prompt View prompt Prompt Create a year-end fundraising campaign strategy document for a marine conservation nonprofit. Include donor segmentation (4 tiers from $25 to $5,000+), a 47-day multi-channel timeline, messaging framework, and success metrics. Attachments Donor Database 84kb TXT Fundraising Data 2024 and 2025 13,203 lines MD Protect our oceans 2025 Year-end fundraising campaign strategy Ocean Guardians Alliance November 15 – December 31, 2025 Campaign overview This 47-day year-end campaign aims to raise $500,000 to establish three new marine sanctuaries and fund 50 youth education programs. Through coordinated multi-channel outreach across email, social media, direct mail, and personal engagement, we will mobilize our donor community across four strategically segmented giving tiers. Campaign goal: $500,000 Duration: 47 days (Nov 15 – Dec 31, 2025) Impact goals: 3 marine sanctuaries | 50 youth education programs Donor segments: 4 strategic tiers (Major, Sustaining, Engaged, Emerging) Donor segmentation strategy Our donor base is strategically segmented into four tiers, each requiring tailored messaging, touchpoints, and cultivation strategies. Segment 1: Major donors ($5,000+) Profile: 23 donors, lifetime giving $250K+, personal relationships with Executive Director Approach: Personal outreach via phone and meetings, exclusive impact briefings, recognition opportunities Target: $150,000 (30% of campaign goal) Communication frequency: 6 personalized touches over 47 days Segment 2: Sustaining champions ($1,000–$4,999) Profile: 87 donors, monthly or annual giving patterns, highly engaged with mission Approach: Video content, behind-the-scenes updates, exclusive donor community events Target: $175,000 (35% of campaign goal) Communication frequency: 8–10 touches via email, direct mail, and digital content Segment 3: Engaged supporters ($250–$999) Profile: 342 donors, event attendees, social media followers, volunteer base Approach: Email sequences, social campaigns, matching gift challenges, peer-to-peer fundraising Target: $100,000 (20% of campaign goal) Communication frequency: 10–12 touches via email and social media Segment 4: New & emerging donors ($25–$249) Profile: 1,200+ prospects, newsletter subscribers, first-time or small-amount givers Approach: Compelling storytelling, low-barrier entry points, social proof, easy giving mechanisms Target: $75,000 (15% of campaign goal) Communication frequency: 12–15 touches emphasizing accessibility and impact Multi-channel campaign timeline Phase 1: Pre-launch (Nov 1–14) Finalize board member commitments and matching gift pledges Complete content production (videos, testimonials, impact stories) Email list segmentation and campaign page preparation Phase 2: Launch week (Nov 15–21) Major donor personal outreach and cultivation meetings Launch email sequence to all donor segments Social media campaign kickoff with #ProtectOurOceans2025 Press release distribution and media outreach Phase 3: Giving Tuesday peak (Nov 26 – Dec 3) 24-hour social media blitz across all platforms Email intensification with matching gift emphasis Real-time progress updates and impact storytelling Influencer and partner activations Phase 4: Mid-campaign momentum (Dec 4–20) Weekly impact story series featuring program beneficiaries Sustaining donor cultivation and upgrade conversations Social proof campaigns highlighting donor testimonials Challenge grant announcements and corporate partnership news Phase 5: Final sprint (Dec 21–31) Daily countdown communications across all channels Last-chance matching gift messaging and tax benefit reminders Year-end urgency messaging with real-time goal tracker Personal calls to top 50 prospects Messaging framework Core narrative "Every wave begins with a single drop. Your gift protects the oceans that sustain all life on Earth—from the smallest plankton to the communities that depend on healthy marine ecosystems." Key messages by segment Major donors: Legacy impact, transformational change, thought partnership, leadership role Sustaining champions: Reliable foundation, multiplied impact, community of leaders, consistent support Engaged supporters: Tangible outcomes, accessible impact, shared mission, collective action New donors: Easy entry, immediate difference, joining a movement, meaningful participation Multi-channel strategy Email (primary channel) 8–12 touches per segment over 47 days Personalized subject lines and dynamic content blocks Mobile-optimized visual storytelling Simplified giving process with single-click donations Social media (amplification) Daily posts across Instagram, Facebook, Twitter/X, LinkedIn Video content 3x weekly featuring program beneficiaries User-generated content campaigns with #ProtectOurOceans2025 Influencer partnerships with marine biologists and ocean athletes Direct mail (high-touch segment) Personalized letters to Major Donors and Sustaining Champions Premium photography and materials reflecting mission values Handwritten notes from Executive Director and Program Director Success metrics & goals Total raised: $500,000 Average gift increase: 15% year-over-year growth New donor acquisition: 200+ new donors Recurring gift conversions: 50+ new monthly donors Email open rate: 35%+ (above nonprofit average of 25%) Email click-through rate: 8%+ (above nonprofit average of 2.5%) Social media reach: 100,000+ impressions Post-campaign stewardship plan Immediate actions (Jan 1–15, 2026) Final campaign results announcement via email and social media Thank-you video from ED and program beneficiaries Tax receipts and personalized acknowledgment letters (100% within 48 hours) Personal thank-you calls to all $1,000+ donors Short-term follow-up (Jan 16 – Mar 31, 2026) Donor feedback survey on campaign experience First impact update with photos and stories from funded programs Recognition on website donor wall and in newsletter Strategic planning for next campaign cycle Long-term engagement (Apr – Dec 2026) Quarterly impact reports with detailed program outcomes Site visit opportunities for major donors to see sanctuaries Invitation to annual ocean conservation gala Retention and upgrade cultivation strategy Together, we protect the oceans that sustain all life. Ocean Guardians Alliance | oceanguardians.org Fundraising campaigns Build complete year-end campaigns with donor segmentation, email sequences, and thank-you templates. Track performance across channels to see which investments drive the best returns. Learn more Learn more Learn more Program design Develop complete program frameworks with logic models, evaluation plans, and resource guides. Transform concepts into implementation-ready documentation that demonstrates strategic thinking to funders. Learn more Learn more Learn more View prompt View prompt View prompt Prompt Create a Word document with volunteer role descriptions for a literacy nonprofit. Include 4 roles: Reading tutors (one-on-one weekly sessions), reading buddies (small group reading circles), event coordinators (book fairs and literacy events), and administrative volunteers (data entry, scheduling, communications). For each role, include purpose, key responsibilities, time commitment, location, training requirements, and ideal qualifications. Attachments Program overview 14 kb PDF Volunteer data 45 rows csv Volunteer role descriptions Reading tutor Role purpose: Provide one-on-one literacy instruction to elementary students, helping them develop reading skills and confidence through personalized, weekly tutoring sessions. Key responsibilities Conduct 45-60 minute individual tutoring sessions weekly with assigned student Assess student reading level and select appropriate books and materials Use evidence-based reading instruction techniques learned in training Track student progress and document each session Communicate regularly with Program Coordinator about student development Build trusting relationship with student that encourages risk-taking in learning Adapt teaching approach based on student needs and learning style Time commitment: 2-3 hours per week (includes session time and preparation) for minimum one semester (4 months) Location: Partner elementary schools (Lincoln Elementary, Washington Elementary, or Jefferson Elementary) Schedule: Flexible within school hours (typically 2:30-4:00 PM, Mon-Fri) Training required: General orientation (3 hours) + Reading Tutor training (4 hours) + 2 supervised practice sessions Background check: Required (provided and paid for by ReadBright, takes 3-5 business days) Qualifications High school diploma or equivalent Love of reading and belief in its power to transform lives Patience and enthusiasm working with children ages 6-11 Reliable transportation to school sites Ability to commit to consistent weekly schedule for full semester No prior teaching experience required - we provide full training Benefits of volunteering Direct, measurable impact on child literacy and academic success Develop valuable teaching and mentoring skills Flexible schedule that fits your availability Supportive community of fellow volunteers and staff Training in evidence-based reading instruction Personal satisfaction of transforming a young life Reference letters available for students, job seekers, or career changers Reading buddy Role purpose: Lead small group reading circles (3-5 students) that make reading fun, build community, and develop comprehension skills through discussion and shared reading activities. Key responsibilities Facilitate weekly 45-minute small group reading circle with 3-5 students Select age-appropriate, engaging books that spark discussion and imagination Guide group discussions using comprehension questions and reading strategies Create inclusive environment where all students feel comfortable participating Plan and lead related activities (art projects, vocabulary games, creative writing) Track attendance and document group dynamics and student engagement Foster positive peer interactions and model respectful communication Time commitment: 2 hours per week (includes session and prep time) for minimum one semester Group size: 3-5 students (mixed or similar reading levels depending on group goals) Location: Partner elementary schools in dedicated reading circle spaces Schedule: Flexible weekly times (typically after school 2:30-4:00 PM) Training required: General orientation (3 hours) + Reading Buddy training (2 hours) + observed practice session Ideal for People who love facilitating discussions and group dynamics Those who want to inspire love of reading through shared experience Volunteers comfortable managing multiple students simultaneously Anyone who enjoys creative activity planning around books Event coordinator Role purpose: Plan and execute literacy events, book fairs, and community programs that celebrate reading and engage families in literacy development. Key responsibilities Plan and coordinate quarterly book fairs at partner schools Organize annual Read-A-Thon fundraiser and community literacy celebration Recruit and manage event-day volunteers Coordinate with school staff, vendors, and community partners Manage event budgets and track expenses Set up and break down event spaces Create promotional materials and communicate event details Evaluate event success and gather feedback for improvement Time commitment: 4-6 hours per week (varies by event cycle - heavier before events, lighter between) Event types: Book fairs, Read-A-Thon, family literacy nights, author visits, volunteer appreciation Planning timeline: Events planned 6-8 weeks in advance with weekly check-ins Team structure: Work with 2-3 other coordinators plus Program Director Training required: General orientation (3 hours) + Event Coordinator training (3 hours) + shadow one full event Ideal qualifications Strong organizational and project management skills Experience coordinating events or managing volunteers (preferred but not required) Comfortable with budget tracking and vendor communication Creative problem-solving abilities Excellent communication skills Flexibility to attend some weekend or evening events (scheduled months in advance) Administrative volunteer Role purpose: Provide essential behind-the-scenes support through data entry, scheduling, donor communications, and office tasks that keep ReadBright running smoothly. Key responsibilities (choose your focus area) Database management Enter and update volunteer information in database Track volunteer hours and generate monthly reports Maintain student records and progress documentation Create mailing lists and distribution groups Ensure data accuracy and completeness Scheduling coordination Match volunteers with students based on availability and needs Send training and session reminders to volunteers Coordinate substitute coverage when volunteers are absent Manage school calendar and communicate schedule changes Track attendance and follow up on missed sessions Donor communications Draft thank you letters for donations Prepare donor impact reports with program statistics Update mailing addresses and contact information Assist with fundraising campaign materials Track in-kind donations and volunteer hour values Time commitment: 3-5 hours per week, flexible schedule (remote work possible for some tasks) Location: ReadBright office or remote (depending on task) Schedule: Flexible within business hours (9 AM - 5 PM, Mon-Fri) Training required: General orientation (3 hours) + Administrative Systems training (2 hours) + role-specific coaching Skills needed Proficiency with computers and common software (Microsoft Office, Google Workspace) Strong attention to detail and data accuracy Ability to maintain confidentiality with sensitive information Good written communication skills Organizational skills and ability to meet deadlines Comfortable learning new database and scheduling systems Ideal for Retirees with professional administrative experience People who prefer behind-the-scenes support roles Those seeking remote volunteer opportunities Individuals with limited availability who want to make an impact Anyone who loves systems, organization, and data Volunteer management Generate role descriptions, onboarding guides, and hour tracking systems in one conversation. Build recruitment materials and recognition messages that scale with you. Learn more Learn more Learn more Data visualization Transform satisfaction surveys and program statistics into board presentations. Analyze participation patterns and outcome measurements across quarters. Learn more Learn more Learn more Claude connects to your tools Work across your donor database, productivity suite, and research tools all in one place. Explore connectors Explore connectors Explore connectors AI Fluency for nonprofits This free course will help anyone on your team feel confident with AI. No technical background required. View course View course View course Play video Play video Get started with Claude If your organization has fewer than 20 people, get started by verifying your nonprofit status with our partner Goodstack. For larger organizations, reach out to our sales team. Team For organizations purchasing fewer than 20 seats $8 /user/month Verify with Goodstack Verify with Goodstack Verify with Goodstack Nonprofit connectors Single sign-on (SSO) and domain capture Access to file creation (docs, slides, spreadsheets, and PDFs) Central billing and administration Nonprofit guides and docs Minimum 5 seats Enterprise For organizations operating at scale Contact sales Contact sales Contact sales Everything in Pro, plus: More usage* Enhanced context window Compliance API for observability and monitoring Single sign-on (SSO) and domain capture System for Cross-domain Identity Management (SCIM) Custom data retention controls *Additional usage limits apply. Prices shown don’t include applicable tax. More resources Brian Impact Foundation powers their search for the next generation of social innovators with Claude Brian Impact Foundation powers their search for the next generation of social innovators with Claude Brian Impact Foundation powers their search for the next generation of social innovators with Claude Case study Case study Case study The Patrick J. McGovern Foundation standardizes grant evaluation with Claude The Patrick J. McGovern Foundation standardizes grant evaluation with Claude The Patrick J. McGovern Foundation standardizes grant evaluation with Claude Case study Case study Case study Rising Academies’ chatbot tutors reach 150,000+ students across Sub-Saharan Africa with Claude Rising Academies’ chatbot tutors reach 150,000+ students across Sub-Saharan Africa with Claude Rising Academies’ chatbot tutors reach 150,000+ students across Sub-Saharan Africa with Claude Case study Case study Case study Homepage Homepage Next Next Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Write Button Text Button Text Learn Button Text Button Text Code Button Text Button Text Write Help me develop a unique voice for an audience Hi Claude! Could you help me develop a unique voice for an audience? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Improve my writing style Hi Claude! Could you improve my writing style? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Brainstorm creative ideas Hi Claude! Could you brainstorm creative ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Learn Explain a complex topic simply Hi Claude! Could you explain a complex topic simply? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Help me make sense of these ideas Hi Claude! Could you help me make sense of these ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Prepare for an exam or interview Hi Claude! Could you prepare for an exam or interview? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Code Explain a programming concept Hi Claude! Could you explain a programming concept? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Look over my code and give me tips Hi Claude! Could you look over my code and give me tips? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Vibe code with me Hi Claude! Could you vibe code with me? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! More Write case studies This is another test Write grant proposals Hi Claude! Could you write grant proposals? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to — like Google Drive, web search, etc. — if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can - an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Write video scripts this is a test Anthropic Anthropic © [year] Anthropic PBC Products Claude Claude Claude Claude Code Claude Code Claude Code Max plan Max plan Max plan Team plan Team plan Team plan Enterprise plan Enterprise plan Enterprise plan Download app Download app Download app Pricing Pricing Pricing Log in Log in Log in Features Claude in Chrome Claude in Chrome Claude in Chrome Claude in Slack Claude in Slack Claude in Slack Claude in Excel Claude in Excel Claude in Excel Skills Skills Skills Models Opus Opus Opus Sonnet Sonnet Sonnet Haiku Haiku Haiku Solutions AI agents AI agents AI agents Code modernization Code modernization Code modernization Coding Coding Coding Customer support Customer support Customer support Education Education Education Financial services Financial services Financial services Government Government Government Healthcare Healthcare Healthcare Life sciences Life sciences Life sciences Nonprofits Nonprofits Nonprofits Claude Developer Platform Overview Overview Overview Developer docs Developer docs Developer docs Pricing Pricing Pricing Regional Compliance Regional Compliance Regional Compliance Amazon Bedrock Amazon Bedrock Amazon Bedrock Google Cloud’s Vertex AI Google Cloud’s Vertex AI Google Cloud’s Vertex AI Console login Console login Console login Learn Blog <a class="clickable_link w-inline-block" data-wf-component-context="%5B%7B%22componentId%22%3A%22759f53cb-5b4b-89cf-d1a6-4d21b1b92b2e%22%2C%22instanceId%22%3A%22904c9b00-d366-acc0-29ec-f33b281a0956%22%7D%2C%7B%22componentId%22%3A%2284512419-220f-283b-ae01-195dde253845%22%2C%22instanceId%22%3A%22254d70fe-9fc2-4a04-c2e3-76dab742479c%22%7D%2C%7B%22componentId%22%3A%220254e612-9509-0757-3332-f6be61ca6889%22%2C%22instanceId%22%3A%2284512419-220f-283b-ae01-195dde253848%22%7D%5D" data-wf-element-id="0254e612-9509-0757-3332-f6be61ca688a" data-cta-position="" data-wf-event-ids="" href="/blog" data-cta="" target="" data-cta-copy="" data-wf-native-id-path="904c9b00-d366-acc0-29ec-f33b281a0956:254d70fe-9fc2-4a04-c2e3-76dab742479c:84512419-220 | 2026-01-13T08:47:52 |
https://www.youtube.com/ads/ | 온라인 동영상 광고 캠페인 - YouTube 광고 콘텐츠로 이동 YouTube를 선택해야 하는 이유 작동 방식 개요 작동 방식 채널 만들기 채널 시작하기 광고 제작 동영상 광고 제작 캠페인 설정 캠페인 설정하기 잠재고객 찾기 예산 결정 실적 측정 실적을 측정하세요 뉴스 및 아이디어 리소스 개요 리소스 광고 소재 크리에이티브 리소스 크리에이터 크리에이터 프로모션 측정 측정 도구 통계 권장사항 성공사례 FAQ 카카오톡 상담 카카오톡 상담을 시작하기 위해 아이콘을 클릭해주세요 (월-금 9:30 - 18:00) 1-877-763-9810 지금 시작하기 YouTube Ads를 통해 비즈니스 성장을 도모하세요 잠재고객이 시청하는 플랫폼을 통해 도달하여 채널의 주목도를 높이고 비즈니스 성과를 창출해 보세요 광고 시작하기 작동 방식 알아보기 고객에게 다가가고 새로운 고객을 찾으세요 거리 곳곳의 미식가, 전국의 패셔니스타. 온라인상의 더 많은 곳에서 정보를 검색, 탐색하거나 콘텐츠를 시청하는 고객에게 도달하세요. YouTube가 비즈니스에 가장 중요한 사람들과 연결해 줍니다. 천 마디 말보다 한 번 보는 게 더 낫다는 말이 있습니다. 동영상은 백만 마디의 가치가 있습니다. 뇨르드 로타 Majestic Heli Ski 사업주 중요한 순간에 등장하기 예산 규모에 상관없이 시청자를 고객으로 전환하세요. YouTube Ads는 Google 데이터를 사용하여 적절한 순간에 적절한 사용자에게 메시지를 전달합니다. 관련성이 가장 높은 순간에 정확하게 사용자에게 도달할 수 있었습니다. 킴 톰슨, Spark Foundry 원하는 성과를 달성하세요 사람들은 YouTube Ads를 통해 더욱 쉽게 비즈니스를 선택할 수 있습니다. 매출, 구독자 수, 웹사이트 방문자 수 등을 늘려보세요. YouTube에서 광고를 시작한 후로 매출이 매년 거의 두 배씩 성장했습니다. 스테파니 슈베허, Tulane's Closet 소유주 겸 개발자 고객에게 다가가고 새로운 고객을 찾으세요 거리 곳곳의 미식가, 전국의 패셔니스타. 온라인상의 더 많은 곳에서 정보를 검색, 탐색하거나 콘텐츠를 시청하는 고객에게 도달하세요. YouTube가 비즈니스에 가장 중요한 사람들과 연결해 줍니다. 천 마디 말보다 한 번 보는 게 더 낫다는 말이 있습니다. 동영상은 백만 마디의 가치가 있습니다. 뇨르드 로타 Majestic Heli Ski 사업주 중요한 순간에 등장하기 예산 규모에 상관없이 시청자를 고객으로 전환하세요. YouTube Ads는 Google 데이터를 사용하여 적절한 순간에 적절한 사용자에게 메시지를 전달합니다. 관련성이 가장 높은 순간에 정확하게 사용자에게 도달할 수 있었습니다. 킴 톰슨, Spark Foundry 원하는 성과를 달성하세요 사람들은 YouTube Ads를 통해 더욱 쉽게 비즈니스를 선택할 수 있습니다. 매출, 구독자 수, 웹사이트 방문자 수 등을 늘려보세요. YouTube에서 광고를 시작한 후로 매출이 매년 거의 두 배씩 성장했습니다. 스테파니 슈베허, Tulane's Closet 소유주 겸 개발자 2 X 시청자가 YouTube에서 상품을 접한 경우 구매 가능성이 2배 높은 것으로 조사되었습니다. 1 70 % 70%가 넘는 시청자가 YouTube를 통해 새로운 브랜드를 알게 된다고 응답했습니다. 2 4 X 시청자는 브랜드, 제품, 서비스에 대한 정보를 찾을 때 YouTube를 다른 플랫폼에 비해 4배 더 많이 사용합니다. 3 효과적인 광고 제작에 필요한 모든 것 누구나 실적을 높일 수 있는 YouTube 광고를 만들 수 있습니다. 스마트폰에서 바로 동영상을 만들거나 Google에서 제공하는 무료 도구와 리소스를 사용하세요. 도움이 될 완벽한 파트너를 찾을 수도 있습니다. 자세히 알아보기 YouTube 광고 시작하기 지금 시작하기 1 경쟁사 평균 대비. 출처: Google/Talkshoppe, 미국, whyVideo 연구, 응답자 수 2,000명, 만 18~64세 일반 대중 동영상 사용자 대상, 2020년 2월 2, 3 출처: Google/Talkshoppe, 미국, whyVideo 연구, 응답자 수 2,000명, 만 18~64세 일반 대중 동영상 사용자 대상, 2020년 2월 SNS YouTube 소개 정보 블로그 YouTube 작동의 원리 채용정보 보도자료 YouTube Culture & Trends 제품 YouTube Kids YouTube Music YouTube Originals YouTube Podcasts YouTube Premium YouTube Select YouTube Studio YouTube TV 비즈니스 개발자 YouTube 광고 크리에이터 YouTube Kids 콘텐츠 제작 크리에이터 리서치 크리에이터 서비스 디렉토리 YouTube for Artists YouTube Creators YouTube NextUp YouTube VR YouTube의 약속 Creators for Change CSAI Match 사회 공헌 YouTube 소개 제품 비즈니스 크리에이터 YouTube의 약속 정보 블로그 YouTube 작동의 원리 채용정보 보도자료 YouTube Culture & Trends YouTube Kids YouTube Music YouTube Originals YouTube Podcasts YouTube Premium YouTube Select YouTube Studio YouTube TV 개발자 YouTube 광고 YouTube Kids 콘텐츠 제작 크리에이터 리서치 크리에이터 서비스 디렉토리 YouTube for Artists YouTube Creators YouTube NextUp YouTube VR Creators for Change CSAI Match 사회 공헌 정책 및 안전 저작권 브랜드 가이드라인 개인 정보 보호 약관 Cookies management controls 도움말 العربية (الإمارات العربية المتحدة) English español (Argentina) English (Australia) português (Brasil) English (Canada) español (Chile) 中文 (简体, 中国) español (Colombia) Deutsch (Deutschland) español (España) français (France) 中文 (繁體字, 中國香港特別行政區) Bahasa Indonesia (Bahasa Indonesia) עברית (ישראל) English (India) italiano (Italia) 日本語 (日本) 한국어 (대한민국) español (México) Nederlands (Nederland) español (Perú) polski (Polska) русский (Россия) svenska (Sverige) English (Singapore) ไทย (ไทย) Türkçe (Türkiye) 中文 (繁體, 台灣) українська (Україна) English (United Kingdom) Tiếng Việt (Việt Nam) English (UAE) English (China) English (Hong Kong SAR China) English (Bahasa Indonesia) English (Israel) English (Malaysia) English (United States) español (Estados Unidos) français (Canada) हिन्दी (भारत) Melayu (Malaysia) 쿠폰 이용약관: 아래의 이용약관에서 'Google Ads'는 상황에 따라 Google Ads 또는 Google Ads Express를 의미할 수 있습니다. 이 쿠폰은 청구서 수신 주소가 미국 내에 있는 고객만 사용할 수 있습니다. 광고주당 사용할 수 있는 프로모션 코드는 1개로 제한됩니다. 이 쿠폰을 사용하려면 2020년 12월 31일까지 계정에 프로모션 코드를 입력해야 합니다. 이 쿠폰을 사용하려면 첫 Google Ads 계정에서 광고 노출이 처음 발생한 날로부터 14일 이내에 코드를 입력해야 합니다. 크레딧을 받으려면 프로모션 코드를 입력한 후 30일 이내에 광고 캠페인에서 비용이 50달러(세금 제외) 이상 발생해야 합니다. 50달러의 광고비를 결제하는 것만으로는 크레딧을 받을 수 없습니다. 광고비가 50달러 이상 지출되었는지에 대한 추적은 프로모션 코드를 입력한 다음부터 진행됩니다. 2단계와 3단계가 완료되면 보통 5일 이내에 계정의 결제 요약에 크레딧이 반영됩니다. 크레딧은 향후 광고비에만 적용되며, 코드를 입력하기 전에 발생한 비용에는 크레딧이 적용되지 않습니다. 크레딧 금액이 소진될 때 알림이 제공되지 않으며, 추가로 발생하는 광고비는 계정에서 선택한 결제 방법으로 청구됩니다. 광고를 계속하지 않은 경우 언제든지 캠페인을 일시중지하거나 삭제할 수 있습니다. 프로모션 크레딧을 받으려면 Google Ads 청구가 정상적으로 이루어지며 계정이 양호한 상태여야 합니다. 전체 이용약관은 여기에서 확인할 수 있습니다. | 2026-01-13T08:47:52 |
https://www.youtube.com/t/contact_us/ | 문의하기 KR YouTube 정보 커뮤니티 가이드 문의하기 채용정보 문의하기 도움이 필요한 경우 YouTube 고객센터 를 방문하세요. 계정 만들기, 동영상 보기 및 업로드, 채널 관리 등 여러 가지 일반적인 질문에 대한 답을 찾을 수 있습니다. 고객센터에서 원하는 내용을 찾을 수 없는 경우 커뮤니티 도움말 포럼 을 방문해 보세요. 버그가 있습니까? 현재 사이트 관련 문제 페이지에서, 이미 알려진 문제 중 현재 수정 작업이 진행되고 있는 문제의 목록을 살펴보세요. 기업 홍보 프레스룸 이 공간 에서는 미디어 연락처 정보, 보도자료, B-Roll 영상 자료, FAQ, 대화식 YouTube 연혁을 제공합니다. 파트너 프로그램 YouTube 파트너 프로그램에 가입하려면 정보 페이지 를 방문하여 자세한 내용을 확인하세요. 광고 AdAge 100 광고주이든 현지 소매상이든 관계없이 누구나 YouTube 광고 프로그램을 이용하면 전 세계에서 가장 큰 온라인 동영상 커뮤니티를 활용하는 것이 됩니다. YouTube에서 광고를 하는 데 대한 기본사항을 알아보세요 . 보안 악용 문제 사이트에 악용 문제가 있는 경우에는 안전센터 를 통해 문의해 주시기 바랍니다. 사이트 보안 문제 YouTube 사이트와 관련된 보안 문제는 여기에서 신고하실 수 있습니다 . 법적 문제 저작권 문제 내가 저작권을 보유한 동영상이 허락 없이 올라와 있는 것을 발견할 경우 다음 안내 에 따라 저작권 침해 신고를 제출하시기 바랍니다. 콘텐츠 확인 프로그램 콘텐츠 확인 프로그램에 참여하려면 콘텐츠 확인 페이지를 방문하세요. 부적절한 콘텐츠 YouTube에 올라온 부적절한 동영상을 신고하려면 동영상 아래에 있는 '신고' 링크를 클릭하세요. YouTube 정책에 대한 자세한 내용은 서비스 약관을 참조 하시기 바랍니다. 기타 개발자 개발자이거나 Google API에 관심이 있는 경우 개발자 페이지 를 방문하세요. Google에 추가 콘텐츠를 제출하세요. 가젯, 쇼핑, 지역 정보, 도서 등 콘텐츠를 Google에 배포할 수 있는 모든 방법 을 확인하세요. 주소 아래 주소로 YouTube에 연락하실 수 있습니다. Google LLC, D/B/A YouTube 901 Cherry Ave. San Bruno, CA 94066 USA 팩스: +1 650-253-0001 | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netsec/top/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://forem.com/enter?signup_subforem=63&state=new-user | Welcome! - Forem Forem Feed Follow new Subforems to improve your feed DEV Community Follow A space to discuss and keep up software development and manage your software career Future Follow News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Open Forem Follow A general discussion space for the Forem community. If it doesn't have a home elsewhere, it belongs here Gamers Forem Follow An inclusive community for gaming enthusiasts Music Forem Follow From composing and gigging to gear, hot music takes, and everything in between. Vibe Coding Forem Follow Discussing AI software development, and showing off what we're building. Popcorn Movies and TV Follow Movie and TV enthusiasm, criticism and everything in-between. DUMB DEV Community Follow Memes and software development shitposting Design Community Follow Web design, graphic design and everything in-between Security Forem Follow Your central hub for all things security. From ethical hacking and CTFs to GRC and career development, for beginners and pros alike Golf Forem Follow A community of golfers and golfing enthusiasts Crypto Forem Follow A collaborative community for all things Crypto—from Bitcoin to protocol development and DeFi to NFTs and market analysis. Parenting Follow A place for parents to the share the joys, challenges, and wisdom that come from raising kids. We're here for them and for each other. Forem Core Follow Discussing the core forem open source software project — features, bugs, performance, self-hosting. Maker Forem Follow A community for makers, hobbyists, and professionals to discuss Arduino, Raspberry Pi, 3D printing, and much more. HMPL.js Forem Follow For developers using HMPL.js to build fast, lightweight web apps. A space to share projects, ask questions, and discuss server-driven templating Dropdown menu Dropdown menu Skip to content Navigation menu Search Powered by Algolia Search Log in Create account DEV Community Close Join the Forem Forem is a community of 3,676,891 amazing members Continue with Apple Continue with Facebook Continue with GitHub Continue with Google Continue with Twitter (X) OR Email Password Remember me Forgot password? By signing in, you are agreeing to our privacy policy , terms of use and code of conduct . New to Forem? Create account . 💎 DEV Diamond Sponsors Thank you to our Diamond Sponsors for supporting the DEV Community Google AI is the official AI Model and Platform Partner of DEV Neon is the official database partner of DEV Algolia is the official search partner of DEV DEV Community — Your community HQ Home About Contact Code of Conduct Privacy Policy Terms of Use Built on Forem — the open source software that powers DEV and other inclusive communities. Made with love and Ruby on Rails . DEV Community © 2016 - 2026. We're a blogging-forward open source social network where we learn from one another Log in Create account | 2026-01-13T08:47:52 |
https://www.youtube.com/howyoutubeworks?utm_campaign=ytgen&utm_source=ythp&utm_medium=LeftNav&utm_content=txt&u=https%3A%2F%2Fwww.youtube.com%2Fhowyoutubeworks%3Futm_source%3Dythp%26utm_medium%3DLeftNav%26utm_campaign%3Dytgen | YouTube 작동의 원리: 누구나 목소리를 낼 수 있는 공간 콘텐츠로 이동 YouTube 작동의 원리 AI 저작권 크리에이터 경제 선거 아동 및 청소년 학습 뉴스 개인 정보 보호 맞춤 동영상 YouTube 정책 영향력 보고서 투명성 보고서 YouTube 작동의 원리 YouTube의 사명 평범한 사람들이 자신의 목소리를 낼 수 있게 돕고 더 큰 세상과 만나게 하는 것 YouTube는 모든 사람이 마땅히 자신의 목소리를 낼 수 있어야 하고 서로의 이야기에 귀를 기울이며 의견을 나누고 커뮤니티를 형성할 때 세상이 더 나아진다고 믿습니다. 이 사이트에서 YouTube가 이 모든 일을 어떻게 실현하는지 자세히 알아보세요. 빠른 링크 AI 저작권 크리에이터 경제 선거 아동 및 청소년 뉴스 개인 정보 보호 맞춤 동영상 새로운 소식 블로그 디지털 세상으로부터가 아니라, 디지털 세상 안에서 청소년을 보호 게임, 스마트폰, 스트리밍 플랫폼에 이르기까지 청소년들 사이에서 새로운 기술의 인기가 높아지면서, 부모가 변화하는 기술 환경 속에서 자녀를 어떻게 올바르게 안내해야 하는지에 대한 질문은 물론, 청소년을 보호하고 성장을 지원하는 데 규제가 어떤 역할을 해야 하는지에 대한 중요한 질문도 함께 제기되고 있습니다. 블로그 YouTube 20주년을 기념하는 20가지 방법 YouTube가 탄생 20주년을 맞이했습니다. 19초 길이의 클립 하나로 시작된 YouTube가 어느덧 음악, Shorts 동영상, 팟캐스트 등 200억 개가 넘는 동영상이 업로드된 대규모 플랫폼이 되었습니다. 단 20년 만에 이루어진 엄청난 성장입니다. YouTube에서는 다양한 방식으로 20주년을 기념하고자 합니다. 이 축제를 함께 즐기실 수 있도록 새로운 기능과 통계, 숨겨진 보석 같은 기능, 이스터 에그를 맛보기로 소개합니다. 아래에서 살펴보세요. 블로그 YouTube, 업계 선도 기업들과 청소년 디지털 웰빙 협약 발표 YouTube CEO 닐 모한의 메시지: 오늘부터 YouTube는 10개국을 대표하는 지역 콘텐츠 크리에이터 및 배급사 10여 곳과 함께 '아동 및 청소년 디지털 웰빙 이니셔티브'에 참여합니다. 이 이니셔티브는 아동과 청소년의 연령에 적합한 고품질 콘텐츠를 개발하기 위한 통합된 비전을 지원합니다. | 2026-01-13T08:47:52 |
https://forem.com/enter?signup_subforem=63 | Welcome! - Forem Forem Feed Follow new Subforems to improve your feed DEV Community Follow A space to discuss and keep up software development and manage your software career Future Follow News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Open Forem Follow A general discussion space for the Forem community. If it doesn't have a home elsewhere, it belongs here Gamers Forem Follow An inclusive community for gaming enthusiasts Music Forem Follow From composing and gigging to gear, hot music takes, and everything in between. Vibe Coding Forem Follow Discussing AI software development, and showing off what we're building. Popcorn Movies and TV Follow Movie and TV enthusiasm, criticism and everything in-between. DUMB DEV Community Follow Memes and software development shitposting Design Community Follow Web design, graphic design and everything in-between Security Forem Follow Your central hub for all things security. From ethical hacking and CTFs to GRC and career development, for beginners and pros alike Golf Forem Follow A community of golfers and golfing enthusiasts Crypto Forem Follow A collaborative community for all things Crypto—from Bitcoin to protocol development and DeFi to NFTs and market analysis. Parenting Follow A place for parents to the share the joys, challenges, and wisdom that come from raising kids. We're here for them and for each other. Forem Core Follow Discussing the core forem open source software project — features, bugs, performance, self-hosting. Maker Forem Follow A community for makers, hobbyists, and professionals to discuss Arduino, Raspberry Pi, 3D printing, and much more. HMPL.js Forem Follow For developers using HMPL.js to build fast, lightweight web apps. A space to share projects, ask questions, and discuss server-driven templating Dropdown menu Dropdown menu Skip to content Navigation menu Search Powered by Algolia Search Log in Create account DEV Community Close Join the Forem Forem is a community of 3,676,891 amazing members Continue with Apple Continue with Facebook Continue with GitHub Continue with Google Continue with Twitter (X) OR Email Password Remember me Forgot password? By signing in, you are agreeing to our privacy policy , terms of use and code of conduct . New to Forem? Create account . 💎 DEV Diamond Sponsors Thank you to our Diamond Sponsors for supporting the DEV Community Google AI is the official AI Model and Platform Partner of DEV Neon is the official database partner of DEV Algolia is the official search partner of DEV DEV Community — Your community HQ Home About Contact Code of Conduct Privacy Policy Terms of Use Built on Forem — the open source software that powers DEV and other inclusive communities. Made with love and Ruby on Rails . DEV Community © 2016 - 2026. We're a blogging-forward open source social network where we learn from one another Log in Create account | 2026-01-13T08:47:52 |
http://claude.com/pricing#api | Pricing | Claude -------> Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Pricing Pricing Explore here Ask questions about this page Copy as markdown Pricing Individual Team & Enterprise API Active Free Try Claude $0 Free for everyone Try Claude Try Claude Try Claude Chat on web, iOS, Android, and on your desktop Generate code and visualize data Write, edit, and create content Analyze text and images Ability to search the web Unlock more from Claude with desktop extensions Pro For everyday productivity $17 Per month with annual subscription discount ($200 billed up front). $20 if billed monthly. Try Claude Try Claude Try Claude Everything in Free, plus: More usage* Access Claude Code on the web and in your terminal Create files and execute code Access to unlimited projects to organize chats and documents Access to Research Connect Google Workspace: email, calendar, and docs Integrate any context or tool through connectors with remote MCP Memory across conversations Extended thinking for complex work Ability to use more Claude models Max Get the most out of Claude From $100 Per person billed monthly Try Claude Try Claude Try Claude Everything in Pro, plus: Choose 5x or 20x more usage than Pro* Higher output limits for all tasks Memory across conversations Early access to advanced Claude features Priority access at high traffic times Claude in Excel Additional usage limits apply. Prices shown don’t include applicable tax. Team For collaboration across organizations Create a Team plan Create a Team plan Create a Team plan Standard seat Chat, projects, and more $25 Per person / month with annual subscription discount. $30 if billed monthly. Minimum 5 members. Premium seat Includes Claude Code $150 Per person / month. Minimum 5 members. More usage* Admin controls for remote and local connectors Single sign-on (SSO) and domain capture Enterprise deployment for the Claude desktop app Enterprise search across your organization Connect Microsoft 365, Slack, and more Central billing and administration Early access to collaboration features Claude Code available with premium seat Enterprise For businesses operating at scale Contact sales Contact sales Contact sales Everything in Team, plus: More usage* Enhanced context window Role-based access with fine-grained permissioning System for Cross-domain Identity Management (SCIM) Audit logs Google Docs cataloging Compliance API for observability and monitoring Claude Code available with premium seat Custom data retention controls HIPAA-ready offering available Additional usage limits apply. Prices shown don’t include applicable tax. Education plan Get a comprehensive university‐wide plan for an institution, including its students, faculty, and staff. Learn more Learn more Learn more Student and faculty access Comprehensive access for all university members at discounted rates Academic research and learning mode Dedicated API credits and educational features for student learning Training and enablement Resources for successful adoption across your institution Latest models Contact sales Contact sales Contact sales Start building Start building Start building Save 50% with batch processing. Learn more Batch processing Opus 4.5 Most intelligent model for building agents and coding Input $ 5 / MTok Output $ 25 / MTok Prompt caching Write $ 6.25 / MTok Read $ 0.50 / MTok Sonnet 4.5 Optimal balance of intelligence, cost, and speed Input Prompts ≤ 200K tokens $ 3 / MTok Prompts > 200K tokens $ 6 / MTok Output Prompts ≤ 200K tokens $ 15 / MTok Prompts > 200K tokens $ 22.50 / MTok Prompt caching ≤ 200K tokens Write $ 3.75 / MTok Read $ 0.30 / MTok > 200K tokens Write $ 7.50 / MTok Read $ 0.60 / MTok Haiku 4.5 Fastest, most cost-efficient model Input $ 1 / MTok Output $ 5 / MTok Prompt caching Write $ 1.25 / MTok Read $ 0.10 / MTok Prompt caching pricing reflects 5-minute TTL. Learn about extended prompt caching . Explore detailed pricing Explore detailed pricing Explore detailed pricing Pricing for tools Get even more out of Claude with advanced
features and capabilities. Learn more Learn more Learn more Web search Give Claude access to the latest information from the web. Doesn’t include input and output tokens required to process requests. Cost $10 / 1K searches Code execution Run Python code in a sandboxed environment for advanced data analysis. 50 free hours of usage daily per organization. Additional hours $0.05 per hour per container Service tiers Balance availability, performance, and predictable costs based on your needs. Learn more Learn more Learn more Contact sales Contact sales Contact sales Priority When time, availability, and predictable pricing are most important Standard Default tier for both piloting and scaling everyday use cases Batch For asynchronous workloads that can be processed together for better efficiency Legacy models Learn more Learn more Learn more Explore detailed pricing Explore detailed pricing Explore detailed pricing Save 50% with batch processing. Learn more Batch processing Opus 4.1 Input $ 15 / MTok Output $ 75 / MTok Prompt caching Write $ 18.75 / MTok Read $ 1.50 / MTok Sonnet 4 Input $ 3 / MTok Output $ 15 / MTok Prompt caching Write $ 3.75 / MTok Read $ 0.30 / MTok Opus 4 Input $ 15 / MTok Output $ 75 / MTok Prompt caching Write $ 18.75 / MTok Read $ 1.50 / MTok Haiku 3 Input $ 0.25 / MTok Output $ 1.25 / MTok Prompt caching Write $ 0.30 / MTok Read $ 0.03 / MTok Prompt caching pricing reflects 5-minute TTL. Learn about extended prompt caching . Homepage Homepage Next Next Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Write Button Text Button Text Learn Button Text Button Text Code Button Text Button Text Write Help me develop a unique voice for an audience Hi Claude! Could you help me develop a unique voice for an audience? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Improve my writing style Hi Claude! Could you improve my writing style? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Brainstorm creative ideas Hi Claude! Could you brainstorm creative ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Learn Explain a complex topic simply Hi Claude! Could you explain a complex topic simply? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Help me make sense of these ideas Hi Claude! Could you help me make sense of these ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Prepare for an exam or interview Hi Claude! Could you prepare for an exam or interview? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Code Explain a programming concept Hi Claude! Could you explain a programming concept? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Look over my code and give me tips Hi Claude! Could you look over my code and give me tips? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Vibe code with me Hi Claude! Could you vibe code with me? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! More Write case studies This is another test Write grant proposals Hi Claude! Could you write grant proposals? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to — like Google Drive, web search, etc. — if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can - an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Write video scripts this is a test Anthropic Anthropic © [year] Anthropic PBC Products Claude Claude Claude Claude Code Claude Code Claude Code Max plan Max plan Max plan Team plan Team plan Team plan Enterprise plan Enterprise plan Enterprise plan Download app Download app Download app Pricing Pricing Pricing Log in Log in Log in Features Claude in Chrome Claude in Chrome Claude in Chrome Claude in Slack Claude in Slack Claude in Slack Claude in Excel Claude in Excel Claude in Excel Skills Skills Skills Models Opus Opus Opus Sonnet Sonnet Sonnet Haiku Haiku Haiku Solutions AI agents AI agents AI agents Code modernization Code modernization Code modernization Coding Coding Coding Customer support Customer support Customer support Education Education Education Financial services Financial services Financial services Government Government Government Healthcare Healthcare Healthcare Life sciences Life sciences Life sciences Nonprofits Nonprofits Nonprofits Claude Developer Platform Overview Overview Overview Developer docs Developer docs Developer docs Pricing Pricing Pricing Regional Compliance Regional Compliance Regional Compliance Amazon Bedrock Amazon Bedrock Amazon Bedrock Google Cloud’s Vertex AI Google Cloud’s Vertex AI Google Cloud’s Vertex AI Console login Console login Console login Learn Blog Blog Blog Claude partner network Claude partner network Claude partner network Courses Courses Courses Connectors Connectors Connectors Customer stories Customer stories Customer stories Engineering at Anthropic Engineering at Anthropic Engineering at Anthropic Events Events Events Powered by Claude Powered by Claude Powered by Claude Service partners Service partners Service partners Startups program Startups program Startups program Tutorials Tutorials Tutorials Use cases Use cases Use cases Company Anthropic Anthropic Anthropic Careers Careers Careers Economic Futures Economic Futures Economic Futures Research Research Research News News News Responsible Scaling Policy Responsible Scaling Policy Responsible Scaling Policy Security and compliance Security and compliance Security and compliance Transparency Transparency Transparency Help and security Availability Availability Availability Status Status Status Support center Support center Support center Terms and policies Privacy choices Cookie settings We use cookies to deliver and improve our services, analyze site usage, and if you agree, to customize or personalize your experience and market our services to you. You can read our Cookie Policy here . Customize cookie settings Reject all cookies Accept all cookies Necessary Enables security and basic functionality. Required Analytics Enables tracking of site performance. Off Marketing Enables ads personalization and tracking. Off Save preferences Privacy policy Privacy policy Privacy policy Responsible disclosure policy Responsible disclosure policy Responsible disclosure policy Terms of service: Commercial Terms of service: Commercial Terms of service: Commercial Terms of service: Consumer Terms of service: Consumer Terms of service: Consumer Usage policy Usage policy Usage policy x.com x.com LinkedIn LinkedIn YouTube YouTube Instagram Instagram English (US) English (US) 日本語 (Japan) Deutsch (Germany) Français (France) 한국어 (South Korea) | 2026-01-13T08:47:52 |
https://www.youtube.com/t/terms | 서비스 약관 KR 서비스 이용약관 유료 서비스 약관 유료 서비스 사용 규칙 저작권 집중관리단체 공지 저작권 고지 커뮤니티 가이드 서비스 약관 다른 언어로 서비스 약관 보기: English 및 한국어 약관의 구성 본 요약은 서비스 약관('약관')을 살펴보는 데 도움을 주기 위해 만들어졌습니다. 이 정보가 유용한 가이드가 되기를 바라며, 약관 전문도 반드시 확인하시기 바랍니다. YouTube에 오신 것을 환영합니다. 이 섹션에서는 YouTube와 사용자의 관계를 설명합니다. 여기에는 서비스에 대한 설명이 포함되며, 계약을 정의하고, 서비스 제공자를 밝힙니다. 서비스 이용 대상 이 섹션에서는 서비스 이용에 대한 특정 요구사항을 설명하고, 사용자 분류를 정의합니다. 서비스의 이용 이 섹션에서는 서비스를 이용할 수 있는 권한과 서비스 이용에 적용되는 조건을 설명합니다. 또한, 서비스가 변경될 수 있음에 대해서도 설명합니다. 귀하의 콘텐츠 및 운영 이 섹션은 서비스에 콘텐츠를 제공하는 사용자에게 적용됩니다. 콘텐츠를 업로드함에 따라 허여하는 권한의 범위를 정의하고, 타인의 권리를 침해하는 콘텐츠를 업로드하지 않겠다는 사용자 동의가 포함됩니다. 계정 정지 및 해지 이 섹션에서는 사용자와 YouTube가 관계를 종료할 수 있는 방법을 설명합니다. 서비스에 포함된 소프트웨어에 대하여 이 섹션에서는 서비스의 소프트웨어에 대한 세부정보를 확인할 수 있습니다. 기타 법적 조항 이 섹션에서는 당사자들의 법적 의무에 대해 설명합니다. YouTube가 책임지지 않는 사항에 대한 설명도 확인할 수 있습니다. 본 계약에 대하여 이 섹션에서는 약관의 변경이나 준거법 등 계약과 관련된 중요한 세부정보를 확인할 수 있습니다. 서비스 약관 날짜: 2022년 1월 5일 서비스 약관 YouTube에 오신 것을 환영합니다. 소개 YouTube 플랫폼과 플랫폼에서 제공되는 제품, 서비스, 기능(이하 통칭하여 ' 서비스 ')을 사용해 주셔서 감사합니다. YouTube 서비스 YouTube 서비스는 사용자가 동영상 및 기타 콘텐츠를 찾아보고, 감상하고, 공유하며, 전 세계 사람들과 소통하고, 정보를 나누며, 아이디어를 주고 받을 수 있는 공간을 제공함은 물론, 규모에 관계없이 모든 독창적인 콘텐츠 크리에이터와 광고주에게 배포 플랫폼의 역할을 합니다. YouTube 고객센터 에서 다양한 제품 정보와 사용 방법을 참고할 수 있습니다. 특히 YouTube Kids , YouTube 파트너 프로그램 , YouTube 유료 멤버십 및 구매 관련 정보가 제공됩니다. TV, 게임 콘솔 또는 Google Home 등의 다른 기기 에서 콘텐츠를 즐기는 방법도 확인할 수 있습니다. 서비스 제공자 서비스를 제공하는 법인은 델라웨어 법률에 따라 운영되며, 1600 Amphitheatre Parkway, Mountain View, CA 94043에 소재한 Google LLC입니다(이하 ' YouTube ' 또는 ' 당사 '). 본 약관에서 YouTube의 ' 계열사 '는 Alphabet Inc. 기업 그룹에 (현재 또는 추후) 소속된 다른 회사를 지칭합니다. 적용 약관 귀하는 서비스 사용 시에 수시로 업데이트될 수 있는 본 약관, YouTube 커뮤니티 가이드 , 정책, 안전 및 저작권 정책 (' 계약 '으로 총칭)을 준수해야 합니다. 본 서비스에 광고 또는 스폰서십을 제공하거나, 콘텐츠에 유료 프로모션을 포함하는 경우 YouTube 광고 정책 도 당사와의 계약에 포함됩니다. 본 약관에 제공된 기타 링크 또는 참조는 정보 참고 목적으로만 제공되며, 계약의 일부가 아닙니다. 본 계약을 주의해서 읽고 숙지하시기 바랍니다. 본 계약에 이해할 수 없거나, 동의하지 않는 내용이 있다면 서비스를 사용하지 마시기 바랍니다. 서비스 이용 대상 연령 요건 서비스를 사용하려면 만 14세 이상이어야 합니다. 하지만 부모나 법정대리인이 사용 설정하면 모든 연령대의 아동이 서비스 또는 YouTube Kids를 사용할 수 있습니다(제공 국가에만 해당). 부모 또는 법정대리인 의 허락 귀하가 거주 국가에서 법률상 미성년자에 해당하는 경우, 귀하는 서비스를 사용할 수 있도록 부모 또는 법정대리인의 허락을 받았음을 진술합니다. 부모 또는 법정대리인과 함께 본 계약을 숙지하시기 바랍니다. 거주 국가에서 법률상 미성년자로 간주되는 사용자의 부모 또는 법정대리인이 사용자의 서비스 사용을 허락한 경우, 부모 또는 법정대리인은 본 계약 조건의 적용을 받게되며, 미성년 사용자의 서비스 이용 활동에 대한 책임을 집니다. 가족의 YouTube 사용을 관리하는 데 도움이 되는 도구와 자료(만 14세 미만의 아동에게 서비스 및 YouTube Kids를 사용 설정하는 방법 포함)가 YouTube 고객센터 와 Google의 Family Link 에서 제공됩니다. 사업자 회사 또는 기관을 위해 서비스를 사용하는 경우, 귀하는 해당 단체를 대신하여 행위할 권한이 귀하에게 있고, 해당 단체가 본 계약에 동의함을 진술합니다. 서비스의 이용 서비스 내 콘텐츠 서비스 내 콘텐츠에는 귀하, YouTube 또는 제3자가 제공하는 동영상, 오디오(예를 들어, 음악 및 기타 음향), 그래픽, 사진, 텍스트(댓글 및 스크립트), 브랜딩(상표 이름, 상표권, 서비스 표시 또는 로고 등), 인터랙티브 기능, 소프트웨어, 측정항목, 기타 자료가 포함됩니다. (이하 통칭하여 ‘ 콘텐츠 ’) 법률에 따라 YouTube가 책임을 지는 경우를 제외하고, 콘텐츠에 대한 책임은 서비스에 콘텐츠를 제공하는 사용자 또는 단체에게 있습니다. YouTube는 콘텐츠를 호스팅하거나 제공할 의무가 없습니다. 커뮤니티 가이드 또는 법률을 위반하는 등 본 약관을 준수하지 않는 콘텐츠를 발견하면 YouTube에 신고 할 수 있습니다. Google 계정 및 YouTube 채널 Google 계정 없이도 콘텐츠 탐색 및 검색 등 일부 서비스를 사용할 수 있습니다. 하지만 Google 계정이 있어야 사용 가능한 기능도 있습니다. Google 계정이 있으면 동영상에 좋아요 표시, 채널 구독, YouTube 채널 만들기 등이 가능합니다. Google 계정 만들기 안내를 따르세요. YouTube 채널을 만들면 동영상 업로드, 댓글 작성, 재생목록 만들기 등의 추가 기능을 이용할 수 있습니다. YouTube 채널을 만드는 방법 에 대한 자세한 내용을 참조하세요. Google 계정을 보호하려면 비밀번호를 공개하지 말아야 합니다. 타사 애플리케이션에서 Google 계정 비밀번호를 재사용하면 안 됩니다. 비밀번호 또는 Google 계정의 무단 사용 사실을 알게 된 경우의 조치 등 Google 계정 보안 유지 에 대해 자세히 알아보세요. 귀하의 정보 당사의 개인정보처리방침 은 서비스를 사용할 때 개인정보가 어떻게 처리되고 보호되는지 설명합니다. YouTube Kids 개인정보처리방침 은 YouTube Kids에만 해당하는 개인정보 보호관행에 대한 추가 정보를 제공합니다. 개인적 용도 또는 가족 활동 과정에서 업로드한 오디오 또는 시청각 콘텐츠인 경우를 제외하고, 귀하가 서비스에 업로드한 오디오 또는 시청각 콘텐츠는 YouTube 정보처리규정 에 따라 처리됩니다. 자세히 알아보기 권한 및 제한사항 귀하는 본 계약 및 관련 법령을 준수하는 한 귀하에게 제공된 서비스에 액세스하여 이를 사용할 수 있습니다. 귀하는 개인적, 비영리적 용도로 콘텐츠를 보고 들을 수 있습니다. 귀하는 내장가능한 YouTube 플레이어를 통해 YouTube 동영상을 표시할 수도 있습니다. 서비스 사용 시 다음 제한사항이 적용됩니다. (a) 서비스의 명시적 승인, 또는 (b) YouTube 및 해당하는 경우 각 권리 소유자의 사전 서면 승인을 받은 경우를 제외하고는, 서비스나 콘텐츠의 어떤 부분에 대해서도 액세스, 복제, 다운로드, 배포, 전송, 방송, 표시, 판매, 라이선스 부여, 변경, 수정 또는 그 밖의 사용을 금지합니다. (a) 콘텐츠의 복사 또는 기타 사용을 방지 또는 제한하거나, (b) 서비스 또는 콘텐츠의 사용을 제한하는 기능 또는 보안 관련 기능을 포함하여 서비스의 어떤 부분에 대해서도 우회, 무력화, 기망적인 관여 또는 그 밖의 방해 행위(또는 이러한 행위들에 대한 시도)를 금지합니다. (a) YouTube의 robots.txt 파일에 따른 공개 검색엔진의 경우, 또는 (b) YouTube의 사전 서면 승인을 받은 경우를 제외하고, 자동화된 수단(로봇, 봇넷 또는 스크래퍼 등)을 사용해 서비스에 액세스하면 안 됩니다. 당사자의 허가를 받거나, 위의 3항에서 허용하지 않는 한, 개인 식별이 가능한 정보(예: 사용자 이름이나 얼굴 모습)를 수집해서는 안 됩니다. 서비스를 사용해 원치 않는 홍보성/상업성 콘텐츠나 그 밖의 원치 않는 대량의 구매 권유 자료를 배포하면 안 됩니다. 동영상 조회수, 좋아요 또는 싫어요 수를 늘리거나, 채널 구독자 수를 늘리기 위해 사람들에게 비용을 지불하거나, 인센티브를 제공하는 등 서비스에 대한 실제 사용자 참여도의 부정확한 측정을 야기 또는 조장하거나, 달리 어떠한 방법으로든 측정항목을 조작하면 안 됩니다. 근거가 없거나, 권한을 남용하거나 또는 사소한 제출 등으로 보고, 신고, 불만 제기, 이의 제기 또는 항소 절차를 남용하면 안 됩니다. 본 서비스에서 또는 본 서비스를 통해 YouTube 컨테스트 정책 및 가이드라인 을 준수하지 않는 컨테스트를 시행하면 안 됩니다. 개인적, 비영리적 용도 외의 목적으로 콘텐츠를 보거나 듣기 위해 서비스를 사용하면 안 됩니다(예를 들어, 공개적으로 서비스의 동영상을 상영하거나, 음악을 스트리밍하면 안 됩니다). (a) YouTube 광 고 정책 에서 허용하는 경우(정책을 준수하는 간접 광고 등)를 제외하고, 서비스나 콘텐츠에 또는 그 주변이나 내부에 배치된 광고, 후원, 홍보물을 판매하거나, (b) 오로지 서비스의 콘텐츠만 포함되거나, 광고, 후원, 홍보물 판매의 주된 이유가 서비스의 콘텐츠인 웹사이트 페이지나 애플리케이션에서 광고, 후원, 홍보물을 판매(예를 들어, 사용자들이 방문하는 주요 목적이 YouTube 동영상인 웹페이지의 광고 판매)하기 위하여 서비스를 사용하면 안 됩니다. 유보 서비스를 사용한다고 해서 본 서비스의 어떠한 요소(예를 들어, 사용자 이름이나 다른 사용자 또는 YouTube가 게시한 다른 콘텐츠 등)에 대해서 소유권이나 권리가 부여되는 것은 아닙니다. 서비스 개발, 개선 업데이트 YouTube는 지속적으로 본 서비스를 변경 및 개선하고 있습니다. 지속적인 발전의 일환으로 기능이나 구성을 추가하거나 삭제하고, 새로운 디지털 콘텐츠 또는 서비스를 제공하거나 기존 서비스의 제공을 중단하는 등 본 서비스 전체 또는 일부를 개선하거나 변경할 수 있습니다. 당사는 성능이나 보안을 개선하거나, 법령을 준수하기 위한 변경을 하거나, YouTube 시스템 상의 불법적인 활동이나 시스템을 악용하는 행위를 방지하기 위해 본 서비스나 그 일부를 변경 또는 중단할 수 있습니다. 이러한 변경사항은 사용자 전체, 일부 또는 특정 개인에게 영향을 미칠 수 있습니다. 본 서비스에 다운로드 가능한 소프트웨어(YouTube 스튜디오 애플리케이션 등)가 필요하거나 포함되는 경우, 소프트웨어에 대한 새로운 버전이나 기능이 제공되면 기기 설정에 따라 소프트웨어가 기기에서 자동으로 업데이트될 수 있습니다. 귀하가 본 서비스를 이용하는 데 부정적인 영향을 미치는 중대한 변경사항이 있을 경우, YouTube는 귀하에게 합당한 사전 통지를 전달합니다. 다만, 합리적으로 통지가 불가능한 경우(예: 사용자가 로그인 없이 본 서비스를 이용하는 경우)이거나 긴급한 상황(예: 악용사례를 방지하거나, 법적 요건에 대응하거나, 보안 및 운용가능성 관련 문제를 해결)에서는 예외로 합니다. 또한 YouTube는 Google 테이크아웃 을 사용해 Google 계정에서 귀하의 콘텐츠를 내보낼 기회를 제공하며, 여기에는 관련 법규 및 정책이 적용됩니다.. 귀하의 콘텐츠 및 운영 콘텐츠 업로드 YouTube 채널을 보유한 경우 귀하는 서비스에 콘텐츠를 업로드할 수 있습니다. 자신의 콘텐츠를 사용해 비즈니스 또는 문화예술 사업을 홍보할 수 있습니다. 콘텐츠를 업로드하기로 했다면, 본 계약 또는 법령을 준수하지 않는 콘텐츠를 서비스에 제출하면 안 됩니다. 예를 들어, 당사자 허가를 받았거나, 법적으로 허용되는 경우가 아니라면 제출한 콘텐츠에 제3자의 지적 재산(예를 들어, 저작권으로 보호되는 자료)이 포함되어서는 안 됩니다. 귀하가 서비스에 제출한 콘텐츠에 대한 법적 책임은 귀하에게 있습니다. 당사는 스팸, 멀웨어, 불법 콘텐츠 등과 같은 침해 및 악용 사례를 감지하기 위해 자동화된 시스템으로 귀하의 콘텐츠를 분석할 수 있습니다. 귀하가 부여하는 권리 귀하의 콘텐츠에 대한 소유권은 귀하에게 있습니다. 하지만 아래에 설명된 바와 같이 귀하는 YouTube 및 서비스의 다른 사용자에게 일정한 권리를 부여해야 합니다. YouTube에 부여하는 라이선스 귀하는 본 서비스에 콘텐츠를 제공함으로써 콘텐츠를 사용(복제, 배포, 수정, 표시, 공연 등)할 수 있는 세계적이고, 비독점적이며, 무상으로 제공되고, 양도가능하며, 서브라이선스를 허여할 수 있는 라이선스를 YouTube에 부여합니다. YouTube는 본 서비스를 운영하고, 홍보 및 개선하기 위한 목적으로만 이러한 라이선스를 사용할 수 있습니다. 본 약관의 어떠한 조항도 법령에서 허용되는 범위를 넘어서는 라이선스를 YouTube에 부여하는 것은 아닙니다. 다른 사용자에게 부여하는 라이선스 또한 귀하는 서비스의 다른 사용자들에게 서비스를 통해 귀하의 콘텐츠에 액세스할 수 있는 세계적이고, 비독점적이며, 무상으로 제공되는 라이선스를 부여하며, 본 서비스에서 제공하는 기능(예를 들어, 비디오 플레이백이나 퍼가기)을 통해 설정된 바에 따라 해당 콘텐츠를 사용할 권리, 즉, 복제, 배포, 수정, 표시, 공연 등을 할 수 있는 권리를 부여합니다. 보다 명확히 설명하자면, 이 라이선스는 다른 사용자가 본 서비스와는 별개로 귀하의 콘텐츠를 활용할 수 있는 어떠한 권리나 권한도 부여하지 않습니다. 라이선스 기간 귀하가 부여한 라이선스는 해당 콘텐츠가 아래에서 설명하는 바에 따라 삭제될 때까지 유지됩니다. 콘텐츠가 삭제되면 라이선스가 종료되지만, 서비스 운영, 삭제 전에 허용한 콘텐츠의 사용, 또는 법령에서 달리 요구하는 경우에는 예외가 인정될 수 있습니다. 예를 들어, 귀하가 콘텐츠를 삭제하더라도 YouTube는 (a) 귀하의 콘텐츠가 포함된 홍보자료를 회수하거나, (b) 서비스의 제한적인 오프라인 시청 기능(예를 들어, 유료가입 서비스에서 이용할 수 있는 기능)에 따라 다른 이용자가 이용하는 콘텐츠를 회수해야 하는 의무가 있는 것은 아니며, (c) YouTube가 법적 필요에 의해 보관할 합리적인 이유가 있는 사본을 삭제해야 하는 것은 아닙니다. 수익 창출 권리 귀하는 서비스에 있는 귀하의 콘텐츠에서 수익을 창출할 권리를 YouTube에 부여합니다. 수익 창출에는 콘텐츠에 광고를 게재하거나 사용자에게 이용료를 청구하는 것도 포함될 수 있습니다. 이 계약으로 귀하에게 수익금을 지급받을 자격이 주어지지는 않습니다. 2021년 6월 1일부터 YouTube와 맺은 기타 계약을 통해 YouTube로부터 지급받을 자격이 있는 수익금(YouTube 파트너 프로그램, 채널 멤버십 또는 Super Chat 수익금 포함)은 모두 로열티로 취급됩니다. 법에서 요구되는 경우 Google이 지급액에서 세금을 원천징수합니다. 귀하의 콘텐츠 삭제 귀하는 언제든지 서비스에서 자신의 콘텐츠를 삭제 할 수 있습니다. 콘텐츠를 삭제하기 전에 콘텐츠 사본 을 만들 수도 있습니다. 만약 귀하가 본 약관에서 요구하는 권한을 더 이상 보유하지 않는 경우 콘텐츠를 삭제해야 합니다. YouTube에 의한 콘텐츠 삭제 귀하의 콘텐츠가 (1) 본 계약을 위반하거나, (2) YouTube, 사용자 또는 제3자에게 위해를 야기한다고 합리적으로 판단되는 경우, 당사는 그러한 콘텐츠를 삭제하거나 차단할 권리를 보유합니다.. YouTube는 통지가 (a) 법적 이유로 금지되거나, (b) 사용자, 기타 제3자, YouTube 또는 그 계열사에게 위해를 야기할 수 있다고 합리적으로 판단되는 경우(예를 들어, 통지하는 것이 법령 또는 규제당국의 명령을 위반하는 경우, 조사를 방해하는 경우, 본 서비스의 보안을 해하는 경우 등)를 제외하고, 귀하에게 해당 조치의 이유를 지체 없이 통지합니다. 항소 방법을 포함한 신고 및 집행에 대한 자세한 내용은 고객센터의 문제해결 페이지에서 확인할 수 있습니다. 커뮤니티 가이드 위반 경고 YouTube는 YouTube 커뮤니티 가이드 를 위반하는 콘텐츠를 대상으로 한 '경고' 시스템을 운영하고 있습니다. 최초 위반인 경우 YouTube는 일반적으로 주의만 주고, 그 이후의 위반의 경우 귀하의 채널에 대해 경고가 적용됩니다. 경고마다 다양한 제한사항이 수반되며 채널이 YouTube에서 영구적으로 삭제될 수도 있습니다. 경고가 채널에 미치는 영향에 대한 자세한 설명은 커뮤니티 가이드 위반 경고 기본사항 페이지 에서 확인할 수 있습니다. 경고가 잘못 주어졌다고 생각되는 경우 여기 에서 항소할 수 있습니다. 경고로 인해 채널에 제한이 적용된 경우 다른 채널을 사용해 제한을 회피하면 안 됩니다. 이 금지 조항을 위반하는 것은 본 계약을 중대하게 위반하는 행위로서 Google은 Google 계정을 해지하거나 본 서비스 전체 또는 일부의 액세스 권한을 해지할 권리를 보유합니다. 저작권 보호 YouTube는 저작권자가 온라인상에서 자신의 지적 재산을 관리하는 데 도움이 되는 정보를 YouTube 저작권 센터 에서 제공하고 있습니다. 본 서비스에서 귀하의 저작권이 침해되었다고 생각하는 경우 YouTube에 신고 해 주시기 바랍니다. YouTube는 YouTube 저작권 센터 의 절차에 따라 저작권 침해 신고에 대응합니다. YouTube 저작권 센터에서는 저작권 위반 경고 해결 방법에 대한 정보도 제공하고 있습니다. 반복적으로 저작권을 침해하는 사용자는 YouTube 정책에 따라 일정한 경우 서비스 액세스가 해지될 수 있습니다. 계정 정지 및 해지 귀하에 의한 해지 귀하는 언제든지 서비스 사용을 중지할 수 있습니다. 안내 에 따라 자신의 Google 계정에서 본 서비스를 삭제하면 됩니다. 삭제 시 귀하의 YouTube 채널이 폐쇄되고, 데이터가 삭제됩니다. 사용을 중지하기 전에 귀하의 데이터 사본을 다운로드할 수도 있습니다. YouTube에 의한 해지 및 정지 YouTube는 (a) 귀하가 본 계약을 중대하게 또는 반복적으로 위반하거나, (b) 법적 요건이나 법원 명령 등의 준수를 위한 경우, 또는 (c) 사용자, 기타 제3자, YouTube 또는 그 계열사에 책임이나 위해를 야기하는 행위가 있다고 합리적으로 판단되는 경우, 귀하의 Google 계정을 정지 또는 해지하거나 본 서비스 전체 또는 일부에 대한 귀하의 액세스를 해지할 권리를 보유합니다. 해지 또는 정지 에 대한 통지 YouTube는 통지가 (a) 법적 이유로 금지되거나, (b) 사용자, 다른 제3자, YouTube 또는 그 계열사에게 위해를 야기할 수 있다고 합리적으로 판단되는 경우(예를 들어, 통지하는 것이 법령 또는 규제당국의 명령을 위반하는 경우, 조사를 방해하는 경우, 본 서비스의 보안을 해하는 경우 등)를 제외하고, 귀하에게 YouTube에 의한 해지 또는 정지의 이유를 지체 없이 통지합니다. 서비스 변경으로 인해 YouTube가 귀하의 액세스를 해지하는 경우, 합리적으로 가능하다면 서비스에서 귀하의 콘텐츠를 가져올 충분한 시간을 귀하에게 제공합니다. 계정 정지 또는 해지의 효과 귀하의 Google 계정이 해지되거나 본 서비스에 대한 액세스가 제한되어도 서비스의 일부(예를 들어, 단순한 시청)는 계정 없이 계속 사용할 수 있으며, 본 계약은 그러한 사용에 대해서 계속 적용됩니다. Google 계정이 잘못 해지 또는 정지되었다고판단되는 경우 이 양식을 사용하여 항소 할 수 있습니다. 서비스에 포함된 소프트웨어에 대하여 다운로드 가능한 소프트웨어 서비스에 다운로드 가능한 소프트웨어(YouTube 스튜디오 애플리케이션 등)가 필요하거나 포함되는 경우, 라이선스를 제공하는 추가 약관의 적용을 받는 소프트웨어가 아니라면, YouTube는 귀하에게 서비스의 일부로 제공한 소프트웨어를 사용할 수 있는 개인적이고, 세계적이며, 무상으로 제공되고, 양도 불가능하며, 비독점적인 라이선스를 제공합니다. 이 라이선스는 귀하가 본 계약에서 허용하는 방법에 따라 YouTube가 제공하는 바대로 본 서비스를 사용하고 혜택을 누릴 수 있도록 하기 위한 목적으로만 제공됩니다. 귀하는 이 소프트웨어의 어느 부분도 복사, 수정, 배포, 판매 또는 대여할 수 없으며, 소프트웨어를 역설계하거나, 소스 코드의 추출을 시도할 수 없습니다. 다만, 법률상 이와 같은 제한이 금지되거나, YouTube의 서면 승인을 받은 경우는 제외합니다. 오픈소스 본 서비스에서 사용되는 일부 소프트웨어는 당사가 귀하에게 부여하는 오픈소스 라이선스 하에서 제공될 수 있습니다. 오픈소스 라이선스에는 명시적으로 본 약관의 일부 규정에 우선하는 규정이 있을 수 있으므로, 그러한 라이선스 내용을 숙지하시기 바랍니다. 기타 법적 조항 보증 의 부인 본 계약에 명시되거나, 법률에서 요구되지 않는 한, 본 서비스는 '있는 그대로' 제공되며 YouTube는 서비스와 관련한 어떤 구체적인 약정이나 보증도 하지 않습니다. 예를 들어, 법률상 허용되는 한도 내에서, 당사는 (a) 서비스를 통해 제공되는 콘텐츠, (b) 서비스의 특정 기능이나 서비스의 정확성, 안정성, 가용성 또는 귀하의 필요를 충족할 능력, 또는 (c) 귀하가 제출하는 어떤 콘텐츠든 서비스에서 액세스할 수 있음을 보증하지 않습니다. 모바일로 YouTube 광고를 시청하는 경우 데이터 요금이 발생할 수 있습니다. 책임의 제한 법률에서 요구되는 경우를 제외하고, YouTube, 그 계열사, 임원, 이사, 직원 및 대리인은 다음 사항을 원인으로 발생한 이익·수입·사업 기회·영업권·예상된 절감 효과의 상실, 데이터의 손실 또는 손상, 간접적 또는 결과적 손실, 징벌적 손해에 대해 책임을 지지 않습니다. 서비스의 오류, 실수 또는 부정확한 내용 귀하의 서비스 사용으로 인한 개인의 상해나 재산 피해 서비스의 무단 액세스 또는 사용 서비스의 중단 또는 중지 제3자에 의해 서비스에 또는 서비스를 통해 전송된 바이러스 또는 악성 코드 귀하의 콘텐츠 사용을 포함해 사용자 또는 YouTube가 제출한 콘텐츠, 및/또는 콘텐츠의 삭제 또는 이용 불가 본 조항은 청구의 근거가 보증, 계약, 불법 행위 또는 기타 법리 등 무엇이든 상관없이 모든 청구에 적용됩니다. 관련 법률이 허용하는 한도 내에서, 본 서비스와 관련된 또는 그로 인한 청구에 대한 YouTube 및 그 계열사의 총 배상 책임은 (a) 귀하가 청구에 관하여 YouTube에 서면 통지하기 전 12개월 동안 YouTube가 귀하의 서비스 사용과 관련해 귀하에게 지급한 수익 금액과, (b) 미달러 $500 중 높은 금액으로 제한됩니다. 면책 관련 법률이 허용하는 한도 내에서, 귀하는 (a) 귀하의 서비스 사용 및 액세스, (b) 귀하의 본 약관 조항 위반, (c) 귀하의 제3자의 저작권, 재산권 또는 프라이버시권 등 권리침해, 또는 (d) 귀하의 콘텐츠로 손해를 입었다는 제3자의 주장으로 발생하는 모든 청구, 손해, 의무, 손실, 책임, 비용 또는 채무, 지출(변호사 비용 등)로부터 YouTube, 그 계열사, 임원, 이사, 직원 및 대리인을 보호하고, 이들의 책임을 면제하며, 이로 인하여 손해를 입지 않도록 하는 데 동의합니다. 이러한 방어 및 면책 의무는 본 계약과 귀하의 본 서비스 사용이 종료된 후에도 유효하게 존속합니다. 제3자 링크 서비스에는 YouTube가 소유하거나 관리하지 않는 제3자 웹사이트 및 온라인 서비스의 링크가 포함될 수 있습니다. YouTube는 해당 웹사이트 및 온라인 서비스에 관여할 수 없으며, 관련 법률이 허용하는 한도 내에서, 이에 대한 책임을 지지 않습니다. 본 서비스에서 떠나는 경우 귀하가 방문하는 각 제3자 웹사이트 및 온라인 서비스의 약관과 개인정보처리방침을 검토하시기 바랍니다. 본 계약에 대하여 본 계약 ' 의 변경 당사는 (1) 서비스 수정 사항을 반영하거나, 사업 방식의 변화를 반영하거나(예: 새 제품 또는 기능을 추가하거나 기존의 것들을 삭제하는 경우) (2) 법령, 규제 또는 보안상 등의 이유가 있거나 (3) 악용 또는 위해를 방지하기 위해 본 계약을 변경할 수 있습니다. 본 계약에 중대한 변경사항이 있을 경우, YouTube는 최소 30일 전에 사전 통지와 변경사항 검토 기회를 제공하지만, (1) 사용자에게 유리한 신규 제품 또는 기능을 출시하는 경우 또는 (2) 발생 중인 악용사례를 방지하거나 법적 요건에 대응해야 하는 등 긴급한 상황인 경우는 예외입니다. 새로운 약관에 동의하지 않으면 업로드한 콘텐츠를 삭제하고 본 서비스 이용을 중지해야 합니다. 본 계약의 지속 귀하의 서비스 사용이 종료되어도 본 계약의 '기타 법적 조항', '본 계약에 대하여' 부분은 계속 귀하에게 적용되며, 귀하가 부여한 라이선스는 '라이선스 기간'에서 설명된 바에 따라 지속됩니다. 분리 어떤 이유로든 본 계약의 특정 조항이 집행 불가능한 것으로 판명되는 경우, 이는 다른 조항에 영향을 미치지 않습니다.. 권리 포기 귀하가 본 계약을 준수하지 않았을 때 당사가 즉시 조치를 취하지 않더라도, 이는 당사가 보유하는 권리(향후 조치를 취할 권리 등)를 포기하는 것을 의미하지 않습니다. 해석 본 약관에 사용된 ' 포함 ' 또는 ‘ 등 '이란 표현은 '포함하되 한정되지 않음'이란 의미이며, 당사가 제시한 예시는 설명을 위한 목적으로 사용된 것입니다. 준거법 일부 국가의 법원에서는 분정 유형에 따라 미국 캘리포니아주 법률을 적용하지 않을 수 있습니다. 귀하가 이러한 국가에 거주하고, 미국 캘리포니아주 법률의 적용이 배제되는 경우, 거주 국가의 법률이 본 약관과 관련된 분쟁에 적용됩니다. 그렇지 않은 경우, 귀하는 본 약관 또는 서비스와 관련되거나, 이로부터 야기된 일체의 분쟁에 대해 미국 캘리포니아주 법률이 적용되며, 캘리포니아주 국제사법의 적용은 배제된다는 것에 동의합니다. 마찬가지로, 거주 국가의 법원이 귀하가 미국 캘리포니아주 산타클라라 카운티 법원의 관할에 합의하는 것을 허용하지 않는 경우, 본 약관과 관련된 분쟁에 관하여 귀하의 거주지 재판관할이나 법정지가 적용됩니다. 그렇지 않은 경우, 본 약관 또는 서비스와 관련되거나, 이로부터 야기된 모든 청구는 미국 캘리포니아주 산타클라라 카운티의 연방 또는 주 법원이 전속관할을 가지며, 귀하와 YouTube는 해당 법원이 인적 관할을 갖는 것에 동의합니다. 발효일: 2022년 1월 5일( 이전 버전 보기 ) | 2026-01-13T08:47:52 |
https://old.reddit.com/r/fantasyfootball/ | r/fantasyfootball - No bye weeks here jump to content my subreddits edit subscriptions popular - all - users | AskReddit - pics - funny - movies - worldnews - news - todayilearned - nottheonion - explainlikeimfive - mildlyinteresting - DIY - videos - OldSchoolCool - TwoXChromosomes - tifu - Music - books - LifeProTips - dataisbeautiful - aww - science - space - Showerthoughts - askscience - Jokes - Art - IAmA - Futurology - sports - UpliftingNews - food - nosleep - creepy - history - gifs - InternetIsBeautiful - GetMotivated - gadgets - announcements - WritingPrompts - philosophy - Documentaries - EarthPorn - photoshopbattles - listentothis - blog more » fantasyfootball hot new rising controversial top wiki Want to join?  Log in  or  sign up  in seconds. limit my search to r/fantasyfootball use the following search parameters to narrow your results: subreddit: subreddit find submissions in "subreddit" author: username find submissions by "username" site: example.com find submissions from "example.com" url: text search for "text" in url selftext: text search for "text" in self post contents self:yes (or self:no) include (or exclude) self posts nsfw:yes (or nsfw:no) include (or exclude) results marked as NSFW e.g.  subreddit:aww site:imgur.com dog see the search faq for details. advanced search: by author, subreddit... Submit a new link Submit a new text post Get an ad-free experience with special benefits, and directly support Reddit. get reddit premium fantasyfootball join leave Posting Rules | FAQ | Latest Index Thread | How to post a Player Discussion | AMAugust | r/FF-created Tools r/FF - Good For Your Season Check out the FAQ and latest Index Thread ! The more you help others, the more likely they are to help you. Posting Rules View the full Posting Rules and Guidelines . 1- No individual threads of any kind specific to your team or league. Use the consolidated threads for individualized questions and avoid encouraging these threads. You will be banned without additional warning for violating this rule. 2-Don't post standalone Player/Game Discussion threads when a Game Thread or Postgame Thread is active 3-Keep the subreddit on topic and quality up. No memes, irrelevant media or spam. 4-Search or check new before posting. 5 – Be respectful. Do not return to old post to gloat/shame/mock Read our self-promotion guidelines before posting your own content . Daily Threads Use the daily threads for your fantasy needs! Links to them can be found in the official INDEX post stickied on the front page. [Who Do I Start?] , [Who Do I Keep?] , [Who Do I Draft?] , [Add/Drop] , [Trade] , [Rate My Team] , [Dynasty & Best Ball] and [Simple Questions/League Issues] threads will be posted daily. Individual threads will be removed and the submitter banned. AMA Schedule Guest Date AMAugust begins! 7/28 Games & Contests FanDuel Reddit Daily Fantasy 2022 Announcement | View standings View our Pick 'em, Eliminator, and Gridiron games at NarFFL.com NarFFL The official Reddit fantasy football league. 1,584 teams fighting for a right to hoist THE HORN . More info at /r/NarFFL & NarFFL.com Helpful Links Official Chatroom: Telegram Unofficial Discord: Discord FantasyPros - Expert Consensus Rankings (ECR) , Who Should I Start? , & Draft Wizard Fantasy Football Calculator - Mock draftroom by /u/nivek 4for4.com - Fantasy stats, rankings, & tools Clickydraft - Free Live Draft Board by /u/gimliclc Related Subreddits /r/nfl /r/NarFFL /r/findaleague /r/dfsports /r/FFCommish /r/DynastyFF /r/WFF /r/FFIDP /r/CFB /r/fantasybaseball /r/fantasybball /r/fantasyhockey Wiki Wiki Home Rules Self-Promotion Guidelines FAQ Beginners Guide Resource Guide Accuracy Challenge Reddit 101 Filter Posts Text Only Links Only News Only Quality Posts Only Tools & Resources No Daily Posts No Josh Gordon Help us help you. Contact the mods anytime! a community for  17 years MODERATORS message the mods Welcome to Reddit, the front page of the internet. Become a Redditor and join one of thousands of communities. × 1 398 399 400 Top 100 Fantasy Players of All-Time (Since 1970, Best 50 Games Average Adjusted VOLS%) Quality Post   ( self.fantasyfootball ) submitted  6 days ago  by  Thi11yG00th  -  announcement 70 comments share save hide report loading... 2 1 2 3 Official: [Index] - For All Your Team/League Questions - Thu 01/08/2026 Index   ( self.fantasyfootball ) submitted  4 days ago   *  by  FFBot  -  announcement comment share save hide report loading... 3 263 264 265 Top 10 “PPR Scams” in 2025 - WRs and RBs   ( i.redd.it ) submitted  11 hours ago  by  depressichemisti 62 comments share save hide report loading... 4 2024 2025 2026 The 49ers say TE George Kittle officially tore his Achilles.   ( bsky.app ) submitted  1 day ago  by  gw2380 117 comments share save hide report 5 1113 1114 1115 Kittle carted in Philly with lower-leg injury   ( nbcsports.com ) submitted  1 day ago  by  IceCreamPaintJob 176 comments share save hide report loading... 6 6 7 8 Jan 12, 2026: Wildcard MNF FanDuel and DraftKings Trends - Top 15 by Last 3 Actual Value   ( self.fantasyfootball ) submitted  12 hours ago  by  rbrad comment share save hide report loading... 7 0 0 0 Is there a free NFL playoff pool site that starts after Wild Card round? Tools & Resources   ( self.fantasyfootball ) submitted  4 hours ago  by  ganglyman009 1 comment share save hide report loading... 8 1 2 3 2026 vs 2027 Dynasty Rookie Mock Draft: How Far Ahead is the 2027 Class Really? Dynasty   ( youtu.be ) submitted  16 hours ago  by  Dekku25 7 comments share save hide report loading... 9 20 21 22 Game threads?   ( self.fantasyfootball ) submitted  1 day ago  by  IllustriousSpeaker27 18 comments share save hide report loading... 10 0 0 0 Off-Season Buys - January Player Discussion   ( thegoallinegrind.com ) submitted  12 hours ago  by  kschwab6 comment share save hide report loading... 11 640 641 642 Colston Loveland 2026 fantasy outlook   ( self.fantasyfootball ) submitted  2 days ago  by  FFdarkpassenger45 192 comments share save hide report loading... 12 0 0 0 Pittsburgh vs Houston - Unofficial game thread Game Thread   ( self.fantasyfootball ) submitted  12 hours ago   *  by  teachingroland 58 comments share save hide report loading... 13 5 6 7 Jan 11, 2026: Wildcard SNF FanDuel and DraftKings Trends - Top 15 by Last 3 Actual Value Tools & Resources   ( self.fantasyfootball ) submitted  1 day ago  by  rbrad 1 comment share save hide report loading... 14 3 4 5 Wildcard Sunday FanDuel and DraftKings Trends - Top 15 by Last 3 Actual Value | Jan 11, 2026 Tools & Resources   ( self.fantasyfootball ) submitted  1 day ago   *  by  rbrad 3 comments share save hide report loading... 15 0 0 0 Parity League Scoring   ( self.fantasyfootball ) submitted  1 day ago   *  by  Full_Reindeer5094 22 comments share save hide report loading... 16 24 25 26 The DFS Must Starts: Allen leads big 2 of 3 Wild Card weekend slates Player Discussion   ( blitzsportsmedia.com ) submitted  2 days ago  by  fantasyfbguru2 2 comments share save hide report 17 271 272 273 Who would you rather have, Chris Olave or Garrett Wilson? Player Discussion   ( self.fantasyfootball ) submitted  3 days ago  by  ProperEnthusiasm1486 149 comments share save hide report loading... 18 7 8 9 Week 1 Playoff Projections powered by Vegas Props is live (!!) Tools & Resources   ( self.fantasyfootball ) submitted  2 days ago  by  bbl27 firstdown.studio 1 comment share save hide report loading... 19 1257 1258 1259 Lions expect to discuss trading David Montgomery this offseason   ( nbcsports.com ) submitted  3 days ago  by  BreakfastTop6899 218 comments share save hide report 20 58 59 60 Season Scoring for Playoff teams QB, RB, RB, WR, WR, TE, D   ( self.fantasyfootball ) submitted  3 days ago  by  aagusgus 9 comments share save hide report loading... 21 285 286 287 Predicting Breakout WRs in 2026 [Tempering Expectations]   ( self.fantasyfootball ) submitted  3 days ago  by  KyonFantasyFootball Kyle Menton, Fantasy Points 126 comments share save hide report loading... 22 71 72 73 RB Analysis: Looking Back at 2025 and Forward to 2026   ( jonsalve.substack.com ) submitted  3 days ago  by  TheFFTrader 13 comments share save hide report 23 0 0 0 "Omarion Hampton (questionable, ankle) vs Patriots 7th ranked run D - What are we doing?   ( self.fantasyfootball ) submitted  1 day ago  by  blood_and_parchment 21 comments share save hide report loading... 24 38 39 40 Drake Maye: 2025 Season Review Player Discussion   ( fptrack.com ) submitted  3 days ago  by  drkelemnt 34 comments share save hide report loading... 25 2 3 4 Jan 10, 2026: Wildcard Saturday FanDuel and DraftKings Trends - Top 15 by Last 3 Actual Value Tools & Resources   ( self.fantasyfootball ) submitted  2 days ago  by  rbrad comment share save hide report loading... view more:  next › about blog about advertising careers help site rules Reddit help center reddiquette mod guidelines contact us apps & tools Reddit for iPhone Reddit for Android mobile website <3 reddit premium Use of this site constitutes acceptance of our  User Agreement  and  Privacy Policy . © 2026 reddit inc. All rights reserved. REDDIT and the ALIEN Logo are registered trademarks of reddit inc. Advertise - sports π Rendered by PID 29 on reddit-service-r2-loggedout-59f68dfc9-pk5xp at 2026-01-13 08:47:51.571458+00:00 running d5e020e country code: KR. | 2026-01-13T08:47:52 |
https://discourse.llvm.org/t/rfc-reducing-process-creation-overhead-in-llvm-regression-tests/88612?u=nikic | [RFC] Reducing process creation overhead in LLVM regression tests - LLVM Project - LLVM Discussion Forums LLVM Discussion Forums [RFC] Reducing process creation overhead in LLVM regression tests LLVM Project llvm , testing BStott October 16, 2025, 4:24pm 1 On Windows, process creation incurs a significant overhead, especially when antivirus software is installed. I estimate the overhead per process on my work PC to be around 0.027 seconds, and Lit spawned 246200 processes during check-llvm , i.e. around 10 minutes of CPU time spent just creating and destroying processes. This RFC demonstrates that we can reduce the time taken by check-llvm by at least 20% on Windows by merging processes. Inspired by @rgal ’s observation that process creation is a significant overhead for Lit tests, I have been trying some ideas to reduce the number of process invocations during check-llvm , to hopefully reduce testing times and CI workload (examining the CI logs on GitHub, running the regression tests on Windows seems to take about 8 minutes - example from a random pull request I found ). The main approach I have explored is introducing new frontends for opt / llc that operate on multiple modules in one process, and mechanically “merging” a group of tests just before testing by replacing them with one test that invokes the new multi-module tool. I drafted a very rough prototype of this idea here and the results are promising, with a reduction in testing runtime on my Windows PC from 950 to 775 seconds, or 236 to 61 seconds if only tests identified as mergeable are considered. Surprisingly, a noticeable difference on Linux (WSL) was also observed, though not as dramatic as the one observed on Windows. graph 1536×2048 122 KB Prototype implementation Merged tests consist of a single run directive invoking the multi-module version of the tool (these are optmany and llcmany in my proof-of-concept and reside in the llvm/tools directory), the result of which is piped into FileCheck with the test file as the check file as usual. Following this are a series of INPUT_FILE directives specifying the paths to the original test modules, which are interpreted by the multi-module tool. Finally, the FileCheck directives from the original tests are extracted and appended to the merged tests, interspersed by checks for special boundary labels outputted by the multi-module tool. An example of a merged test is as follows: RUN: optmany -o - -hide-filename < %s -O2 -S | FileCheck %s INPUT_FILE: llvm\test\Transforms\InstCombine\no-unwind-inline-asm.ll INPUT_FILE: llvm\test\Transforms\InstCombine\unwind-inline-asm.ll CHECK: TEST_BEGIN CHECK-LABEL: INPUT_FILE llvm\test\Transforms\InstCombine\no-unwind-inline-asm.ll CHECK: define dso_local void @test() CHECK-NEXT: entry: CHECK-NEXT: tail call void asm sideeffect CHECK-NEXT: ret void CHECK: TEST_END CHECK: TEST_BEGIN CHECK-LABEL: INPUT_FILE llvm\test\Transforms\InstCombine\unwind-inline-asm.ll CHECK: define dso_local void @test() CHECK-NEXT: entry: CHECK-NEXT: invoke void asm sideeffect unwind CHECK: %0 = landingpad { ptr, i32 } CHECK: resume { ptr, i32 } %0 CHECK: TEST_END These are created and run by a Python program called test_consolidator in llvm/utils . To try it, first update the information in test_consolidator.json in the project root and then invoke test_consolidator/main.py from the LLVM clone directory and, once it’s set up and prompts for a command, run all-merged to run all regression tests with as many merged as possible - note that some TableGen tests fail when ran this way; this is because they rely on relative paths but the prototype implementation copies all tests to a temporary directory. As for deciding which tests can be merged, the prototype implementation just sees tests with the exact same run directive (tests with multiple run directives are treated as multiple tests with one each) and the same REQUIRES / UNSUPPORTED directives and lit.local.cfg as mergeable. This results in 17832 regression tests (42% of all .ll tests) being identified as mergeable; these are converted into 5272 merged tests, reducing the total number of processes invoked from 248091 to 197581. I also experimented with parallelising optmany but this did not result in a meaningful speed improvement during actual test runs, as Lit is already running tests in parallel. Prototype limitations Swathes of code are copied from llc.cpp and optdriver.cpp into llcmany and optmany . This doesn’t just violate the DRY principle but also has the major flaw that changes made to this code will not be tested by the merged tests. If this idea is to be viable then this code must be extracted into library functions (e.g. optInit and optProcessModule ) which are called by opt and optmany (this follows the iniative already started by the extraction of optMain to a static library). This refactoring would be the main cost of implementing this solution. The prototype test consolidator is quite slow to create the merged tests, taking 20 seconds to identify mergeable tests and 1 minute 50 seconds to create the merged tests on my PC. It is written in Python and relies on lots of regexes for parsing out FileCheck directives reliably(ish) and more - I am quite new to writing regexes so this is definitely a major area for optimisation. It should be possible to make this process very fast, so that it can be run just before testing. Also, it is certain that you can invent a Lit test which confuses it (I only made sure all mergeable tests that are normally invoked by check-llvm still pass after merging). Another issue is that when a merged test fails, it requires some work to work out which test it was. A potential solution could be automatically re-running the individual tests from the merged tests that were reported as failures - this could be implemented by parsing Lit’s output or by integrating with Lit. Other approaches A few other approaches I considered are: Mechanically merging as many opt / llc tests as possible by concatenating them into one module before testing. I decided that this approach, while the least invasive (it would only require the introduction of one “merge tests” script that is ran before testing), would be too fragile as merging modules would invalidate the existing FileCheck directives, especially if identifiers, metadata IDs, etc. have to be uniquified. Compiling the tools to be tested as shared libraries and invoking them within the Lit process. This is the most powerful approach in that it could theoretically eliminate the process creation overhead entirely, and is also the most resilient to being upset by unusually structured Lit tests. However, it poses the extremely invasive restriction on all the tools for which the idea is applied that the main function must be idempotent and should never call exit or similar, as this would exit from the Lit worker itself - unless some hackery is done like linking with a fake exit function, but this is too evil. Is reducing process invocations to speed up regression testing a useful pursuit? Do you think the trade-off of maintenance and increased testing complexity and fragility is worth it for the potential reduction in testing times? Does anyone have other ideas to achieve the same goal in a better way? CC @jmorse 7 Likes [RFC] LLVM_LINK_LLVM_DYLIB should default to ON on Posix platforms `cl::opt` options of class types (apart from `std::string`) are not reset to their initial values LLVM Weekly - #616, October 20th 2025 nikic October 16, 2025, 7:09pm 2 I do think that the general direction here is worth pursuing – this is most problematic on Windows, but increased process startup overhead is also one of the big downsides of enabling LLVM_LINK_LLVM_DYLIB builds on Linux, because dynamic relocations add significant overhead to short-running test processes. However, I’m not really a fan of the specific approach you are using. This kind of pre- and post-processing of tests looks very fragile to me. The broad alternative I’d consider is to support a daemonized running mode for tools like opt , and corresponding support in lit to send certain “commands” to the corresponding daemon instead, keeping a pool of such processes live. This should be mostly transparent from the perspective of the test. 8 Likes cachemeifyoucan October 16, 2025, 10:24pm 3 Also want to point out both merging and daemon approach also needs to work great when tests are failing, especially the tool just crashes. It needs to ping point exactly which tests are failing, hopefully without re-executing (since it can be non-deterministic). I guess another competing idea will be just going fully distributable so you can run it as wide as possible. Usually one lit test has a very small dependency, and you can distribute that very well, but we don’t encode fine-grain dependencies in CMake to allow that. 1 Like boomanaiden154-1 October 16, 2025, 11:50pm 4 I agree with Nikita that adding new binaries that can support running multiple files at the same time and using lit to merge the test lines isn’t the best option. The patch you have looks like it duplicates a bunch of code and will end up having a pretty high maintenance overhead. However, I do think this work is quite valuable. I have recently spent a bunch of time working on eliminating process start overhead for testing across the monorepo by working towards enabling lit’s internal shell by default on Linux. That eliminates bash invocations and has resulted in a 10-15% speedup in a couple of the big test suites. We’ve been focusing on this primarily for premerge. Most of the time spent running premerge is spent running lit tests, and we’re trying to drive down test latency that way. We’ve mostly been focused on the low hanging fruit (like finishing up the enablement of the internal shell), but the next step on that front would probably be some sort of daemon mode. There is prior art for a daemon mode in LLVM ( ⚙ D86351 WIP: llvm-buildozer and https://www.youtube.com/watch?v=usPL_DROn4k ). I don’t think anyone has made it work specifically for testing, but I would certainly be interested in seeing it. If someone ends up putting in the work to do this, it would also be great if in addition to the LLVM tools, we could also get it working with clang. That would probably have similar impact on the clang test suite and might have some impact on other test suites like libc++. However, the libc++ test suite doesn’t spend much time in process startup compared to the other test suites last I checked (and disabling PIE doesn’t have a large impact on the test suite time). I think a daemon mode would have appropriate maintenance/test speedup tradeoffs, assuming the work is done to make sure it reports crashes correctly. 1 Like jh7370 October 17, 2025, 7:45am 5 Based purely on what you’ve described, my biggest concern would be that merging processes would not mean these processes would then share memory, rather than each one having a completely clean state to work with, which could theoretically mean tests pass when merged, but fail when separate (or indeed vice versa). I acknowledge that this class of bugs is likely to be rare. Perhaps it would be sufficient to make this configurable at cmake time, with developers having it enabled and build bots having it disabled or similar. 1 Like dblaikie October 17, 2025, 6:08pm 6 FWIW, Carbon uses a single process to run tests ( carbon-lang/testing/file_test at trunk · carbon-language/carbon-lang · GitHub carbon-lang/toolchain/testing/file_test.cpp at trunk · carbon-language/carbon-lang · GitHub ) that might be worth some inspiration. Combined with an LLVM busybox perhaps it could work for most of LLVM’s test suite - though the current implementation’s probably closer to clang, so maybe trying it with in-process clang might be an easier prototype/increment. 4 Likes BStott October 21, 2025, 8:41am 7 Thanks everyone for the kind and constructive feedback. I agree the test merging approach isn’t ideal. I’m currently prototyping the daemon-based approach. rnk October 25, 2025, 12:27am 8 Thanks for looking into this, it’s something I’ve talked about often over lunch, but I have no action to show for it. There is further prior art here to look at in the Chromium test launcher ( 2013 announcement , implementation ). One of the innovations here was to re-run failing tests in isolation at the end of the test run to distinguish between failures caused by state carried over from prior test execution, vs true positive failures of the test when run by itself. With a more centrally-controlled corporate project like Chromium, you can imagine that there is some dedicated cleanup crew that pulls data on test re-runs and tries to continuously keep them under control. 4 Likes BStott November 13, 2025, 2:00pm 9 Hi everyone, I’ve been experimenting with a prototype for the daemonized test running idea which can be found here . So far, I’ve just been applying the idea to opt and FileCheck and comparing performance in the llvm/Transforms folder. Lit collects the stdout and stderr from the daemon, as well as the return code, and displays them as normal. If the daemon exits unexpectedly during a test, Lit takes the exit code as the exit code for the test and restarts the daemon, so crashing is taken care of. To try the daemonized testing, invoke Lit with --use-daemon-tools . On Windows, running all the llvm/Transforms tests with regular Lit takes 137 seconds on my PC. With my prototype for running opt and FileCheck as daemons, it takes just 32 seconds, although 0.97% of tests in the Transforms directory fail incorrectly. The biggest problem for the approach is static state in LLVM. Static variables are not reset between daemon tasks, so any static variable that may affect the output can break tests - for example, NumDevirtCalls in WholeProgramDevirt.cpp wasn’t being reset between runs, causing the Transforms/WholeProgramDevirt/import.ll test to fail unexpectedly - I think the causes for the remaining failures are similar. The daemonization approach could only be applied universally if all state which is shared between modules and may change the output is removed and forbidden. Another idea I had is, for tests that fail when run using the daemon, to try re-running them without it - this would cover cases where the daemonization causes incorrect failures, but doesn’t solve the issue pointed out by jh7370 that shared state could cause tests to pass incorrectly. The daemonization is transparent from the perspective of the Lit test, although it may be sensible to make a way for a test to opt out of running tools in daemon mode in case the test relies on state that can’t be properly reset, or even to make it opt-in on a per-invocation basis (e.g. RUN: %opt_daemon rather than RUN: opt ). 5 Likes boomanaiden154-1 November 13, 2025, 2:30pm 10 An almost 80% decrease in test times is quite nice! Trying to figure out what to do with the command line options is probably one of the biggest obstacles to landing this. It would be really nice to fix this for good and scope cl::opt values to a LLVMContext or similar. That would be a really nice improvement in general. It would also open up the possibility of doing daemon mode in threads instead of processes, but I think there would be some problems with that around handling crashes and I/O. I’m not sure if anyone has done a design of how that would look though. I’m wondering if for prototyping purposes, it would be possible to hack up cl:: so that you can reset the command line options that are set to their default values. I don’t think that would be difficult to implement and it would allow for getting full results (eg running the entirety of check-llvm and similar). I would even be fine landing this with that approach, assuming there aren’t other issues with global state, and we have a plan to do the proper thing in the future, ideally with resourcing to finish it. 2 Likes nikic November 29, 2025, 5:09pm 11 Is cl::opt really the issue here? As long as we’re using multiple processes and not threads, we should already have the facilities to parse command line options multiple times (see ResetAllOptionOccurrences etc). The example @BStott mentioned is global state in WPD which does not use any of our standard facilities: llvm-project/llvm/lib/Transforms/IPO/WholeProgramDevirt.cpp at 8462cff40daf40e58d705f5d86d4e91ef6e6294c · llvm/llvm-project · GitHub This is a plain bug in the pass, and should be fixed. Passes should never use global state in this matter. For this particular case, WholeProgramDevirtCutoff should probably be replaced with a DebugCounter, as the option exists only for debugging. 3 Likes boomanaiden154-1 November 29, 2025, 6:47pm 12 nikic: As long as we’re using multiple processes and not threads, we should already have the facilities to parse command line options multiple times (see ResetAllOptionOccurrences etc). When I was looking through the API documentation I did not see ResetAllOptionOccurrences . This was never a major blocker, but that makes it pretty trivial. I misunderstood what the actual problem was (probably should have actually looked at the code..). Thanks for pointing that out. 1 Like boomanaiden154-1 November 29, 2025, 7:14pm 13 I’ve posted [WPD] Change Devirt Cutoff to use DebugCounter by boomanaiden154 · Pull Request #170009 · llvm/llvm-project · GitHub to fix the issue in WPD. 1 Like mingmingl-llvm December 2, 2025, 1:12am 14 As the author of original WPD change, I’m obliged to mention that debug counters requires -DLLVM_ENABLE_ASSERTIONS=ON but a release compiler typically don’t enable this. And technically using a debug counter isn’t a drop-in replacement; it requires users to seek for work arounds and takes additional work, especially for large real-world programs where debug assertions might fail the compilation at irrelevant places (which is observed and not very uncommon). That said, I’m onboard with the direction to reduce process creating overhead in regression tests, so approved [WPD] Change Devirt Cutoff to use DebugCounter by boomanaiden154 · Pull Request #170009 · llvm/llvm-project · GitHub to not block this effort. I haven’t looked into the details of the prototype PR linked in the RFC and might missed something pretty obvious, but how this work handles debug counter when multiple modules repeatedly uses the same debug counter? Would the same per-process global counter caveat apply? There is a method to reset counter state at llvm-project/llvm/include/llvm/Support/DebugCounter.h at 91e8780424c0e7c2f11f1adfc47915f975691d87 · llvm/llvm-project · GitHub , but it’s only called once by one optimizer pass (based on the cross-reference I had). nikic December 2, 2025, 10:44am 15 mingmingl-llvm: I haven’t looked into the details of the prototype PR linked in the RFC and might missed something pretty obvious, but how this work handles debug counter when multiple modules repeatedly uses the same debug counter? Would the same per-process global counter caveat apply? I don’t think the API for it exists right now, but debug counters provide a unified mechanism which can be globally reset, similar to what is possible with cl::opt and LLVM statistic counters. 1 Like resistor December 13, 2025, 2:12am 16 While I’m very interested in improving test time, I’m generically nervous about the idea of not re-executing the primary utilities-under-tests. One question that occurs to me is whether we could either daemonize, or simply integrate into some part of the test runner, things like not or even FileCheck itself, which would reduce process spawns with almost not loss of test coverage. 1 Like jrtc27 December 14, 2025, 1:43pm 17 For some tests this is probably true in that we really are trying to test the tools themselves. But for the vast majority of the tests I would argue we’re not actually trying to test the tools as tools, we’re just using the tools as a means to test specific parts of their behaviour. For example, everything in llvm/test/CodeGen doesn’t actually care one bit about llc, llc is just a low-level frontend. What it cares about is what assembly gets produced for a given IR input for a given target configuration, and llc is just the means to perform that. Especially given that llc itself isn’t even involved in a normal compilation process, normally we’re using the IR-to-assembly pipeline constructed by Clang itself (or another language frontend), so if testing the tools themselves were important then we’d invest in a bunch of tests for producing assembly via Clang. However, for something like llvm-objdump, we really are testing the end-to-end functionality of the tool as used in the real world. Or at least for the llvm-objdump tests themselves; contrast with all the tests, e.g. in lld/test, that use llvm-objdump as a means to evaluate the result rather than testing the tool itself. Also, what is the concern for things going wrong? If there’s leakage due to a lack of resetting/reinitialisation from one test to the next, that’s likely to show up in the form of non-determinism when running the tests, due to changes in test scheduling, especially once you factor in running with different amounts of parallelism across a variety of machines. Famous last words, but I’d expect it to be quite hard to have a bug in this area that consistently doesn’t show up across all buildbots, let alone end developers’ machines. As for deterministic errors like “this option no longer works”, if we have test coverage for it then that’ll show up as the test consistently failing the moment this approach gets used, so it’ll be found, and if we don’t have test coverage for it then whether we use this approach or not makes no difference to the behaviour of any test so it doesn’t matter (and if someone starts to write a test that depends on it then they should find that the test doesn’t give what they expect, so hunt down why and fix it). 1 Like dblaikie December 15, 2025, 10:52pm 18 Assuming we’re going to still to do single-thread per process execution of tests… then I’d suggest that failures (especially those that only reproduce in this multi-invocation-in-a-single-process mode, if we’re going to do the work to run them in isolation on failure to differentiate the failure mode) should print a command that reproduces the entire execution - the specific set of tests and order that the failed in. (based on past experience - had a test framework that did just this, parallel execution, but in separate processes (though without the test reordering that LLVM tests do (where they’re run longest-to-shortest, the framework I was in always ran tests in command line/source order) which probably produces more interesting cases), each process being single threaded - and certain orderings would produce failures where others wouldn’t - I added logging to list which tests were ran in each process and was only then able to stably reproduce the problem, isolate and fix it - I can still remember that bug 15+ years later because it was frustrating but really interesting to isolate and solve… ) 1 Like boomanaiden154-1 December 15, 2025, 10:58pm 19 dblaikie: if we’re going to do the work to run them in isolation on failure to differentiate the failure mode) should print a command that reproduces the entire execution - the specific set of tests and order that the failed in. This would be good to have regardless of whether or not we daemonize tests. I don’t think it would be hard or expensive to add per-worker logging to lit, and would help debug issues that are already occurring today, although mostly within lit itself (e.g., [lit] Ensure ulimit does not persist across tests by boomanaiden154 · Pull Request #164485 · llvm/llvm-project · GitHub ). 1 Like BStott December 18, 2025, 5:09pm 20 Hi everyone, After the holidays I’ll have some time to focus on landing this, so I think it would be good to consolidate the final design first. There are a few implementation details I would appreciate feedback on. The work to land this consists of: Adding the “daemon mode” functionality to the LLVM tools being tested. Adding support for the daemonized tools in Lit. Incrementally updating existing tests to use the new daemonized tools. Incrementally reducing cases of static state in LLVM that break the daemonized testing approach. Lit It seems that Lit’s core is supposed to be detached from LLVM itself, with LLVM-specific functionality (for example command substitutions) added by the local configuration. It seems like embedding support for the specific way that the LLVM daemonized tools end up working within Lit would contradict this goal. I propose introducing a SpecialCommand abstract class in Lit, representing any command that isn’t an executable invocation, and updating _executeShCmd to support these commands, including within command chains. These shall be provided through the Lit configuration. Additionally, the existing in-process commands in Lit can be refactored to use this system, meaning that they will also be able to be used in command chains. I implemented the daemon tools in Lit in a similar fashion in the prototype implementation, although the daemon tools are hardcoded in TestRunner.py . For chained process invocations, Lit starts all the processes at the same time, so the startup overhead of the second process in a chain can be overshadowed (thus alleviated) by the processing time of the first. For simplicity, in the prototype implementation I decided the special commands would be run synchronously and act as barriers between the regular commands. Lit waits for the last “real” command to finish to collect its output and then runs the special command, before providing its output to the next command. Do you think it would be worth trying to support this asynchronous behaviour for special commands too, i.e. allowing to start up the next command before the daemonized one finishes? I think it would introduce a lot of complexity. As running the special commands is a feature of Lit’s internal shell, the daemon testing will only be usable when Lit’s internal shell is enabled. In the prototype, I had Lit replace all invocations of opt and FileCheck with daemon invocations. For landing this, I think it would be better to have the daemonization be opt-in for each test, by providing a separate command (e.g. “%daemon-opt” that Lit tests which work with daemonization can call). This way, the removal of persistent state that breaks the daemon testing idea can be incremental, and tests can be updated to use the daemon proceses gradually. I agree with @jrtc27 that tests intended to test user-facing tools end-to-end should still invoke the tool as a separate process. What do you think? Daemon interface/IPC Handling stdin / stdout / stderr for the daemonized processes, as well as collecting the return code, is tricky. In the prototype, I used the following interface: Input: If Lit wants to provide a file to use as stdin , it sends “in.file {path}” to the daemon via stdin. This is used when the standard input of the command is a file. If Lit wants to provide a string directly as input to the daemon, it sends "in.bytes {len} {bytes}" to the daemon’s stdin . This is used when the standard input of the command is the output of the last, to avoid having to write it to a temporary file. As an exception, if the output of the last command is binary rather than text, it is sent via a file, as I couldn’t find a cross-platform way to pass binary data to a subprocess from the Python side. Output/error: The daemon tool’s output is sent via stdout as normal, followed by a special message to indicate that the daemon is finished - this also communicates the return code. Likewise, the error log is sent via stderr . Lit sits collecting the stdout and stderr from the daemon until it receives the “Task finished” message. Program arguments: Once the input is specified, the daemon is sent a "run {args}" command. The arguments are split up and passed as argc and argv . Crash handling: If the daemon tool exits unexpectedly, its return code is taken as the return code for the command. The way input was handled in the prototype was especially complicated. The reason I didn’t just have the input to the daemon tool be the daemon’s stdin is that LLVM’s input file reading waits until the input stream is closed, and the daemon’s stdin never closes, leading to a deadlock. One solution would be to change LLVM’s input file reading to stop when it finds a End-of-Transmission character (character code 4, a.k.a. ^D ) - this way, the standard input for the tool could be sent directly through the stdin pipe of the daemon, without requiring the complicated solution used in the prototype. However this would only be viable for text files, as binary files may contain ^D characters that aren’t meant to signal EOT. Do you think this change would be a good idea? LLVM tools We want a way to run the LLVM tools (FileCheck, opt, llc, clang, etc) in “daemon mode” with as little code repetition as possible. Each tool has initialization that should be performed once ( InitLLVM , initializing passes, etc.), as well as the code to run the tool with a given set of arguments and input, which will be called many times by the daemon. In the prototype, I decided to integrate the daemon running functionality into the normal versions of the tools, for example opt is started as a daemon by running opt --daemon . The majority of main is extracted into a run function which is called repeatedly by a shared runDaemonMode function implementing the daemon interface. The advantages of this approach are that no code has to be repeated and no changes to the build system are made - however, it may be undesirable for this functionality to be built into the tools themselves. Another idea would be to change the core implementation of each tool to be a static library exposing a function to initialize the tool (called once) and one to invoke it with a given set of arguments (called once per daemon invocation). Both the regular version of the tool and the daemon version will call into this library. Which of these approaches do you find preferable? Does anyone know of a better way to structure this? Thanks for all the discussion and feedback so far. next page → Related topics Topic Replies Views Activity [lit] check-all hanging LLVM Dev List Archives 23 248 January 8, 2019 [RFC] Testsuite in lldb & possible future directions LLDB 14 196 February 7, 2018 Proposal for GSoC project for improving llvm-test testsuite LLVM Dev List Archives 11 178 March 25, 2008 RFC: Dropping DejaGNU LLVM Dev List Archives 13 159 October 20, 2009 Testing Best Practices/Goals (in the context of compiler-rt) LLVM Dev List Archives 40 335 March 1, 2016 Home Categories Guidelines Terms of Service Privacy Policy Powered by Discourse , best viewed with JavaScript enabled | 2026-01-13T08:47:52 |
https://developers.reddit.com/apps/subscriber-count | 📈 Subscriber Sidebar | Reddit for Developers Readme Subscriber Sidebar A Devvit application to monitor your subscriber count and display it publicly in your subreddit's sidebar. Supports Mobile, Shreddit, and Old Reddit. Installation On the app's directory page , click the + Add to community button. Accept app permissions, and select the subreddit/community you wish to use the app with. Once installed, you will be automatically taken to the app's settings page. Note: Please allow up to 5 minutes for the sidebar to be updated with your subscriber information after initial installation. App Settings Widget Name / Sidebar Header Specify the name of the widget used for Shreddit and the Reddit app, and the header used for the sidebar on Old Reddit. Subscriber Customization Customize how your subscriber count is displayed. This setting is similar to customizing the subscriber and online users metric like before. Subscriber Refresh Choose how often to update the subscriber count. Default is every hour. Note: Each update will result in a mod log entry due to it making a wiki revision for the Old Reddit sidebar, quicker refreshes will mean more mod log updates. Display Preference Choose whether to display the subscriber count on Old Reddit, Shreddit, or both. Default is Shreddit / Reddit App. Changes may take 1-2 minutes to fully process. Take Note You will need to make sure that you have space for a new widget in your community, or you will not see the subscriber count in the sidebar. Once the widget is created, you can reorder the widgets as desired. On Old Reddit, the subscriber count will be added to the very top of the sidebar and cannot be moved. It uses a line separator (---) to assist with updating itself, so please do not delete it. Common Issues "Oops, something went wrong" when adjusting app settings This is most often due to issues with initializing or updating the sidebar wiki page on Old Reddit, and may be caused by the wiki page simply not existing. To check this, navigate to https://old.reddit.com/r/SUBREDDIT/about/edit/ (replacing SUBREDDIT with your subreddit) and look for the text box under the sidebar header. Make a change to the text box, scroll to the bottom of the page, then click save. This process creates the sidebar wiki page for Old Reddit if it doesn't exist, and forces an update to it if it does. Wait a few minutes, then check to see if the subscriber count is displaying in the sidebar when viewing your subreddit via the old.reddit.com URL. If it's displaying, you can reattempt changes to the app settings. Changelog v1.3 ADDED Option to turn off subscriber count for Old Reddit or Shreddit / Reddit App v1.2 ADDED Widget and sidebar now receive forced updates after changing app settings rather than waiting for next refresh Improved logic to mitigate situations where an update may duplicate the subscriber count in Old Reddit sidebar Improved logic to only update the widget and Old Reddit sidebar if the subscriber count has changed since the last update FIXED Issue preventing creation of subscriber widget when there was an existing image widget without a URL Issue preventing creation of subscriber widget when reinstalling the app Several Wiki-related errors v1.1 ADDED Configurable refresh duration Additional logging to help troubleshoot issues/errors v1.0 Initial Release Help & Support Contact WolfXemo with any questions, suggestions, or issues Terms & Conditions / Privacy Policy About this app WolfXemo Creator App identifier subscriber-count Version 1.3.1 Send feedback Terms and conditions Privacy policy Company Reddit, Inc. Reddit for Business Careers Press Contact Blog Community Reddit.com Reddit for Community Content Policy Help Center Moderator Code of Conduct Privacy & Safety Privacy Policy User agreement Transparency Report r/redditsecurity Other Terms and Policies Copyright 2026 Reddit Inc. All rights reserved. Company Reddit, Inc. Reddit for Business Careers Press Contact Blog Community Reddit.com Reddit for Community Content Policy Help Center Moderator Code of Conduct Privacy & Safety Privacy Policy User agreement Transparency Report r/redditsecurity Other Terms and Policies Copyright 2026 Reddit Inc. All rights reserved. | 2026-01-13T08:47:52 |
https://www.reddit.com/r/netsec/?f=flair_name%3A%22Cloud%20Security%22 | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://developers.reddit.com/apps/community-home | 🚀 Community Home + Topic Posts | Reddit for Developers #Community #General Readme Thanks for checking out Community Home! Report a bug via Direct Message Examples of Home Posts: Example of a Topic: https://www.reddit.com/r/FortNiteBR/comments/1h3t22i/chapter_6_season_1_鬼_hunters/ Example of a Topic (Compact): https://www.reddit.com/r/FortNiteBR/comments/1g8clxm/rfortnitebr_x_fortnitemares_2024/ Community Home Community Home adds new ways to showcase trending topics, list upcoming events, and send notifications to users in your subreddit Key Features 📌 Topics: Create trending topic summaries that signpost visitors to related content 🚀 Home: Pin an interactive post to spotlight topics happening now in the community 🕒 Reminders: Engage users with live countdown timers and reminder notifications 📈 Analytics: Gain insights through comprehensive engagement metrics Quick Start Guide Installation Click the “Add to community“ button at the top of the page Create Home Post Use the Create Home Post option found in the “ … ” menu in your subreddit Add your Community Home to highlights by using the moderator shield button Create Topics Use the Create Topic Post option found in the “ … ” menu in your subreddit Take a break, that’s it! 👏 Full Documentation 📌 Topics Creating a topic Use the Create New Topic menu option This is found in the “ … ” menu in your subreddit You can give your new topic a title and search phrase Editing topic details Open a topic post and use the Edit button in bottom right You can edit settings including: Search Phrase Subtitle Linked Posts (Megathreads / Status Updates) Start / End Times Posting updates to a topic Open a topic post and use the Edit button in bottom right, then: Select the menu options across the bottom to: Post a new update, shown with a LIVE indicator for first hour Post a new Live Poll Post a new Image Poll Editing updates in a topic Open a topic post and locate the update you'd like to edit Press the update's icon (eg. your Snoovatar) to see a dropdown Compact Mode: Press the top right of an update to see dropdown Adding countdown timers and reminders Open a topic post and use the Edit button in bottom right, then: Select "Add Schedule" Add a start time that is in the future You can type phrases like: "now", "in 4 hours", "tomorrow", "in 2 days" "today 11am", "tomorrow 2:25pm", "next tuesday at 14:52" "14-aug-2024 at 7pm ET", "next tuesday at 09:00 in new york" View more examples here Enable Use Start Time to show it in the topic This will add a countdown timer and reminder button to the topic Changing the appearance of a topic Open a topic post and use the Edit button in bottom right, then: Select the menu options across the top to: Change the Key Color of the Topic Update or remove custom topic images Show or hide the Title Removing a topic Removing a topic post from the moderator shield will remove it from Home Reminders for removed topics will not be sent 🚀 Home This interactive post automatically displays topics sorted by newest first Topics with a start or end time enabled will take priority Thumbnails are automatically generated, or can be replaced with a custom image 🕒 Reminders Topics with future start times will display a Remind Me button Users can set reminders for upcoming events or updates The app automatically sends reminder notifications before the time starts 📈 Analytics Use the View Analytics menu option from any topic to see engagement data that includes: Clickmap information for individual topics Totals of how many reminders have been sent Upvotes and comments totals from linked posts ✅ Best Practices Create Topics to advise of subreddit restrictions when experiencing a surge of visitors Set start times for Topics about upcoming events to allow users to set reminders Add a start or end time to Topics to show them in Home as Events Cheat Sheet Q: Which Reddit platforms are supported? A: Desktop, Mobile, iOS, Android Q: How many Home posts or Topics can I create? A: There is no limit! Q: Can subreddit users create Home Post or Topics? A: These posts can only be submitted by moderators Q: What happens to Topic reminders if I remove the post? A: Related reminders are cancelled Q: What happens to Topic reminders if I change start time? A: Reminders will send at the new time Q: How old Reddit users set Topic reminders? A: Reminders can be set up from the Topic's comments Q: Does this app collect user data? A: No Q: Is a hotdog a sandwich? A: Yes ❣️ Support and Feedback Questions, suggestions, or issues: Direct Message Privacy policy: https://www.reddit.com/r/Xenc/w 🐋 About this app Xenc Creator App identifier community-home Version 1.0.10 Send feedback Terms and conditions Privacy policy Company Reddit, Inc. Reddit for Business Careers Press Contact Blog Community Reddit.com Reddit for Community Content Policy Help Center Moderator Code of Conduct Privacy & Safety Privacy Policy User agreement Transparency Report r/redditsecurity Other Terms and Policies Copyright 2026 Reddit Inc. All rights reserved. Company Reddit, Inc. Reddit for Business Careers Press Contact Blog Community Reddit.com Reddit for Community Content Policy Help Center Moderator Code of Conduct Privacy & Safety Privacy Policy User agreement Transparency Report r/redditsecurity Other Terms and Policies Copyright 2026 Reddit Inc. All rights reserved. | 2026-01-13T08:47:52 |
https://replit.com/enterprise | Replit for Enterprise | Enterprise Development Platform Agent Products Agent Design Database Publish Security Integrations Mobile For Work Teams Replit for teams to build together Enterprise Replit with Enterprise-grade security & controls Use Cases Business Apps Rapid Prototyping Roles Enterprise PM Designers Operations Software Developers Small Businesses SMB owners Founders Resources Get Started Docs Community Expert Network Inspiration Customer Stories Gallery Blog News Pricing Careers Agent Contact sales Log in Sign up Products For Work Resources Pricing Careers Contact sales Log in Start building End Your Software Backlog. Empower your entire organization to create applications by simply describing them. Replit's enterprise platform translates your description into production-ready software, securely and at scale. Contact Sales First Name (required) Last Name (required) Work Email (required) Phone Number (optional) Message (optional) Contact Sales Loved by 40 million app creators, including teams at: Replit is the most secure agentic platform for production-ready apps Replit’s got everything you need to make building & launching your app a breeze — build & refine your apps through conversing with Agent. Every Replit app comes with a built in database, user-authentication, integrations and Enterprise Grade security. Self-debugging & autonomous agent allows anyone to build complex production grade apps Anyone from your Product, Design or Business teams can build apps and tools within a few prompts. Agent can autonomously handle complex tasks and debugging so you don't have to. In-built Auth, Database, Hosting & Monitoring services make pushing an app to production a breeze Every project includes a pre-configured, production grade Auth and Database that grows with your project-no separate setup or installation needed. You can also easily connect to services like Stripe, Open AI and more. Enterprise controls & security for your apps Replit platform has SSO/SAML, SOC2 & all the standard Enterprise admin controls. Plus, pre deployment security screening, secure in-built services and better defaults ensure the apps you built remain secure too. Jon Humphrey, Rokt SVP of Solutions and Operations "I sat there on an iPad mini and I deployed a fully functional end-to-end application with Google OAuth in about a day. And I have no background in engineering. That was my 'holy shit' moment where I said, 'My goodness, I can't believe I just did that.'" Mike Messenger, Zillow Director of Field Operations “Replit empowers our operations teams to quickly create enterprise-grade apps, no-code needed.” Key Vaidya, Hg Capital Portfolio CTO “The ability to go from idea to working application in minutes has opened new possibilities for innovation across our portfolio. We're seeing apps built in 45 minutes that save teams hours every week." From rapidly prototyping MVPs to building internal tools or customer facing apps, the possibilities are endless Replit’s got everything you need to make building & launching your app a breeze — build & refine your apps through conversing with Agent. Every Replit app comes with a built in database, user-authentication, integrations and Enterprise Grade security. Rapid Prototyping Rapidly prototype your product ideas for customer demos and feedback. Launch it as production ready app or hand it off to engineering for continued development Internal Tools Build that perfect tool you always wanted and simplify your workflow and increase your productivity Customer facing apps Build new, production-ready apps for your customers much faster via faster prototyping and more seamless handoff from product to engineering teams Purchase Replit Enterprise Through Your Preferred Cloud Marketplace Replit Enterprise is now available on Azure Marketplace and Google Cloud Marketplace, making it easier than ever to procure our agentic development platform through your existing cloud provider relationship. Streamlined procurement — Use existing cloud credits, consolidated billing, and pre-approved vendor relationships Available on Azure Marketplace and Google Cloud Marketplace Enterprise features include — SSO/SAML, SCIM provisioning, dedicated support, and advanced privacy controls Empower your Product, Design & Business teams to bring their ideas to life Product Teams Quickly prototype and test your product ideas with clickable prototypes to speed up customer demos, gather feedback faster, and dramatically shorten your product development cycle. Don’t just hand off a PRD to engineering—hand off working source code. Designers Bring your Figma designs to life and simplify that developer handoff by building out a clickable prototype. Now your designs can be transferred to product with perfect fidelity. Sales & Marketing Teams Build that perfect tool you always wanted and simplify your workflow and increase productivity. Where you want to analyze sales call transcripts or generate quick landing pages for marketing, you can do it all with a Replit app Operations Teams Build that perfect tool you always wanted and simplify your workflow and increase productivity. Where you want to build a custom dashboard to analyze support tickets, or a procurement tool, you can build it all with a Replit app. Request a hackathon Transform your organization in 4 hours Solve real business challenges Cross-functional teams build apps that address your organizations actual needs and pain points. No coding required Anyone can participate regardless of technical background—vibe coding makes programming accessible to all. Deploy live applications Teams go from idea to working application in just 4 hours, ready to showcase and implement. Request a Hackathon Try Replit now Replit empowers anyone with an idea to become a creator, while giving professional designers the freedom to creatively explore and build — without being held back by code or the limitations of design tools: Start building Handy Links About us Vibe Coding 101 Help How to guides Import from GitHub Status Additional resources Brand kit Partnerships Legal Terms of service Commercial agreement Privacy Subprocessors DPA Report abuse Connect X / Twitter Tiktok Facebook Instagram Linkedin Scroll to top All rights reserved. Copyright © 2026 Replit, Inc. | 2026-01-13T08:47:52 |
https://github.com/llvm/llvm-test-suite | GitHub - llvm/llvm-test-suite Skip to content Navigation Menu Toggle navigation Sign in Appearance settings Platform AI CODE CREATION GitHub Copilot Write better code with AI GitHub Spark Build and deploy intelligent apps GitHub Models Manage and compare prompts MCP Registry New Integrate external tools DEVELOPER WORKFLOWS Actions Automate any workflow Codespaces Instant dev environments Issues Plan and track work Code Review Manage code changes APPLICATION SECURITY GitHub Advanced Security Find and fix vulnerabilities Code security Secure your code as you build Secret protection Stop leaks before they start EXPLORE Why GitHub Documentation Blog Changelog Marketplace View all features Solutions BY COMPANY SIZE Enterprises Small and medium teams Startups Nonprofits BY USE CASE App Modernization DevSecOps DevOps CI/CD View all use cases BY INDUSTRY Healthcare Financial services Manufacturing Government View all industries View all solutions Resources EXPLORE BY TOPIC AI Software Development DevOps Security View all topics EXPLORE BY TYPE Customer stories Events & webinars Ebooks & reports Business insights GitHub Skills SUPPORT & SERVICES Documentation Customer support Community forum Trust center Partners Open Source COMMUNITY GitHub Sponsors Fund open source developers PROGRAMS Security Lab Maintainer Community Accelerator Archive Program REPOSITORIES Topics Trending Collections Enterprise ENTERPRISE SOLUTIONS Enterprise platform AI-powered developer platform AVAILABLE ADD-ONS GitHub Advanced Security Enterprise-grade security features Copilot for Business Enterprise-grade AI features Premium Support Enterprise-grade 24/7 support Pricing Search or jump to... Search code, repositories, users, issues, pull requests... --> Search Clear Search syntax tips Provide feedback --> We read every piece of feedback, and take your input very seriously. Include my email address so I can be contacted Cancel Submit feedback Saved searches Use saved searches to filter your results more quickly --> Name Query To see all available qualifiers, see our documentation . Cancel Create saved search Sign in Sign up Appearance settings Resetting focus You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} llvm / llvm-test-suite Public Notifications You must be signed in to change notification settings Fork 381 Star 223 License View license 223 stars 381 forks Branches Tags Activity Star Notifications You must be signed in to change notification settings Code Pull requests 29 Actions Security Uh oh! There was an error while loading. Please reload this page . Insights Additional navigation options Code Pull requests Actions Security Insights llvm/llvm-test-suite main Branches Tags Go to file Code Open more actions menu Folders and files Name Name Last commit message Last commit date Latest commit History 4,874 Commits ABI-Testsuite ABI-Testsuite Bitcode Bitcode CTMark CTMark ClangAnalyzer ClangAnalyzer External External Fortran Fortran LLVMSource LLVMSource LNTBased LNTBased MicroBenchmarks MicroBenchmarks MultiSource MultiSource SingleSource SingleSource autoconf autoconf cmake cmake litsupport-tests litsupport-tests litsupport litsupport test-suite-externals test-suite-externals tools tools utils utils .arcconfig .arcconfig .gitignore .gitignore CMakeLists.txt CMakeLists.txt CollectDebugInfoUsingLLDB.py CollectDebugInfoUsingLLDB.py CompareDebugInfo.py CompareDebugInfo.py DiffOutput.sh DiffOutput.sh FindMissingLineNo.py FindMissingLineNo.py GenerateReport.pl GenerateReport.pl HTMLColDiff.pl HTMLColDiff.pl HashProgramOutput.sh HashProgramOutput.sh LICENSE.TXT LICENSE.TXT Makefile Makefile Makefile.FORTRAN Makefile.FORTRAN Makefile.common Makefile.common Makefile.config.in Makefile.config.in Makefile.dummylib Makefile.dummylib Makefile.f2c Makefile.f2c Makefile.nagfortran Makefile.nagfortran Makefile.programs Makefile.programs Makefile.rules Makefile.rules Makefile.tests Makefile.tests ModuleInfo.txt ModuleInfo.txt ParseMultipleResults ParseMultipleResults PrintLineNo.sh PrintLineNo.sh README.txt README.txt RunSafely.sh RunSafely.sh TEST.aa.Makefile TEST.aa.Makefile TEST.aa.report TEST.aa.report TEST.beta-compare.Makefile TEST.beta-compare.Makefile TEST.beta-compare.report TEST.beta-compare.report TEST.buildrepo.Makefile TEST.buildrepo.Makefile TEST.dbg.Makefile TEST.dbg.Makefile TEST.dbg.report TEST.dbg.report TEST.dbgopt.Makefile TEST.dbgopt.Makefile TEST.dbgopt.report TEST.dbgopt.report TEST.example.Makefile TEST.example.Makefile TEST.ipodbgopt.Makefile TEST.ipodbgopt.Makefile TEST.jit.Makefile TEST.jit.Makefile TEST.jit.report TEST.jit.report TEST.libcalls.Makefile TEST.libcalls.Makefile TEST.libcalls.report TEST.libcalls.report TEST.lineinfo.Makefile TEST.lineinfo.Makefile TEST.llc.Makefile TEST.llc.Makefile TEST.llc.report TEST.llc.report TEST.llcdbg.Makefile TEST.llcdbg.Makefile TEST.m2regllcdbg.Makefile TEST.m2regllcdbg.Makefile TEST.nightly.Makefile TEST.nightly.Makefile TEST.nightly.report TEST.nightly.report TEST.optllcdbg.Makefile TEST.optllcdbg.Makefile TEST.optllcdbg.report TEST.optllcdbg.report TEST.simple.Makefile TEST.simple.Makefile TEST.simple.report TEST.simple.report TEST.typesafe.Makefile TEST.typesafe.Makefile TEST.vtl.Makefile TEST.vtl.Makefile configure configure default.profraw default.profraw default.reference_output default.reference_output filepp filepp instant.txt instant.txt lineinfo.xfail lineinfo.xfail lit.cfg lit.cfg lit.site.cfg.in lit.site.cfg.in View all files Repository files navigation README License LLVM "test-suite" Repository ---------------------------- Please see the LLVM testing infrastructure guide: https://llvm.org/docs/TestSuiteGuide.html for more information on the contents of this repository. About No description, website, or topics provided. Resources Readme License View license Uh oh! There was an error while loading. Please reload this page . Activity Custom properties Stars 223 stars Watchers 288 watching Forks 381 forks Report repository Releases 287 tags Packages 0 No packages published Uh oh! There was an error while loading. Please reload this page . Contributors 224 Uh oh! There was an error while loading. Please reload this page . + 210 contributors Languages RPC 94.1% C 3.1% Fortran 1.2% C++ 1.1% AGS Script 0.4% Awk 0.1% Footer © 2026 GitHub, Inc. Footer navigation Terms Privacy Security Status Community Docs Contact Manage cookies Do not share my personal information You can’t perform that action at this time. | 2026-01-13T08:47:52 |
https://www.suprsend.com/post/comparing-notification-infrastructure-marketing-automation-tools-a-guide-to-choose-the-right-platform-for-your-product | Comparing Notification Infrastructure & Marketing Automation Tools: A Guide to Choose the Right Platform for Your Product Product FEATURES Template Engine Powerful template editors for all channels App Inbox Fully customizable inbox for your app & website Analytics Deep data insights on notification performance Logs Real-time notifications logs for all channels Smart Routing Reach users where they are Branding Seamlessly manage multi-brand customization Workflows Craft complex notification workflows Bifrost Run notifications natively on data warehouse Preferences Develop user focused notifications Integrations Integrate any channel and provider within mins Solutions BY USECASES Transactional Real-time alerts like authentication, activity updates Batching & Digest Aggregate multiple alerts into one Collaboration & Action Alerts on cross-user activity Scheduled Notifications One-time or recurring alerts like reminders Multi-tenant Alerts tailored to your customer's preferences Announcement / Newsletters Feature releases, achievements, product & policy updates Pricing Docs Customers Blog Login Get Started For Free Login Sign up Outlook on Notifications Comparing Notification Infrastructure & Marketing Automation Tools: A Guide to Choose the Right Platform for Your Product Nikita Navral • February 5, 2025 TABLE OF CONTENTS At SuprSend, we often come across questions about the distinctions between the traditional Marketing Automation Tools (MATs) and the emerging Notification Infrastructure Platforms. In this comprehensive guide, we aim to explain the differences between the two and provide insights into why notification infrastructure platforms are gaining traction among product managers and engineering teams. The Evolution of Customer Engagement For a decade, Marketing automation tools (MATs) such as Braze, Customer.io, Iterable, and Clevertap have dominated the market, offering robust solutions for sending targeted marketing campaigns. These campaigns, often promotional in nature, help in customer retention and engagement - important to any business. At the same time, businesses are also required to send out their product notifications related to transactional alerts and updates in customers’ accounts. Often, these notifications are mission critical for businesses. For example, sending payment reminders, approval alerts or notifying a customer when an update / comment is posted so the user can take appropriate action. While MATs are proficient in addressing promotional use cases and engaging with customers on a marketing level, they fall short when it comes to handling complex product notifications crucial for product success. There is a new wave of platforms excelling in this domain, called notification infrastructure, which is redefining how product and engineering teams build and maintain product notifications, without having to build notification services internally. As businesses navigate this notification evolution, understanding where MATs fall short and how notification infrastructures work better become very important to help you choose the right solution for your needs. Understanding the Basics At the core, notification infrastructure platforms and marketing automation tools (MATs) share a common goal—connecting businesses with their audience. While they may share some common goals, their functionalities and usecases differ significantly. Marketing Automation Platforms - A Brief Overview Marketing Automation Platforms (MATs) have proven instrumental in orchestrating targeted and effective marketing campaigns. Here's a snapshot of what MATs are adept at: User Segmentation: MATs excel at storing and segmenting users based on diverse criteria, enabling businesses to tailor their messages for maximum impact. One-Time Campaigns: They facilitate the creation and execution of one-time campaigns, driving specific actions such as new product launch or cart additions. These are primarily sent to mobile push and emails, followed by SMS and whatsapp. Automated Notifications for Cohort Changes: MATs automate notifications triggered by user entry or exit from a cohort, and sending them timely and relevant communication. Quick Experiments and A/B Testing: MATs empower marketers to conduct rapid experiments and A/B tests to optimize funnels and boost conversions. Multi-Step Campaign Journeys: With a visual workflow builder, MATs allow the creation of multi-step campaigns, offering power of context based engagement. Email based User Preferences: They enable collecting user preferences on externally hosted pages, particularly for promotional use cases, enhancing easy unsubscription management. As it is evident, MATs provide a good solution for personalized promotional messages at scale to a cohort of users based on their properties or activity / inactivity on the product - building a good argument on why Marketers should use them instead of building one in-house. To some extent, MATs can be used where the product notifications are handful and simple. However, if you still end up building a notification system in-house to accommodate complex usecases, or you are using your current marketing automation tool as a delivery node after handling complex logics at your end, it is advisable to consider adopting a specialized product notification platform. Notification Infrastructure Platforms - A Brief Overview Born from our pain and experience of building notification services in-house in our previous companies, we understand the need and complexities involved. Many companies invest countless hours re-inventing the wheel to get notifications right and sometimes have a dedicated team handling their in-house notifications, even though they're not notification companies. To give an example, you may have read about what goes behind Slack’s simple yet highly effective notifications alerts. Notifications navigate across browsers, devices, channels, statuses, customer preferences, and many other conditions before that sweet Slack chime reaches your ear. Slack Notifications Flowchart This is where SuprSend comes in – we fill the gaps left by MATs and internally built services, and provide a sophisticated infrastructure that allows you to build Slack like notifications without custom development at your end, and help you to deliver the right customer experience. Let’s look at some areas where Notifications Infrastructure Platforms differ from Marketing Automation Tools. Fundamental differences between MATs and NIPs 1. Extended Channels and Integrations Capabilities MATs Limitation: Traditional MATs focus on sending notifications to conventional channels such as push, email and social channels, but lag in adopting newer communication channels. NIPs Solution: NIPs are designed to be integrations first, integrating seamlessly with existing as well as emerging communication channels like Slack, Microsoft Teams, or in-app notification centers. For instance, they allow businesses to send notifications directly to team collaboration tools like Slack in addition to email, ensuring a more comprehensive and up-to-date communication strategy. Not just this, NIPs provide native integration with various data sources (like Segment, Mixpanel, Data warehouses), notification data destinations (like AWS S3, Segment). This flexibility empowers you to effortlessly manage data across platforms of your choice. 2. Real-Time In-App Notification Feed MATs Limitation: MATs typically excel in scheduled or triggered campaigns but lack infrastructure of real-time in-app notification feeds. If they provide, it is a solution that does not look native to your website. This could hinder user engagement within the application. NIPs Solution: NIPs recognize the importance of alerts within app and offer features like real-time in-app notification feed along with out-of-app channels. This ensures delivering a seamless experience, such as if the user is active in the application, they receive alerts within the application, and if offline, will get alerts on out-of-app channels like email or Slack. Besides, NIPs provide pre-built components as well as headless APIs, making it possible to deliver a native looking experience for in-app feed. Try SuprSend Inbox Playground 3. Multi-Tenancy in Notifications MATs Limitation: Marketing Automation Tools (MATs) typically lack robust multi-tenant architecture, making them unsuitable for organizations with enterprise customers. Without multi-tenancy support, MATs do not provide notification customizations (on branding, preferences, vendors etc) tailored to individual tenants' needs. This limitation means engineering teams have to build their own multi-tenant architecture. NIPs Solution: Notification Infrastructure Platforms (NIPs) address this limitation by providing a robust multi-tenant system out of the box. This feature gives flexibility to tailor communication strategies at per-tenant level. You can read more about multi-tenant notifications in our whitepaper. 4. Designing Complex Workflows MATs Limitation: Marketing Automation Tools (MATs) focus on sending campaigns and that’s why they lack support to build intricate workflows with complex logic. The absence of support for multi-stakeholder collaboration, batching, throttling, and webhooks can burden engineering teams with the responsibility of building workflows in the code. NIPs Solution: Notification Infrastructure Platforms (NIPs) excel in handling complex workflows, involving multi-tenant and multiple stakeholders. Besides, NIPs provide intuitive nodes for batching, throttling, delays, channel routing, reminders, webhooks, and much more. With an advanced workflow engine, NIPs engineering & product teams create quality notifications that are delivered at the right time, frequency, and manner, and are sure to delight customers. 5. Advanced Preference Center MATs Approach: Marketing Automation Tools (MATs) typically offer email based unsubscription hosted outside of the product. While this allows users to opt out of specific email communications, it lacks sophistication in managing preferences across multiple channels and categories. NIPs Advantage: Notification Infrastructure Platforms (NIPs) redefine notification preferences with a highly nuanced preference engine where users can set their preferred channel, category or frequency (eg. instant alerts, hourly or daily digest). You can seamlessly integrate a native looking preference center within your product. The NIPs preference center provides a pre-built components as well as APIs with extensive customization options - eg. for tenants, admin, and departments. This granular control ensures that notifications are delivered in alignment with preferences for users and organizations, enhancing overall engagement and satisfaction. 6. Observability and Analytics MATs Limitation: Designed primarily from a campaign perspective, MATs do not provide observability into each and every notification processed. This oversight can pose challenges in debugging and monitoring, particular for mission critical product notifications. NIPs Solution: In contrast, NIPs place a strong emphasis on observability, providing granular logs into each and every notification - at each workflow step executed, failure errors, latencies, and more. They offer integration with monitoring tools like Datadog and NewRelic, enabling real-time alerts in the event of failures. Additionally, companies often require syncing this notification information back to their data stores for further analytics or showing information to their customers, and NIPs provide mechanisms like webhooks, syncing data to S3 bucket, data destinations like Segment to facilitate these requirements. 7. Reliability MATs Limitation: While MATs are capable of handling large volumes necessary for promotional campaigns, they may not offer the same level of reliability needed for critical transactional communications. NIPs Solution: Reliability is a cornerstone for product communications, where delivery of each and every notification becomes important. NIPs incorporate features such as vendor fallback mechanisms, automated retries, and multiple swimlanes to prioritize delivering time sensitive alerts over bulk notifications, ensuring consistent and dependable delivery of notifications in events of failures. 8. Developer-First Approach MATs Limitation: Typically built for marketers, MATs do not give a developer-first approach, limiting the ability to automate the notification development and providing controls that developers would like to have. NIPs Solution: NIPs recognize the importance of automation in building business notifications similar to any other product features. They provide comprehensive APIs & SDKs that empower developers to automate template creation, workflows, preferences, and seamlessly integrate notification processes into their CI/CD pipelines, aligning more closely with modern software development practices. 9. Separate Workspaces MATs Limitation: MATs may lack the capability to provide distinct workspaces for staging and production environments. Works well for marketers to run, test and optimize campaigns in a high-touch process, but not ideal for notifications related to product features. NIPs Solution: NIPs address this limitation by offering separate workspaces for staging and production environments. This ensures a controlled and secure deployment process, allowing businesses to test and refine their notification strategies in a staging environment before rolling them out to the production environment. This allows a more reliable and risk-mitigated deployment process, crucial for organizations with good development practices. 10. Streamlining Notifications in a large organization MATs Limitation: Marketing Automation Tools (MATs) are typically utilized by Marketing and Growth teams, to build and oversee campaign effectiveness. On the contrary, product notifications often originate from multiple product teams within an organization, each responsible for specific features and respective notifications. This decentralized structure can pose challenges in streamlining processes, especially in organizations with multiple teams across different product lines. NIPs Solution: Notification Infrastructure Platforms (NIPs) offer a centralized solution for organizing notifications across various product teams and lines. With tools for managing multiple projects, environments, Role-Based Access Controls (RBACs), permissions, audit trails, and cost centers, NIPs are ideal for managing notifications in complex organizations. This centralized approach ensures efficient coordination and alignment of notification strategies, enhancing overall communication effectiveness and productivity. Conclusion In conclusion, the emergence of notification infrastructure platforms like SuprSend offer a fresh perspective on notification solutions, particularly for modern products. While marketing automation tools can be used to some degree for product notifications, exploring specialized platforms can provide greater control and flexibility for your notification strategies, and you won’t run into rewriting the service after every few years. As you weigh your options, consider your specific needs, such as delivering product-triggered notifications reliably at scale or getting pre-built components for delivering native experiences, or requiring out-of-the-box capabilities to build sophisticated workflows. By doing so, you can choose the platform that is adaptable to your development cycle and empowers your team to deliver exceptional notification experiences. If you're intrigued at this point, we would love to have you explore SuprSend and discover how it can elevate your notification strategy. Watch out this space to learn about how we are uniquely solving engagement notifications. Share this blog on: Written by: Nikita Navral Co-Founder, SuprSend Implement a powerful stack for your notifications Get Started For Free Book Demo Company About us Signup Login Integrations Pricing Security Privacy Terms Contact Us Support SuprSend for Startups API Status Sign Up Channels Email SMS Notification Inbox Android Push iOS Push Web Push Xiaomi Push Whatsapp SDK Python SDK Node.js SDK Java SDK Android SDK React Native SDK iOS SDK Flutter SDK Go SDK Resources Documentation Changelog Blogs Write for us SMTP Error Codes SMS Providers Comparisons Email Providers Comparisons SMS Providers Alternatives Join us on Slack We are building a community of developers and product builders from across the globe to make notifications a pleasant experience. © 2025 All rights reserved. SuprStack Inc. By clicking “Accept All Cookies” , you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts. View our Privacy Policy for more information. Preferences Deny Accept Privacy Preference Center When you visit websites, they may store or retrieve data in your browser. This storage is often necessary for the basic functionality of the website. The storage may be used for marketing, analytics, and personalization of the site, such as storing your preferences. Privacy is important to us, so you have the option of disabling certain types of storage that may not be necessary for the basic functioning of the website. Blocking categories may impact your experience on the website. Reject all cookies Allow all cookies Manage Consent Preferences by Category Essential Always Active These items are required to enable basic website functionality. Marketing Essential These items are used to deliver advertising that is more relevant to you and your interests. They may also be used to limit the number of times you see an advertisement and measure the effectiveness of advertising campaigns. Advertising networks usually place them with the website operator’s permission. Personalization Essential These items allow the website to remember choices you make (such as your user name, language, or the region you are in) and provide enhanced, more personal features. For example, a website may provide you with local weather reports or traffic news by storing data about your current location. Analytics Essential These items help the website operator understand how its website performs, how visitors interact with the site, and whether there may be technical issues. This storage type usually doesn’t collect information that identifies a visitor. Confirm my preferences and close Get 10% OFF on your next order Subscribe to our newsletter and receive a 10% OFF coupon to use on your next order. Please check your email for your 10% OFF coupon Oops! Something went wrong while submitting the form. | 2026-01-13T08:47:52 |
https://discourse.llvm.org/t/rfc-llvm-link-llvm-dylib-should-default-to-on-on-posix-platforms/85908?u=nikic | [RFC] LLVM_LINK_LLVM_DYLIB should default to ON on Posix platforms - LLVM Project - LLVM Discussion Forums LLVM Discussion Forums [RFC] LLVM_LINK_LLVM_DYLIB should default to ON on Posix platforms LLVM Project rnk April 17, 2025, 11:01am 1 TL;DR: We should make LLVM_LINK_LLVM_DYLIB (and potentially later CLANG_LINK_CLANG_DYLIB ) default to ON in CMake for non-Windows platforms. While all tradeoffs have pros and cons, I think it’s clear at this point that the benefits outweigh the negatives. The DSO build makes building LLVM more accessible to beginners, and I believe that’s important to the long-term health of the project, so we should make it the default. These are the benefits of using the libLLVM DSO: The LLVM DSO uses much less diskspace (18GiB vs 3.1GiB for Linux Rel+asserts). This multiplies by ~5x if you enable debug info. Linking the LLVM tools with the DSO is faster and uses less memory . Linking the tools is a major bottleneck for the check-llvm/clang/mlir testing workflow. Running multiple high-memory link steps inhibits development on entry-level hardware, which beginners tend to have. Using the LLVM DSO by default aligns our default build config with Debian , Fedora , and other Linux distro build configs, which all use libLLVM*.so. If you are a vendor who cares about package size, this enables creating a smaller, more modular collection of toolchain packages to distribute. The downsides of the libLLVM DSO are: Minor hit to startup time on ELF platforms . Recent data says this is marginal, but I’ll expand on this below, since the received wisdom is that this is a major blocker. Non-ELF platforms generally have faster loaders, or collude with the kernel to share relocated pages between processes. The DSO increases the number of compile actions required to rebuild a single tool binary, slowing down iteration times when working with small test inputs. For example, if I make a change to IR/ headers, and I can test my change with llvm-as/dis or opt , the static build would allow me to test my changes without building the entire LLVM DSO, which includes llvm/lib/Target. Static linking, or fine-grained shared linking (BUILD_SHARED_LIBS=ON), can offer faster iteration times in cases like this. The DSO build doesn’t validate internal library dependencies. In the static build, static links often fail if you forget a library dependency. This helps us maintain boundaries between layers in LLVM’s internal architecture. Alternative, unsupported build systems such as Bazel require accurate dependency information. This gap can also be covered with continuous BUILD_SHARED_LIBS testing, which I believe we already have on buildbot, because I broke it at some point. Tool binaries are less hermetic. They already search for paths relative to the executable path, but if you add shared library dependencies, that’s one more path to manage if you want to copy a tool binary around. IIRC we do this in a regression test, which IMO is questionable. The DSO limits whole-program visibility in LTO-enabled builds. This is a major consideration for a vendor attempting to build a highly optimized toolchain binary, but is probably not a major consideration for our default build configuration. Regarding the startup time overhead, this came up on LKML in 2021 , and it resulted in this widely circulated post from Linus Torvalds “shared libraries are not a good thing in general” . Regardless, all the major Linux distros (Fedora, Debian ( see llvm-toolchain package rules )) still use this configuration, presumably because it allows them to split up the toolchain into smaller, more modular packages (clang, llvm, lld, the rest), which use far less disk space. However, recent benchmark data from @mstorsjo shows that this startup time hit is low. For short-lived executions like clang --version , the mean wall time goes from 9.5ms to 12.5ms, resulting in a 3ms overhead or +31%. However, if you add 3ms to a 1sec compilation action, we’re talking about a 0.3% perf hit. The overhead is lost in the noise on large compile actions, such as the ~20s sqlite3.c aggregate compilation tested in that benchmark. I think part of why it is received wisdom that dynamically linked LLVM builds are slow comes from experience running the LLVM test suite, where the dynamic linker often has been the bottleneck, because our test processes are short-lived and process startup is the bottleneck. I did a quick A/B comparison of check-llvm , and my numbers show that the DSO build is faster, but I don’t trust my configuration and this deserves external validation. I think 3ms of startup overhead is something worth optimizing, but this seems like a tradeoff that a vendor should consider, not something people doing their first LLVM build should have to think about. I believe there is also additional room to explore optimization flags such as -Bsymbolic-funcitons-non-weak , -fvisibility-inlines-hidden , as well as finishing up the LLVM_ABI annotations so we can build with -fvisibility=hidden . We can also continue optimizing dynamic relocations, as @chandlerc recently did in a series of PRs improving Clang’s builtin string tables a few months back. These are all good next steps, but I think the pros already outweigh the cons, so they don’t need to be prerequisites. Regarding platform support, LLVM_LINK_LLVM_DYLIB is not supported on Windows. Once we have accurate LLVM_ABI annotations (I hope this happens), then we can re-evaluate turning this on for Windows. Simply put, static linking is a bad default for LLVM today. The build directories are too big, and the many redundant static links use a lot of memory. Flags to optimize the linker are already explicitly mentioned in our getting started guide to work around these large static link steps. New developers regularly complain about build directory size ( 1 ), and most recently, I personally had a 111GB build directory that caused me to explore merging clang unit tests . In order to make the project more accessible, we really should adjust our defaults so that building LLVM doesn’t require so many resources. Using large shared libraries by default would be a good step in that direction. cc relevant folks @mstorsjo @arsenm @nikic @tstellar @MaskRay @compnerd 11 Likes LLVM Weekly - #590, April 21st 2025 RFC: Require Pull Requests for all llvm-project commits nikic April 17, 2025, 12:48pm 2 I think this is a reasonable change, for the reasons you have outlined. Another advantage is that if you are building LLVM with LTO, using the dylib build means you only have to perform one big LTO link, instead of repeating it a few dozen times for each tool. 2 Likes Hardcode84 April 17, 2025, 1:35pm 3 I don’t want to block anyone, or participate in such discussion at all, really, so you can consider this an anonymous user feedback. But I debugged a lot of crashes caused by programs loading multiple incompatible versions of libllvm pulled from different package managers (e.g. llvmlite rebuild and publishing to conda-forge channel (to include SVML patch changes) · Issue #72 · conda-forge/llvmlite-feedstock · GitHub and mentioned there issues) and I would prefer dynamically linked llvm to never exist at all. s-barannikov April 17, 2025, 1:46pm 4 This would also save us from another frequently asked question “why am I getting a segfault?” (Answer: the linker ate all your memory.) You quickly mentioned BUILD_SHARED_LIBS rnk: (BUILD_SHARED_LIBS=ON), can offer faster iteration times in cases like this doesn’t it make this option a better default? Or this topic is about changing the default for external users and not for developers? nikic April 17, 2025, 1:57pm 5 s-barannikov: You quickly mentioned BUILD_SHARED_LIBS rnk: (BUILD_SHARED_LIBS=ON), can offer faster iteration times in cases like this doesn’t it make this option a better default? Or this topic is about changing the default for external users and not for developers? I’d say the advantage to using the dylib build instead of the shared-libs build is that the dylib build is a pretty good option for both a production and a development build, while shared-libs is not suitable for production. 1 Like akorobeynikov April 17, 2025, 4:32pm 6 Hardcode84: I would prefer dynamically linked llvm to never exist at all. Can this (at least partially) be circumvented by e.g. putting namespace llvm into inlined versioned namespace similar to what is done in libc++? With at least LLVM version to be used as a namespace tag. This way one won’t at least have symbol clashes across multiple LLVM versions. Certainly there is no “LLVM ABI”, but at least would prevent this? Fortunately, all the similar cases I had to debug usually ended with assertion failures due to option being registered multiple times, so no real crashes Hardcode84 April 17, 2025, 5:37pm 7 Versioned namespace will probably fix a lot of such issues, and some other projects (TBB) has also used such approach for ABI breaking changes. Also, having a way to configure top-level namespace would be useful by itself, e.g. for custom LLVM forks. So I’m +1 for this. jhuber6 April 17, 2025, 6:20pm 8 libc also does this. Presumably it would require replacing all namespace llvm with namespace LLVM_NAMESPACE and have that macro be defined by the LLVM cmake configuration. It would be really invasive however, I can imagine hoe many uses of llvm::SmallVector we’d need to change. tstellar April 17, 2025, 6:49pm 9 What’s the difference between using a versioned namespace versus adding symbol versions with a linker script (which is what LLVM does now)? reinterpretcast April 17, 2025, 6:55pm 10 rnk: They already search for paths relative to the executable path, but if you add shared library dependencies Searching for paths relative to the executable path for a shared library dependency is somewhat different from doing so for other reasons: you need system loader support. Some POSIX platforms (e.g., AIX) do not support $ORIGIN in the runtime search path. beanz April 17, 2025, 8:14pm 11 I would say I weakly disagree with this. I would like to understand the problem this seeks to solve. If the problem is developer iteration, when I change a single source file in clang and run check-clang it takes less than 5 seconds on my machine to rebuild and re-link clang, and a little over 2 minutes to run the lit tests… I feel like speeding up the link to slow down the lit tests is probably the wrong tradeoff (note: this is on Darwin using ld_prime). If the problem is debug info size and linking memory consumption, could we instead more minimally make LLVM_USE_SPLIT_DWARF default to On ? If the problem is to default build configurations align with distributions… I actually don’t think that is a goal we should have. Distributions have wildly varying constraints that they optimize for which aren’t necessarily aligned with rapid iteration of rebuild/test cycles. I think our default build configuration should be more aligned for developer iteration rather than distribution. I think one key problem here is that POSIX is a pretty wide brush to paint with. As @reinterpretcast mentioned AIX is quite different from Linux or macOS which are themselves different from each other. To @s-barannikov ’s point, our build configuration system today has some known sharp edges. Like allowing users to launch too many link jobs in paralell when using ld.bfd . That’s plagued us for a long time and we should probably just spend some time making our CMake error out on configurations that are almost certainly going to fail (like using ld.bfd and generating debug info on a laptop with 2GB of RAM). 5 Likes compnerd April 17, 2025, 9:10pm 12 I think that this is a good thing to do in general. There is ongoing work to fix the DLL storage for Windows builds (and should be applicable to other platforms as well) so I would think that this is something that we should be able to default to on all targets (hopefully) soon. One minor point - I think that the startup impact is not a permanent fixed cost. In fact, I think that it might be something that actually goes down as the work for the DLL storage starts making its way to the repository as the correct annotations would reduce the number of PLT entries. Also, note the WHOPR aspects are dependent on the number of modules we create. If we create a single LLVM DSO, the overall impact should not be too bad compared to a DSO per module in LLVM. danilaml April 18, 2025, 11:20pm 13 I’m all for verioned/configurable "global’ llvm namespace. Was bit by “some plugin loaded by the application that links to our shared llvm-based lib is picking up wrong symbols (and it’s great if it only ends in cl opt asserts and not a segfault)” one too many times. Even symbol versioning doesn’t really help. @tstellar Symbol resolution rules when multiple versions are present are arcane and not really documented (or I’m really bad at searching). Anyway, if I recall my woes correctly 1) if third-party library/plugin/app links to unversioned llvm, then it’ll likely to pick up your versioned symbols other llvm ones. 2) if you versioned your symbols with fun@FOO_1.2.3 and the third-party is linking against fun@BAR_1.2.3 it’s unclear which one will win the resolution (and I definitely encountered cases there the wrong version was picked). So yeah, symbol versioning makes situation a little bit better but doesn’t solve it completely. I guess custom namespace may also help defining the llvm API surface you actually use (by just greping it in nm output) so you could hide everything else for extra benefit (useful while LLVM_ABI work is in limbo). Anyway, this seems orthogonal to the RFC at hand and could use its own thread. 1 Like planetmarshall April 19, 2025, 6:06pm 14 rnk: The downsides of the libLLVM DSO are… I would add to the downsides that it is not currently possible to build Clang (and possibly other components - I haven’t checked) against a standalone LLVM build when LLVM is built with LLVM_BUILD_LLVM_DYLIB - because of the dependency on the static LLVMSupport library. Obviously this isn’t a fundamental limitation, just the way the build is currently structured and I suspect it’s not a typical configuration. It’s just something I came across when developing the conan package for LLVM. 3 Likes mehdi_amini April 22, 2025, 11:07am 15 libLLVMSupport seems like an issue to me: we have quite a few libraries that depends only on libSupport and would not want all of LLVM. Would it be possible to have libLLVMSupport.so not included in libLLVM.so and have libLLVM.so depend on libLLVMSupport.so? jayfoad April 22, 2025, 12:12pm 16 I’m not too concerned about changing the defaults but I am interested in testing times. From a quick experiment running check-llvm in a Release+Asserts build: Default: 159 seconds CMAKE_EXE_LINKER_FLAGS=-no-pie : 97 seconds LLVM_LINK_LLVM_DYLIB=ON : 171 seconds So turning on LLVM_LINK_LLVM_DYLIB is only slightly slower than the current default, but it precludes the large speed-up you can currently get by turning on -no-pie (see Impact of default PIE on llvm testing times ). This is on Ubuntu 24.04 with an AMD Ryzen 9 9950X 16-Core processor. All timings seem consistent within about +/- 1 second. – Incidentally, LLVM_LINK_LLVM_DYLIB=ON seems incompatible with LLVM_USE_LINKER=lld . If I try to use both I get lots of build errors like: FAILED: bin/llvm-cxxdump : && /usr/lib/ccache/clang++ -fPIC -fno-semantic-interposition -fvisibility-inlines-hidden -Werror=date-time -Werror=unguarded-availability-new -Wall -Wextra -Wno-unused-parameter -Wwrite-strings -Wcast-qual -Wmissing-field-initializers -pedantic -Wno-long-long -Wc++98-compat-extra-semi -Wimplicit-fallthrough -Wcovered-switch-default -Wno-noexcept-type -Wnon-virtual-dtor -Wdelete-non-virtual-dtor -Wsuggest-override -Wstring-conversion -Wmisleading-indentation -Wctad-maybe-unsupported -fdiagnostics-color -ffunction-sections -fdata-sections -O3 -DNDEBUG -fuse-ld=lld -Wl,--color-diagnostics -Wl,--gc-sections tools/llvm-cxxdump/CMakeFiles/llvm-cxxdump.dir/llvm-cxxdump.cpp.o tools/llvm-cxxdump/CMakeFiles/llvm-cxxdump.dir/Error.cpp.o -o bin/llvm-cxxdump -Wl,-rpath,"\$ORIGIN/../lib:" -lLLVM && : ld.lld: error: unable to find library -lLLVM clang++: error: linker command failed with exit code 1 (use -v to see invocation) sunnyflunk April 22, 2025, 12:16pm 17 Integrating the ability to statically link a few key programs (i.e. clang) would remove a lot of the downsides of the DYLIB build. There isn’t really any benefit for the static tooling. There are certain workloads where this can be quite impactful. Note that any numbers I quote are from about 3 years ago so the impact may be reduced with current versions of clang/LLVM. As a distribution, a large % of your packages (in number at least) are quite small. When building a smaller package, the time it takes to run configure (single threaded) is often longer than building the package (5-8s configure, 2-4s make). Cutting the time to load clang can save quite a bit of time on the configure step, with one of the worst offenders I saw called clang about 1500 times over 35 seconds (up to 75 seconds depending on how optimized your clang was). What I ended up doing was building the stack with LINK_LLVM_DYLIB=ON and then in the same tree rerunning cmake with it off and having it relink just clang and lld statically (a slight hack). By doing this I could achieve 95% of the size savings, but retain the performance benefits of fast startup and the extra performance you gain from LTO. The numbers I had at the time for a full build (configure, make, make install) on Fedora: clang: 33.8 seconds clang: 26.6 seconds (after -Bsymbolic-functions and -fno-semantic-interposition patches released to highlight the massive impact on the DYLIB build!) gcc: 18.4 seconds ← as a reference point, which is PGO and static And my build of clang with static clang and lld only: sunnyflunk clang: 14.9 seconds (I also used PGO which wasn’t in Fedora’s clang) I never finished testing if static LLD was worthwhile, the thought was it could help for LTO links (a distribution default) nikic April 22, 2025, 12:21pm 18 planetmarshall: I would add to the downsides that it is not currently possible to build Clang (and possibly other components - I haven’t checked) against a standalone LLVM build when LLVM is built with LLVM_BUILD_LLVM_DYLIB - because of the dependency on the static LLVMSupport library. Even if you use LLVM_LINK_LLVM_DYLIB, the static libraries are still built. They just get linked into libLLVM.so instead of each individual tool. Whether you actually install/ship the static libraries is up to you, but the LLVM_LINK_LLVM_DYLIB option doesn’t interfere with it. While we have since switched to monolithic builds, we have been building various subprojects against standalone LLVM compiled with LLVM_BUILD/LINK_LLVM_DYLIB for a long time, and there have been no problems with it. tobiashieta April 22, 2025, 12:24pm 19 jayfoad: Incidentally, LLVM_LINK_LLVM_DYLIB=ON seems incompatible with LLVM_USE_LINKER=lld . If I try to use both I get lots of build errors like: This seems like a major problem to me. We recommend people to link with lld to save RAM and link time. We need to fix this first IMHO. jayfoad April 22, 2025, 12:34pm 20 On further investigation I only see those errors after I do cmake . -DLLVM_LINK_LLVM_DYLIB=ON in a build tree that was originally configured without that option. Maybe I am not supposed to do this? next page → Related topics Topic Replies Views Activity LLVM questions LLVM Dev List Archives 1 130 September 3, 2019 2025 Runtimes Workshop Notes US Developer Meeting libcxx , libc 0 176 November 10, 2025 BUILD_SHARED_LIBS=True breaks some tests Clang Frontend 13 193 January 12, 2019 [RFC] March Update: Progress report on CMake build system's ability to replace autoconf LLVM Dev List Archives 5 170 March 5, 2015 Building SVN head with CMake - shared libraries? LLVM Dev List Archives 35 336 January 22, 2016 Home Categories Guidelines Terms of Service Privacy Policy Powered by Discourse , best viewed with JavaScript enabled | 2026-01-13T08:47:52 |
https://claude.com/solutions/life-sciences | Life sciences | Claude -------> Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Solutions Solutions / Life sciences Explore here Ask questions about this page Copy as markdown Accelerate science, from discovery through translation Claude helps pharma companies, biotech startups, and research institutions move faster, while maintaining the accuracy your work demands. Get started Get started Get started Contact sales Contact sales Contact sales Play video Play video "At AstraZeneca, AI is a defining force reshaping how we operate across R&D end-to-end. Through R&D powered by AI, we can derive deeper biological insights that help us push the boundaries of science to deliver life-changing medicines, including novel approaches for patient selection. Claude's commitment to mechanistic interpretability provides a safe, secure, and steerable model to empower our science-first approach." Dr. Jorge Reis Filho, Chief of AI for Science Innovation, AstraZeneca R&D "By reducing manual burden and enabling greater scale across our operations, our partnership with Anthropic will empower our teams to focus more time on high-value scientific and strategic work, with the goal of accelerating our path to patient impact." Tahamtan Ahmadi, M.D., Ph.D, Executive Vice President and Chief Medical Officer, Genmab "Veeva AI is industry-specific agentic AI that leverages Veeva's deep applications, data, domain expertise, and Anthropic's Claude. This unique combination allows us to bring the transformative promise of AI to life sciences at scale." Andy Han, Senior Vice President, Veeva AI “Opus 4.5 is an incredible model and a great choice for computational biology. The model is excellent at coding, reasoning about biology, and understanding scientific figures.” Andrew White, CTO, Edison Scientific "Commercial pharma teams are entering an era where real-time clinical intelligence and AI agents fundamentally change how therapies reach the right patients at the right time. Anthropic's models are unmatched in their reasoning capabilities and safety design. This collaboration accelerates our shared mission to ensure that clinical-grade agentic AI becomes a trusted, transformative force across global pharma." Chris Mansi, MD, CEO and co-founder of Viz.ai “Broad Institute scientists pursue the most ambitious questions in biology and medicine, and we create and share tools to help empower scientists everywhere. We’ve been working closely with Manifold on the next generation of the Terra.bio platform—Terra Powered by Manifold. Among the most exciting of these upgrades are AI agents built on Claude that enable scientists to carry out tasks at an entirely new scale and efficiency and explore scientific domains in previously impossible ways.” Heather Jankins, Head of Data Science Platform “Accessing 10x’s single cell and spatial analysis capabilities has traditionally required computational expertise - from writing command-line scripts to managing high-performance computing systems. Now, these same tools can respond to questions asked in plain English. Using Claude, researchers can now perform common analytical tasks—including aligning reads, generating Feature Barcode matrices, performing clustering and other secondary analysis—through a conversational interface that complements traditional computational workflows, making it faster and easier for researchers to engage directly with their data. Claude lowers the barrier to entry for new users and scales to meet the needs of large-scale analyses for advanced research teams.” Serge Saxonov, Co-founder and CEO “AI in R&D only works through an ecosystem. Anthropic is doing this right, bringing together the best technologies while putting access, governance, and interoperability first. Benchling is uniquely positioned to contribute. For more than a decade, scientists have trusted us as the source of truth for experimental data and to modernize their workflows. Now we're building AI that powers this next chapter of R&D.” Ashu Singhal, Co-founder and President “Claude, paired with internal knowledge libraries, has become integral to Sanofi’s AI-driven transformation and is used by the majority of Sanofians on a daily basis within our internal Concierge app. We are seeing significant efficiency gains across the value-chain by optimizing our processes, while our enterprise-wide deployment has enhanced how our teams work. This collaboration with Anthropic augments human expertise to deliver life-changing medicines faster and more effectively to patients worldwide.” Emmanuel Frenehard, Chief Digital Officer “We’ve consistently been one of the first movers when it comes to document and content automation in pharma development. Our work with Anthropic and Claude has set a new standard—we’re not just automating tasks, we’re transforming how medicines get from discovery to the patients who need them.” Read story Read story Read story Louise Lind Skov, Director Content Digitalisation “Claude Code has become a powerful accelerator for us at Schrödinger. For the projects where it fits best, Claude Code allows us to turn ideas into working code in minutes instead of hours, enabling us to move up to 10x faster in some cases. As we continue to work with Claude, we are excited to see how we can further transform the way we build and customize our software.” Pat Lorton, Executive Vice President, Chief Technology Officer, and Chief Operating Officer “At Manifold, our mission is to power faster, leaner life sciences. Building with Claude has enabled us to develop AI agents that translate questions in the semantic space of scientists to execution in the technical space of specialized datasets and tools. Together, we’re transforming how life sciences R&D will happen in the years ahead.” Sourav Dey, PhD, Co-founder and Chief AI Officer “At PwC, we believe responsible AI isn’t just a technology opportunity—it’s a trust imperative. We’re proud to pair our deep sector insight with Claude’s agentic intelligence to reimagine how clinical, regulatory, and commercial teams operate. Together, we’re not just streamlining processes—we’re elevating quality, accelerating discovery, and building systems where confidence scales alongside innovation.” Matt Wood, US and Global Commercial Technology and Innovation Officer “When we set out to create an AI agent that could automate bioinformatics analyses, we focused on three key factors to decide what model provider to use: top-ranking at software development, aligned with life sciences, and support for startups. We evaluated half a dozen platforms, and it became clear that Claude was the standout leader. We’re excited to continue this collaboration and bring cutting-edge AI Agents into the world of biotech research.” Alfredo Andere, Co-founder and CEO “Claude has been an invaluable progress multiplier for Axiom as we build AI to predict drug toxicity. We’ve used billions of tokens in Claude Code, and use it to write many of our PRs. More recently, Claude agents with MCP servers have become core tools for our scientific work. With the right MCPs, Claude agents can directly query databases and storage services to interpret, transform, and test correlations in data, and help us identify what data and features are most useful for predicting clinical drug toxicity.” Alex Beatson, Co-founder “At EvolutionaryScale, we’re building next-generation AI systems to model the living world. Anthropic’s frontier models accelerate our ability to reason about complex biological data and translate it into scientific insight, helping us push the boundaries of what’s possible in life science discovery.” Sal Candido, Co-founder, Chief Technology Officer Prev Prev 0 / 5 Next Next Built for breakthrough science AI you can trust Claude models are safe, secure, and reliably accurate, so you can handle clinical trial data and proprietary compounds with confidence. Built for scientific complexity Analyze genomic data, synthesize findings across hundreds of papers, and design experiments with full citations. Claude matches the complexity of modern drug development. Made for R&D Claude connects to Benchling, PubMed, 10x Genomics, and your lab platforms—so every scientist can accelerate their work from discovery through regulatory submission. Your partner in discovery We collaborate with pharma leaders and research institutions to make sure Claude evolves with the needs of life sciences and advances real scientific discovery. Case study Novo Nordisk accelerates clinical documentation and drug development with Claude Read story Read story Read story Livestream Tune in to watch Anthropic CEO and Co-founder Dario Amodei share his vision for AI in healthcare and life sciences, along with an executive customer panel. Watch Watch Watch Prev Prev Next Next How life sciences teams use Claude Protocols Synthesis Bioinformatics Compliance Active View prompt View prompt View prompt Prompt I need to draft a Phase 2 clinical protocol for our Parkinson's drug. Attached is a summary of the biologic including molecular targets, mechanism of action, and preclinical data from our Phase 1 trial. Let’s use the clinical protocol skill. Attachments PD biologic summary 1.2mb PDF Phase 1 results summary 348kb XLSX Phase 2 Clinical Trial Protocol ABX-7291 for Treatment of Parkinson's Disease | DRAFT v0.1 Study Synopsis Protocol Title: A Phase 2, Randomized, Double-Blind, Placebo-Controlled Study to Evaluate the Efficacy and Safety of ABX-7291 in Patients with Early-Stage Parkinson's Disease Sponsor: [Sponsor Name] Phase: Phase 2 Indication: Early-stage Parkinson's Disease (Hoehn & Yahr Stage 1-2) Study Duration: 24 weeks treatment + 4 weeks follow-up Objectives and Endpoints Primary Objective Evaluate the efficacy of ABX-7291 compared to placebo in reducing motor symptoms in patients with early-stage Parkinson's disease. Primary Endpoint Change from baseline in MDS-UPDRS Part III (Motor Examination) score at Week 24. Secondary Endpoints Change from baseline in MDS-UPDRS Total Score at Week 24 Proportion of patients achieving ≥30% improvement in MDS-UPDRS Part III Change in PDQ-39 (Quality of Life) score at Week 24 Safety and tolerability (AEs, laboratory parameters, vital signs) Study Design This is a Phase 2, randomized, double-blind, placebo-controlled, parallel-group study. Eligible patients will be randomized 1:1:1 to receive ABX-7291 low dose, ABX-7291 high dose, or placebo for 24 weeks. Sample Size and Rationale Total Enrollment: 120 patients (40 per arm) Statistical Power: 80% power at α=0.05 (two-sided) Expected Effect Size: 5-point difference in MDS-UPDRS Part III (SD=8) Dropout Assumption: 15% (based on comparable Phase 2 PD trials) Rationale: Sample size derived from analysis of 12 comparable Phase 2 trials on ClinicalTrials.gov with similar indications and endpoints. Regulatory References 21 CFR 312 (Investigational New Drug Application) FDA Guidance: Parkinson's Disease: Developing Drugs for Treatment (2023) ICH E6(R2): Good Clinical Practice ICH E9: Statistical Principles for Clinical Trials Generated using Clinical Protocol Generation skill Sources: ClinicalTrials.gov (12 comparable studies), FDA guidance documents Ready for review with biostatisticians and regulatory affairs Protocol generation Draft study protocols, SOPs, and consent documents directly in Benchling. Claude structures experimental workflows while you maintain control over scientific decisions. View prompt View prompt View prompt Prompt My colleagues recently published the attached single-cell dataset that describes gene expression differences between adult and pediatric liver samples with a focus on the immune system. I would like to explore these samples but focus on the parenchymal cells and differences between adult and pediatric liver. Can you help me first go through the differentially expressed genes and create a heatmap and then also identify pathways or sets of genes that are enriched in each sample? Research synthesis Survey hundreds of papers in hours instead of weeks. Claude synthesizes findings across biomedical literature, identifies contradictions, and generates testable hypotheses with verifiable citations. View prompt View prompt View prompt Prompt > use the scRNA-qc skill to perform QC and filtering on the raw_feature_matrix from my experiment Now let me run the QC analysis on the raw feature matrix: Bash(python3 scripts/qc_analysis.pypbmc_test_data/raw_feature_bc_matrix.h5) ↳=========================================================== Single-Cell RNA-seq Quality Control AnalysisFollowing scVerse Best Practices … +60 lines (ctrl+o to expand) Excellent! The QC analysis completed successfully. Let me update the visualizations: Read(qc_metrics_before_filtering.png)↳ Read image (732.3KB) Read(qc_filtering_thresholds.png)↳ Read image (210KB) Read(qc_metrics_after_filtering.png)↳ Read image (1.1MB) Perfect! I've successfully completed the QC analysis on your raw feature matrix using the scRNA-qc skill. Here's a summary of the results:QC Analysis SummaryDataset: 2,700 cells × 32,738 genes (raw)Quality Metrics Detected: 13 mitochondrial genes 106 ribosomal genes 13 hemoglobin genes MAD-Based Filtering Thresholds: Total counts: 709 - 6,812 Genes detected: 367 - 1,821 Mitochondrial %: MAD threshold 3.65%, Hard threshold 8.0% Filtering Results: 266 cells removed as outliers (9.9%) 2,434 cells retained (90.1%) Gene filtering reduced from 32,738 to 9,487 genes (29.0%) Key Observations from Visualizations: Before Filtering: The data shows typical scRNA-seq quality with most cells having 1,000-2,000 counts and detecting 500-1,000 genes. Mitochondrial content is generally low (<5%), which is excellent. Thresholds: The MAD-based thresholds are permissive (5 MADs for counts/genes, 3 MADs for MT%), following scverse best practices to avoid over-filtering. After Filtering: The filtered dataset shows cleaner distributions with tighter clustering, lower mitochondrial content (mostly <3%), and good cell-gene correlation. Output Files Created: raw_feature_bc_matrix_filtered.h5ad - Clean filtered dataset ready for downstream analysis raw_feature_bc_matrix_with_qc.h5ad - Original data with QC annotations QC visualization PNGs (before/thresholds/after) The data quality looks excellent! You can now proceed with downstream analysis like normalization, dimensionality reduction, and clustering using the filtered dataset. Bioinformatics and data analysis Process genomic data and optimize analysis workflows with Claude Code. Claude presents results clearly so you can easily communicate with cross-functional teams. View prompt View prompt View prompt Prompt Summarize safety findings from our phase 1 trial for the IND submission (clinical safety module). Flag any signals that need monitoring in phase 2. Attachments Adverse events report 15kb csv Clinical lab results 348kb CSV Clinical Safety Summary Module 2.7.4 | IND-2024-0892 Study Overview Drug: ABX-4721 (anti-inflammatory biologic) Phase: Phase 1 Subjects: 48 healthy volunteers Duration: 12-week duration Adverse Event Summary Total subjects with AEs: 23 (47.9%) Serious adverse events: 2 (4.2%) Discontinuations due to AEs: 1 (2.1%) Deaths: 0 Safety Signals for Phase 2 Monitoring ⚠ Hepatic Elevated ALT (>3x ULN): 3 subjects (6.3%) All resolved without intervention within 14 days → Recommend: LFT monitoring at weeks 2, 4, 8 ⚠ Injection site reactions Mild erythema: 8 subjects (16.7%) No treatment required → Recommend: Document severity grading in Phase 2 Regulatory References 21 CFR 312.32 (IND Safety Reporting) ICH E2A: Clinical Safety Data Management FDA Guidance: Premarketing Risk Assessment Generated from uploaded AE reports and lab data All source documents linked for audit trail Clinical and regulatory strategy and compliance Generate regulatory summaries and compile safety data across modules with full audit trails. Focus on scientific decisions, not document formatting. Claude connects to your research ecosystem Literature, lab notebooks, analysis platforms, all working together in one place. Explore connectors Explore connectors Explore connectors Get started with Claude Individual Team & Enterprise Active Pro For everyday productivity Try Claude Try Claude Try Claude Life sciences connectors and skills Access to file creation (docs, slides, spreadsheets, and PDFs) Access to research Access to Claude Code Life sciences guides and docs Max Get the most out of Claude Try Claude Try Claude Try Claude Everything in Pro, plus: Choose 5x or 20x more usage than Pro* Higher output limits for all tasks Early access to advanced Claude features Additional usage limits apply. Prices shown don’t include applicable tax. <path d="M213.34 381.59C201.84 381.8 196.1 381.67 190.35 381.55C184.6 381.41 178.86 381.29 167.35 381.32C155.84 381.32 150.07 381.2 144.25 380.98C142.79 380.92 141.33 380.86 139.75 380.76C139.57 380.75 139.14 380.73 138.81 380.7C138.46 380.67 138.11 380.64 137.75 380.61C137.05 380.52 136.28 380.54 135.63 380.33C134.97 380.15 134.21 380.04 133.61 379.75C133.31 379.6 132.94 379.54 132.68 379.32L132.26 379.02L132.23 379H132.22C132.37 378.81 132.25 378.93 132.29 378.89L132.24 378.84L132.14 378.75L131.94 378.56C131.39 378.1 131 377.5 130.72 376.76C130.42 376.04 130.21 375.21 130.04 374.34C129.88 373.47 129.75 372.53 129.65 371.66C129.61 371.31 129.57 370.95 129.54 370.58C129.51 370.29 129.49 370 129.46 369.71C129.26 367.37 129.11 364.81 128.97 361.9C128.52 350.33 128.29 344.55 128.07 338.76C127.86 332.98 127.63 327.22 127.9 315.65C128.05 309.86 128.21 305.5 128.41 301.83C128.51 299.99 128.61 298.32 128.75 296.7L128.81 296.09L128.84 295.73L128.9 295.19C128.99 294.47 129.07 293.75 129.2 293.05C129.45 291.67 129.75 290.28 130.45 289.27C130.83 288.8 131.15 288.25 131.63 287.81C132.16 287.46 132.63 287.08 133.21 286.8C134.34 286.2 135.8 285.95 137.28 285.75C | 2026-01-13T08:47:52 |
https://www.reddit.com/mod/netflix/moderators/ | Reddit - Prove your humanity Prove your humanity We’re committed to safety and security. But not for bots. Complete the challenge below and let us know you’re a real person. Reddit, Inc. © "2026". All rights reserved. User Agreement Privacy Policy Content Policy Help | 2026-01-13T08:47:52 |
https://github.com/john-khgoh/LanguageRecognizer/tree/main | GitHub - john-khgoh/LanguageRecognizer Skip to content Navigation Menu Toggle navigation Sign in Appearance settings Platform AI CODE CREATION GitHub Copilot Write better code with AI GitHub Spark Build and deploy intelligent apps GitHub Models Manage and compare prompts MCP Registry New Integrate external tools DEVELOPER WORKFLOWS Actions Automate any workflow Codespaces Instant dev environments Issues Plan and track work Code Review Manage code changes APPLICATION SECURITY GitHub Advanced Security Find and fix vulnerabilities Code security Secure your code as you build Secret protection Stop leaks before they start EXPLORE Why GitHub Documentation Blog Changelog Marketplace View all features Solutions BY COMPANY SIZE Enterprises Small and medium teams Startups Nonprofits BY USE CASE App Modernization DevSecOps DevOps CI/CD View all use cases BY INDUSTRY Healthcare Financial services Manufacturing Government View all industries View all solutions Resources EXPLORE BY TOPIC AI Software Development DevOps Security View all topics EXPLORE BY TYPE Customer stories Events & webinars Ebooks & reports Business insights GitHub Skills SUPPORT & SERVICES Documentation Customer support Community forum Trust center Partners Open Source COMMUNITY GitHub Sponsors Fund open source developers PROGRAMS Security Lab Maintainer Community Accelerator Archive Program REPOSITORIES Topics Trending Collections Enterprise ENTERPRISE SOLUTIONS Enterprise platform AI-powered developer platform AVAILABLE ADD-ONS GitHub Advanced Security Enterprise-grade security features Copilot for Business Enterprise-grade AI features Premium Support Enterprise-grade 24/7 support Pricing Search or jump to... Search code, repositories, users, issues, pull requests... --> Search Clear Search syntax tips Provide feedback --> We read every piece of feedback, and take your input very seriously. Include my email address so I can be contacted Cancel Submit feedback Saved searches Use saved searches to filter your results more quickly --> Name Query To see all available qualifiers, see our documentation . Cancel Create saved search Sign in Sign up Appearance settings Resetting focus You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} john-khgoh / LanguageRecognizer Public Notifications You must be signed in to change notification settings Fork 0 Star 0 License Apache-2.0 license 0 stars 0 forks Branches Tags Activity Star Notifications You must be signed in to change notification settings Code Issues 0 Pull requests 0 Actions Projects 0 Security Uh oh! There was an error while loading. Please reload this page . Insights Additional navigation options Code Issues Pull requests Actions Projects Security Insights john-khgoh/LanguageRecognizer main Branches Tags Go to file Code Open more actions menu Folders and files Name Name Last commit message Last commit date Latest commit History 9 Commits wheelhouse wheelhouse CMakeLists.txt CMakeLists.txt LICENSE LICENSE LanguageRecognizer.cpp LanguageRecognizer.cpp LanguageRecognizer.h LanguageRecognizer.h MANIFEST.in MANIFEST.in README.md README.md checked.h checked.h core.h core.h cpp11.h cpp11.h cpp17.h cpp17.h pyLanguageRecognizer.cpp pyLanguageRecognizer.cpp pyproject.toml pyproject.toml setup.py setup.py tbb12.dll tbb12.dll tbb12.pdb tbb12.pdb tbbmalloc.dll tbbmalloc.dll unchecked.h unchecked.h View all files Repository files navigation README Apache-2.0 license simple-language-recognizer What is it? Package that recognizes the language of an input string from over 70 languages. The package is probabilistic as the words in the input string are sampled. What languages can it detect? Afrikaans, Albanian, Amharic, Arabic, Armenian, Azerbaijani, Basque, Belarusian, Bengali, Bulgarian, Burmese, Catalan, Chinese (Simplified), Chinese (Traditional), Croatian, Czech, Danish, Dutch, English, Estonian, Filipino, Finnish, French, German, Greek, Gujarati, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Irish, Italian, Japanese, Kannada, Kazakh, Khmer, Korean, Kurdish, Kyrgyz, Lao, Latin, Latvian, Ligurian, Lithuanian, Luganda, Luxembourgish, Macedonian, Malay, Malayalam, Marathi, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Scottish Gaelic, Serbian, Sinhala, Slovak, Slovenian, Spanish, Swedish, Tajik, Tamil, Tatar, Telugu, Thai, Tibetan, Tigrinya, Tswana, Turkish, Ukrainian, Urdu, Vietnamese, Yoruba Installing There are installers for Windows, MacOS and Linux ( manylinux ). Manylinux works with multiple Linux distros. To install: pip install simple-language-recognizer Note for MacOS users: If you receive an error like "SyntaxError: Non-UTF-8 code starting with '\xe0'", include the following at the top of your python codes before the import statement. # -*- coding: utf-8 -*- Example from simpleLanguageRecognizer import languageRecognizer input = "This is an example of a short phrase in English but which is longer than 50 characters." output = languageRecognizer(input) print(output) output = languageRecognizer(input,False,3,0.25) print(output) Input arguments text (string): The input string. allLanguages (bool) (Optional): True (All languages) / False (Only European/Latin-based languages). The function works faster when allLanguages is set to False. maxResults (int) (Optional): The maximum length of the output array. The output array might be empty if the input string is not recognized. sampleRatio (double) (Optional): Ratio of words being sampled from the input (0.0 - 1.0). Change log Version 0.0.1: Initial release. Version 0.0.2: Readme.md update. Version 0.0.3: Available for Windows, Linux and MacOS. Special thanks A special thanks to spaCy and NLTK . About No description, website, or topics provided. Resources Readme License Apache-2.0 license Uh oh! There was an error while loading. Please reload this page . Activity Stars 0 stars Watchers 0 watching Forks 0 forks Report repository Releases No releases published Packages 0 No packages published Contributors 2 Uh oh! There was an error while loading. Please reload this page . Languages C++ 98.7% CMake 1.2% Python 0.1% Footer © 2026 GitHub, Inc. Footer navigation Terms Privacy Security Status Community Docs Contact Manage cookies Do not share my personal information You can’t perform that action at this time. | 2026-01-13T08:47:52 |
https://swampup.jfrog.com/ | SwampUP 2025 | JFrog's Premier Event Skip to content Training Agenda Speakers Sponsors Register for 2026 Training Agenda Speakers Sponsors Register for 2026 Napa swampUP 2025 is a Wrap! Check out the highlights Register for 2026 Product Announcements DevGovOps JFrog AppTrust JFrog AppTrust brings application context to the JFrog Platform so you can manage risk end-to-end. With a clear application overview, defined ownership, and evidence-based controls that act as strategic gates, AppTrust allows you to consistently deliver certified and secure applications. Learn More DevGovOps Evidence Ecosystem Essential for establishing trust in your applications – JFrog is making it even easier to collect and centralize all SDLC process attestation evidence with our new Evidence Ecosystem Partners. Explore our integrated partners and new evidence collection methods. Learn More MLSecOps JFrog AI Catalog JFrog AI Catalog is the source of truth for the AI ecosystem, allowing teams to easily identify and access AI models approved for use in their org. Gain control and governance of the AI added to your applications to accelerate deployment and delivery of AI powered applications. Learn More Agentic Experience JFrog Fly JFrog Fly is the software delivery solution built for the AI era, and tailor made for the needs of small teams. Connect your GitHub and in a few clicks the JFrog agent has you up and running so you can store, share, and serve secure SW artifacts with zero hassle. Click, chat, ship… Fly. Join The Beta See Announcements See Our New Capabilities IDE Extensions Control Gain visibility and control over developer extensions and MCP servers developers can access. Transitive Dependency Reachability Gain applicability information along with a clear remediation path for transitive dependency CVEs. Runtime Scope Prioritize scanning by identifying and actioning items in production that haven’t been scanned. Agentic Remediation Bring the power of JFrog’s SAST scanners to your favorite agents to unlock automated remediation of code issues and CVEs. Contact Us Marquee Partnership Announcements GitHub Enhanced Integration With More Automation, Features & Scalability Automate integration with the JFrog App, capture GitHub attestations, improve AI coding, extend security visibility, and more. Learn More ServiceNow Streamline Enterprise Governance and Software Delivery Workflows Sync application context across ServiceNow and JFrog for a unified change management audit trail. Learn More Sonar Unite Code Quality
and Application Risk Management Bring SonarQube’s code quality attestations to JFrog as a key driver for software governance. Learn More Explore all of our Evidence Ecosystem Integrations See All Integrations swampUP 2026 is happening September 1-3 in New York! Register today for 75% off Register Now 3-Day Conference, including Training Day, Welcome Reception, Keynotes, Gala and Breakout Sessions Meet JFrog at GitHub Universe ’25 October 28–29 | San Francisco, CA Fort Mason Center Book a Meeting Thank you to our 2025 swampUP Sponsors Contact Us Register for 2026 Code of Conduct © 2025 JFrog Ltd All Rights Reserved Terms of Use Cookies Policy Privacy Notice Cookies Settings Thank You for Registering! Looking forward to swamp with you Close Window Thank You! Thank you for inquiring about sponsoring swampUP 2024. We’ll be in touch shortly! Close Window | 2026-01-13T08:47:52 |
https://claude.com/resources/tutorials | Tutorials | Claude -------> Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Meet Claude Products Claude Claude Code Features Claude in Chrome Claude in Slack Claude in Excel Skills Models Opus Sonnet Haiku Platform Overview Developer docs Pricing Regional Compliance Console login Solutions Use cases AI agents Coding Industries Customer support Education Financial services Government Healthcare Life sciences Nonprofits Pricing Overview API Max plan Team plan Enterprise plan Learn Blog Courses Customer stories Events Tutorials Use cases Anthropic news Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Contact sales Contact sales Contact sales Try Claude Try Claude Try Claude Tutorials Tutorials Explore here Ask questions about this page Copy as markdown Filter Category Engineering Finance HR Healthcare Life Sciences Marketing Professional Sales Features Artifacts Connectors Projects Research Skills Product Claude in Chrome Claude.ai Reset Reset Reset Apply Apply Apply Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Learn Claude with hands-on tutorials Build your skills through written guides, and video lessons covering everything from quick tasks to complex workflows and best practices. Filter Category Engineering Finance HR Healthcare Life Sciences Marketing Professional Sales Features Artifacts Connectors Projects Research Skills Product Claude in Chrome Claude.ai Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Search Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Grid List Category Product Features Cowork, a research preview Professional Category Professional Product Cowork Features No items found. Read tutorial Read tutorial Read tutorial Cowork, a research preview Cowork, a research preview Text Link Professional How to use the Prior Auth Review sample skill with Claude Healthcare Category Healthcare Product Features Skills Read tutorial Read tutorial Read tutorial How to use the Prior Auth Review sample skill with Claude How to use the Prior Auth Review sample skill with Claude Text Link Healthcare How to use the Nextflow Deployment agent skill with Claude Code Life Sciences Category Life Sciences Product Features Skills Read tutorial Read tutorial Read tutorial How to use the Nextflow Deployment agent skill with Claude Code How to use the Nextflow Deployment agent skill with Claude Code Text Link Life Sciences How to use the Instrument Data to Allotrope Skill with Claude Life Sciences Category Life Sciences Product Features Skills Read tutorial Read tutorial Read tutorial How to use the Instrument Data to Allotrope Skill with Claude How to use the Instrument Data to Allotrope Skill with Claude Text Link Life Sciences How to use the Scientific Problem Selection Skill with Claude Life Sciences Category Life Sciences Product Features Skills Read tutorial Read tutorial Read tutorial How to use the Scientific Problem Selection Skill with Claude How to use the Scientific Problem Selection Skill with Claude Text Link Life Sciences How to use the scVI-Tools bioinformatics skill bundle with Claude Life Sciences Category Life Sciences Product Features Skills Read tutorial Read tutorial Read tutorial How to use the scVI-Tools bioinformatics skill bundle with Claude How to use the scVI-Tools bioinformatics skill bundle with Claude Text Link Life Sciences Using the ClinicalTrials.gov Connector in Claude Life Sciences Category Life Sciences Product Features Connectors Read tutorial Read tutorial Read tutorial Using the ClinicalTrials.gov Connector in Claude Using the ClinicalTrials.gov Connector in Claude Text Link Life Sciences Using the ToolUniverse Extension in Claude Life Sciences Category Life Sciences Product Features Connectors Read tutorial Read tutorial Read tutorial Using the ToolUniverse Extension in Claude Using the ToolUniverse Extension in Claude Text Link Life Sciences Using the Function Connector in Claude Healthcare Category Healthcare Product Features Connectors Read tutorial Read tutorial Read tutorial Using the Function Connector in Claude Using the Function Connector in Claude Text Link Healthcare Using the bioRxiv and medRxiv Connector in Claude Life Sciences Category Life Sciences Product Features Connectors Read tutorial Read tutorial Read tutorial Using the bioRxiv and medRxiv Connector in Claude Using the bioRxiv and medRxiv Connector in Claude Text Link Life Sciences Using the ChEMBL Connector in Claude Life Sciences Category Life Sciences Product Features Connectors Read tutorial Read tutorial Read tutorial Using the ChEMBL Connector in Claude Using the ChEMBL Connector in Claude Text Link Life Sciences Using the Owkin Connector in Claude Life Sciences Category Life Sciences Product Features Connectors Read tutorial Read tutorial Read tutorial Using the Owkin Connector in Claude Using the Owkin Connector in Claude Text Link Life Sciences Using the Open Targets Connector in Claude Life Sciences Category Life Sciences Product Features Connectors Read tutorial Read tutorial Read tutorial Using the Open Targets Connector in Claude Using the Open Targets Connector in Claude Text Link Life Sciences How to use the Clinical Trial Protocol Draft Generation sample skill with Claude Life Sciences Category Life Sciences Product Features Skills Read tutorial Read tutorial Read tutorial How to use the Clinical Trial Protocol Draft Generation sample skill with Claude How to use the Clinical Trial Protocol Draft Generation sample skill with Claude Text Link Life Sciences Using the Medidata Connector in Claude Life Sciences Category Life Sciences Product Features Connectors Read tutorial Read tutorial Read tutorial Using the Medidata Connector in Claude Using the Medidata Connector in Claude Text Link Life Sciences View more No posts for those filters Try another search or clear some of your filters. Clear all filters Clear all filters Clear all filters Search Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Transform how your organization operates with Claude Get started Get started Get started Homepage Homepage Next Next Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Write Button Text Button Text Learn Button Text Button Text Code Button Text Button Text Write Help me develop a unique voice for an audience Hi Claude! Could you help me develop a unique voice for an audience? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Improve my writing style Hi Claude! Could you improve my writing style? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Brainstorm creative ideas Hi Claude! Could you brainstorm creative ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Learn Explain a complex topic simply Hi Claude! Could you explain a complex topic simply? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Help me make sense of these ideas Hi Claude! Could you help me make sense of these ideas? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Prepare for an exam or interview Hi Claude! Could you prepare for an exam or interview? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Code Explain a programming concept Hi Claude! Could you explain a programming concept? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Look over my code and give me tips Hi Claude! Could you look over my code and give me tips? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Vibe code with me Hi Claude! Could you vibe code with me? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to— like Google Drive, web search, etc.—if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can—an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! More Write case studies This is another test Write grant proposals Hi Claude! Could you write grant proposals? If you need more information from me, ask me 1-2 key questions right away. If you think I should upload any documents that would help you do a better job, let me know. You can use the tools you have access to — like Google Drive, web search, etc. — if they’ll help you better accomplish this task. Do not use analysis tool. Please keep your responses friendly, brief and conversational. Please execute the task as soon as you can - an artifact would be great if it makes sense. If using an artifact, consider what kind of artifact (interactive, visual, checklist, etc.) might be most helpful for this specific task. Thanks for your help! Write video scripts this is a test Anthropic Anthropic © [year] Anthropic PBC Products Claude Claude Claude Claude Code Claude Code Claude Code Max plan Max plan Max plan Team plan Team plan Team plan Enterprise plan Enterprise plan Enterprise plan Download app Download app Download app Pricing Pricing Pricing Log in Log in Log in Features Claude in Chrome Claude in Chrome Claude in Chrome Claude in Slack Claude in Slack Claude in Slack Claude in Excel Claude in Excel Claude in Excel Skills Skills Skills Models Opus Opus Opus Sonnet Sonnet Sonnet Haiku Haiku Haiku Solutions AI agents AI agents AI agents Code modernization Code modernization Code modernization Coding Coding Coding Customer support Customer support Customer support Education Education Education Financial services Financial services Financial services Government Government Government Healthcare Healthcare Healthcare Life sciences Life sciences Life sciences Nonprofits Nonprofits Nonprofits Claude Developer Platform Overview Overview Overview Developer docs Developer docs Developer docs Pricing Pricing Pricing Regional Compliance Regional Compliance Regional Compliance Amazon Bedrock Amazon Bedrock Amazon Bedrock Google Cloud’s Vertex AI Google Cloud’s Vertex AI Google Cloud’s Vertex AI Console login Console login Console login Learn Blog Blog Blog Claude partner network Claude partner network Claude partner network Courses Courses Courses Connectors Connectors Connectors Customer stories Customer stories Customer stories Engineering at Anthropic Engineering at Anthropic Engineering at Anthropic Events Events Events Powered by Claude Powered by Claude Powered by Claude Service partners Service partners Service partners Startups program Startups program Startups program Tutorials Tutorials Tutorials Use cases Use cases Use cases Company Anthropic Anthropic Anthropic Careers Careers Careers Economic Futures Economic Futures Economic Futures Research Research Research News News News Responsible Scaling Policy Responsible Scaling Policy Responsible Scaling Policy Security and compliance Security and compliance Security and compliance Transparency Transparency Transparency Help and security Availability Availability Availability Status Status Status Support center Support center Support center Terms and policies Privacy choices Cookie settings We use cookies to deliver and improve our services, analyze site usage, and if you agree, to customize or personalize your experience and market our services to you. You can read our Cookie Policy here . Customize cookie settings Reject all cookies Accept all cookies Necessary Enables security and basic functionality. Required Analytics Enables tracking of site performance. Off Marketing Enables ads personalization and tracking. Off Save preferences Privacy policy Privacy policy Privacy policy Responsible disclosure policy Responsible disclosure policy Responsible disclosure policy Terms of service: Commercial Terms of service: Commercial Terms of service: Commercial Terms of service: Consumer Terms of service: Consumer Terms of service: Consumer Usage policy Usage policy Usage policy x.com x.com LinkedIn LinkedIn YouTube YouTube Instagram Instagram English (US) English (US) 日本語 (Japan) Deutsch (Germany) Français (France) 한국어 (South Korea) | 2026-01-13T08:47:52 |
https://dev.to/trohpso | Raphaël T - DEV Community Forem Feed Follow new Subforems to improve your feed DEV Community Follow A space to discuss and keep up software development and manage your software career Future Follow News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Open Forem Follow A general discussion space for the Forem community. If it doesn't have a home elsewhere, it belongs here Gamers Forem Follow An inclusive community for gaming enthusiasts Music Forem Follow From composing and gigging to gear, hot music takes, and everything in between. Vibe Coding Forem Follow Discussing AI software development, and showing off what we're building. Popcorn Movies and TV Follow Movie and TV enthusiasm, criticism and everything in-between. DUMB DEV Community Follow Memes and software development shitposting Design Community Follow Web design, graphic design and everything in-between Security Forem Follow Your central hub for all things security. From ethical hacking and CTFs to GRC and career development, for beginners and pros alike Golf Forem Follow A community of golfers and golfing enthusiasts Crypto Forem Follow A collaborative community for all things Crypto—from Bitcoin to protocol development and DeFi to NFTs and market analysis. Parenting Follow A place for parents to the share the joys, challenges, and wisdom that come from raising kids. We're here for them and for each other. Forem Core Follow Discussing the core forem open source software project — features, bugs, performance, self-hosting. Maker Forem Follow A community for makers, hobbyists, and professionals to discuss Arduino, Raspberry Pi, 3D printing, and much more. HMPL.js Forem Follow For developers using HMPL.js to build fast, lightweight web apps. A space to share projects, ask questions, and discuss server-driven templating Dropdown menu Dropdown menu Skip to content Navigation menu Search Powered by Algolia Search Log in Create account DEV Community Close Follow User actions Raphaël T 404 bio not found Joined Joined on Jul 20, 2025 github website More info about @trohpso Badges Writing Debut Awarded for writing and sharing your first DEV post! Continue sharing your work to earn the 4 Week Writing Streak Badge. Got it Close Post 2 posts published Comment 0 comments written Tag 0 tags followed Pin Pinned Setup C programming language for Windows users Raphaël T Raphaël T Raphaël T Follow Jan 9 Setup C programming language for Windows users # programming # c # cpp # vscode Comments Add Comment 1 min read Simple HTML Tailwind Integration With Bun Raphaël T Raphaël T Raphaël T Follow Jul 20 '25 Simple HTML Tailwind Integration With Bun # webdev # beginners # bunjs # tailwindcss Comments Add Comment 1 min read loading... 💎 DEV Diamond Sponsors Thank you to our Diamond Sponsors for supporting the DEV Community Google AI is the official AI Model and Platform Partner of DEV Neon is the official database partner of DEV Algolia is the official search partner of DEV DEV Community — A space to discuss and keep up software development and manage your software career Home DEV++ Podcasts Videos DEV Education Tracks DEV Challenges DEV Help Advertise on DEV DEV Showcase About Contact Free Postgres Database Software comparisons Forem Shop Code of Conduct Privacy Policy Terms of Use Built on Forem — the open source software that powers DEV and other inclusive communities. Made with love and Ruby on Rails . DEV Community © 2016 - 2026. We're a place where coders share, stay up-to-date and grow their careers. Log in Create account | 2026-01-13T08:47:52 |
https://jhall.io/tinydevops/2022-12-20-ec02ebf1/ | Tiny DevOps episode #50 Jonny Williams — What is Delivery Management? - Jonathan Hall Jonathan Hall Daily Email ☰ Blog Podcast Services Contact Tiny DevOps Podcast / Agile Principles Tiny DevOps episode #50 Jonny Williams — What is Delivery Management? December 20, 2022 Jonny Williams works at Red Hat as an agile Delivery Lead, and he joins Tiny DevOps to cut through the confusion surrounding "Delivery Management". Jonny Williams works at Red Hat as an agile Delivery Lead, and he joins Tiny DevOps to cut through the confusion surrounding "Delivery Management". In this episode... What is "Delivery Management"? The discipline vs the role Comparisons to Product Management, Agile, Lean, Scrum, ITIL, and ITSM History of Delivery Management How does Delivery Management fit into "Agile"? Where is Delivery Management most popular? How can you start benefiting from the Delivery Management discipline in your organization? How to get started as a Delivery Manager Who should avoid Delivery Management Guest Jonny Williams, Agile Delivery Lead at Red Hat Web site: https://delivervalue.uk/ LinkedIn: https://www.linkedin.com/in/jonny-williams-83433836/ Resources Book: Delivery Management: Enabling Teams to Deliver Value Transcript Jonathan Hall: Ladies and gentlemen, the Tiny DevOps Guy. [music] Jonathan Hall: Hello, everybody. Welcome to another exciting episode of the Tiny DevOps Podcast . I'm your host, Jonathan Hall, and today I am joined by author Jonny Williams, who has just released a new book, we're going to talk all about it. Welcome, Jonny, thanks for coming on. Before we dive into the topic of your book, would you introduce yourself? Tell us a little bit about your background, who you are, what you do, those sorts of things. Jonny Williams: Yes, absolutely. Thank you so much for having me on, it's really good to be here, really excited to have a conversation about the book as well. My name is Jonny Williams, I currently work as an Agile delivery lead at Red Hat so effectively working with customers to enable their adoption of container platforms and automation tools and effectively move towards that more DevOps-aligned culture. Broadly speaking, it's thinking about people, process, and technology, rather than just focusing on one of those three. It's a really interesting role and I love working with people who've got really deep technical knowledge. The thing that I enjoy most is bringing some of that culture change alongside people who are really smart and really understand quite complex technologies. My background prior to that has been working in the UK public sector. Working as a civil servant for a number of years in DWP during the course of the pandemic. DWP is our Department for Work and Pensions in the UK and I was working with platform teams in that space. Doing hybrid cloud work, Kubernetes, all that good stuff, but really working in that DevOps domain and exploring agility, and just trying to enable people to do amazing things and make amazing things happen. Jonathan: When you announced on LinkedIn, what has been now two, three weeks maybe? That your book was out. I didn't even know you were writing a book. I don't know if I should have known that, but we've followed each other for a while on LinkedIn and I saw the book and the title just jumped out at me. The title, spoiler, here we go, is Delivery Management . I'd heard that title, the job title, maybe for the first time a year ago and it's been confusing to me. I imagine it is for other people too and, of course, your book addresses that. I'd like to clear up some of that confusion today if we can and dive into a little bit about some of the things your book talks about. Let's just start with that. What is delivery management? Jonny: That is the question at the heart of the book. For me, the journey of writing the book really helps evolve my understanding of it because I think it's a question that a lot of people have. I would say, and the way that I've defined it in the book is that it's a discipline and that it's a discipline that focuses around aspects of enablement. That's really the way that I've framed it in the book. Impediment removal, coaching, and facilitation, but I think as a discipline, it's very tightly tied up with a role oftentimes people talk about and that job title of delivery manager. Myself, whilst I was working in the UK public sector, I wasn't an Agile delivery manager because there's flavors of delivery management that exist in the public sector. Equally, when I was talking with Marty Cagan about the book, he as someone who has written about delivery management nudged in that direction of saying, "Well, actually, there were private sector organizations, and especially large enterprises that had really explored whether that as a role could bring value." For him, he's framed it previously, which is something I explore in the book and his book inspired as it being something aligned with enabling product teams, which I fully agree with, but almost for him, he sees it as more of an evolution of project management. Personally, I prefer to decouple it from project management because I think actually, there are project managers who will stay in those roles and retain that job title. It's not to say that they can't harness the discipline of delivery management because for me, those three aspects of enablement can be used by almost anyone, from engineering managers to engineers themselves, or whether it's product managers as well. There's aspects of the discipline that I think people can use. However, I think it is distinct from project management and I think that's really important to call out. In many ways though, it does align very neatly with Agile coaching and Scrum mastery but I think the difference is, first and foremost, it's not aligned, specifically to something like Scrum. Then equally in terms of the Agile coaching domain, I think it involves having a bit more skin in the game. There's a bit of a closer tie to the team and especially in terms of that impediment removing aspects. I think a lot of the time Agile coaching is more about enablement in the sense that you're teaching other people how to move forward with something or helping them to find solutions. Whereas delivery management does have a bit more of that time where actually you have to proactively do things yourself to really make things work for a team and ensure that they're not being blocked. Jonathan: Fascinating. I actually think I was introduced to the concept of delivery management by Marty Cagan also, I was reading his book. After reading that I actually went to some of my friends who work as Scrum masters and Agile coaches and I said, "Hey, what do you know about this delivery management concept?" Their reaction was very negative, actually but I'll explain that a little bit more. It was like, "Oh, I think that's an old term or it's like a project management term." They had this idea that it was a straitjacket they have that some organizations make you wear. The same way that some people look at SAFe or even the Scrum master role. If you don't like Scrum, you look at the Scrum master role that way, right? I get the sense that is the same dichotomy we often have. If you've worked in an organization that does project management really well but in an organization that has done Scrum, very poorly, then you have this negative opinion of Scrum masters and product owners and whatever or you have this warm, fuzzy feeling about product managers and vice versa. It doesn't matter where you land. You think that one way, your way is the warm, fuzzy, nice way and everything else is the straitjackety, nonsense, old-school way. That's the vibe I got about delivery management but reading your book, it's completely not that at all. At least the way you portray it. I read that book and I'm like, this is great. I haven't finished the book, by the way, but everything I read, it's like, "This sounds great. This is exactly the work I like to do to help empower people, and work with people, understand their problems, all this stuff. I guess the point I want to make here is, if you have the idea in your head that delivery management is this straitjacket, that some organizations make you wear, maybe try to approach it with a more open mind and shed that preconception. Jonny: Yes, I could fully support that. I think that was one of the big drivers behind writing the book was effectively, it's something that's really poorly defined. I almost think it's really interesting in comparison with some of the frameworks and structures that exist within things like Scrum and SAFe because oftentimes, I think it's almost easy to disprove. I'd say especially with Scrum, having studied Scrum, and worked in really effective high-performing Scrum teams. The most effective Scrum teams were the ones that were using stuff from Kanban, that were using stuff from extreme programming, they were really applying good DevOps practices as well. It was not aligned purely to, here's the basics of the Scrum guide, plus all of these things, which really feel a bit more like anti-patterns. For instance, being really tied to a story pointing, for instance, which I know a lot of people nowadays would probably be quite keen to reject. I think delivery management, in many ways, feels similar. It has been for a long time lacking a definition, really. I think that the way it's described in Marty Cagan's writing, I think other people like Emily Webber, for instance, who's very prominent in the UK public sector, the way that they have described it has really helped. Nevertheless, there are plenty of organizations who are using delivery management as this quite archaic very command and control job title, that is really holding teams back rather than enabling them to move further forwards. For me, one of the key things especially having worked in a number of teams and organizations where delivery management was almost being used by quite senior leaders as a bit of a stick to beat people with and especially, this is something I know that Allen Holub talked about in terms of rejecting that delivery manager job title has been to say, well, someone can't be the lone person who's accountable or responsible for delivery. I completely agree with that. In many organizations, delivery management is seen as you're the person who's carrying the can, you're the person with delivery and your job title is solely responsible for everything delivery related. All of us who've worked in high-performing teams know that's daft because teams either fail together or they succeed together. They learn together, or they go on and effectively uncover new things and experiment together. It's one of these challenges for I think, a lot of leaders, a lot of organizations to really get their head around the fact that teams have to own stuff together. Delivery management is not about being the person who carries the can, much as a product manager can't be solely responsible for the lines of code that are created. In fact, is about enablement. It really is about helping teams to achieve more and deliver value collectively, and remove the things that get in their way that block them from actually achieving that outcome. Jonathan: How old is the title or the practice of delivery management? I only heard about it about a year ago but clearly, it's been around longer than that. Do you have a sense for the history of this role? Jonny: The most familiar space where I'm really aware of it is in the UK public sector. If anyone hasn't looked at the gov.uk revolution that happened in government digital service in the UK, there's a few governments that have really done innovative things. The government in Estonia who've done a lot of amazing digital work, Ukraine, as well have done some fantastic work in the digital space and I think that's been proven over the last year in very difficult circumstances, but roughly around 10 years ago, the government digital service was created in the UK and this was an initiative to effectively accelerate digital delivery. It's very much badged within that digital framework, which I know many of us working in the tech industry wouldn't necessarily align ourselves even with the badge of tech or digital because really, it's either just product or good engineering but actually, a lot of this space of government digital service embodied good product principles and good engineering principles. They hired some fantastic people and the delivery manager role rather than maybe the discipline or they think they are quite closely connected in terms of that government context, really began to emerge in the UK public sector with the emergence of government digital service. Prior to that though, there is some talk that delivery management in its more Agile-aligned, I guess is one way of putting it, or Lean an Agile-aligned form was something that existed in Spotify. That's always quite interesting. That was something I researched with the book and wasn't able to find strong proof of what form it had existed in if it ever did exist at Spotify. It might just be part of the myth of the discipline. Then prior to that as well, I think delivery management by its title feels quite logistical. Actually, that's something with the book where I've had to be quite explicit to say, this is delivery management as a discipline. We're not talking about logistics, we're not talking about service delivery management as well, which is obviously closely aligned with ITIL and ITSM. In terms of service delivery, that fits with a very traditional IT project management aligns even looping into some of the mythical man-month type stuff where we're talking about where does software go or where does IT go once it's been delivered? In this modern day and age, I think we all know that software isn't the same as building a house or it's not the same as building a bridge which you just hand over to the people who are going to give it a lick of paint every 5, 10 years. We all know it's continuous. It's organic and it's socio-technical, but in many ways, the history of the job ties into aspects of that as well where you have someone setting these guide rails for people to deliver something, but it's fixed much more like project management for instance. I think in the modern sense though, and the way that government digital service kicks things off from my experience, personally, and where I learned about stuff and really where the origins of what I believe is this discipline in the modern day and age really is tied into a lot of those ideas about product teams and about enablement as opposed to control. Jonathan: Your experience naturally starts in the UK because that's where you're from, but even in your book you talk about some of the adoption in the United States. I'm just curious, is there a regionalism to delivery management? Is it stronger? Even like Scrum I think is pretty strong in the Netherlands more than it is maybe in the US so a lot of these things they get popular in certain regions. Is delivery management more popular in certain areas than others? Jonny: I love that observation so much. I think that's absolutely spot on. I also think it's really fascinating that Scrum has really taken hold of the Netherlands and it's given us a gift of many talented and knowledgeable practitioners and experts from the Netherlands. People like the Liberators for instance, who just do fantastic stuff. For me, delivery management and the sales of the book have illustrated this to a certain degree. Regionally, I think it's quite popular in the UK but then that has started to spread out globally slightly more. For instance, organizations with roots in Canada and Australia have got more delivery management going on. I think what's very interesting in the US for instance though, is that stuff like engineering management, which isn't necessarily as prominent in places like the UK and Europe, I think if anything, again, it's very loosely defined. If we were to frame engineering management as a discipline as opposed to a job title, I think in many ways we'd struggle. I think many organizations though have gone down that pathway. The thing that I find most interesting about delivery management and its regional prominence is probably that the UK public sector has propelled it, but I know when I was speaking to people in regards to some of the beta readers for the book and its evolution, people did call out and say this has existed. Certainly, this set of disciplines exists in organizations. It's just that a lot of the time it gets bundled in with Agile coaching and Scrum mastery. I think it's useful though to draw that out and distinguish it because of those reasons of-- It's actually healthy for me personally, I think to move Scrum away from being a job title to a Scrum master really being that accountability of a set of things that help because otherwise, Scrum master paints the picture of being an end-all that it'll give you everything that you need to do. Whereas actually there's a lot of gaps and a lot of spaces that exist within that Scrum master accountability. Similarly, with Agile coaching, I think that again it makes more sense as a discipline as opposed to just being a fixed job title or role. Especially as there is obviously that aspect of the Agile industrial complex of people just getting certificates and really the credentials that someone has need to live up to being able to really help people. I think being badged as the coach or a coach for an organization is quite a high bar really. I think where delivery management is good and where it can fit in is that it's at more levels than some of those roles and more agnostic and more open-ended, but especially as a discipline. For me, I would really say in places like the US where there are product managers who potentially are having to carry the burden of doing a lot of enablement and coaching work as well as trying to hold all of that information for customers in their heads and support teams, delivery management might be able to help. Whether it's bringing in someone else to support with that or potentially enabling an engineering manager to take on more of that impediment removal and coaching work or even in terms of teams where I think actually, you've got self-organizing teams. I love this idea quite a lot of self-organizing teams that are purely made up of engineers or researchers where you don't necessarily have someone and very much in that small startup organization space where it really is just a bunch of engineers, but they're thinking, well, there's probably some cultural stuff that we can work on. Again, it's another space where I think delivery management can help. You don't need to wear the hat of being the "delivery manager" but I think as a discipline if for people who are in these spaces regionally, where they're not necessarily working in teams where there is someone functioning as an enabler proactively, but they think having an enabler in that space might help. My personal argument is that how could it not help? Actually picking up delivery management regardless of job title is good. I think it fits with that idea of which is true university I think around the world, is that we are starting to realize that job titles can actually hold us back quite a lot. Arguably it's about the disciplines that we apply more than anything. That's where something like this and hopefully reframing it as a discipline can maybe move people forward a little bit. Jonathan: I do want to talk more about the title concept a bit in a moment. First, I want to explore a little bit more where this discipline is used. You see it growing in the US and other places I guess. Where does it have the strongest foothold? Is it strongest in certain industries or certain company sizes? Is it small companies, big companies, or is it across the board? Jonny: I think what's really interesting from my government experience in terms of scale is that it is present throughout the UK government. I've seen it really prominently in that space. That is broadly speaking, as I say, there are a few flavors of delivery management that exist, but really aligning it to the discipline as I've described it, it's prominent throughout very large-scale parts of government. Department for Work and Pensions for instance, where I worked, if you purely looked at financial transactions, that would be the equivalent of the UK's largest bank. Obviously, as a country with a quite significant large financial services industry, really if you were to frame a part of government as the UK's equivalent of the largest bank it would say a lot the fact that that organization has been able to move towards DevOps and Agility and pick up these accountabilities or discipline aspects of delivery management. I think scale is an interesting one because actually whether it's an organization who are one team pretty much doing all of the work, I think that delivery management can help because it's not just about coordination between different groups of people, especially in that more startup or scale-up space where I'm seeing a few more delivery managers start to appear and a few more people applying the principles within delivery management to enable that aspect of healthy teams that feel psychologically safe, high trust environments. That in part is in the sense of actually the senior leadership people, so whether it's the CEO and CTO adopting aspects of this discipline as well. Understanding how to remove impediments, understanding how to apply stuff like team topologies to really think about the organic nature of their organization and how they want it to function. I think in terms globally as well, where it is starting to appear more and especially in private sector I think another reason I wrote about it as a discipline is that there's a lot more people starting to have this delivery lead or Agile delivery lead job title. I think that is relevant to this discipline because for many of those people in a more delivery lead-aligned role, I think it's almost exactly the same. They are there broadly speaking, to be an enabler, to be a facilitator, a coach, someone who removes impediments. Actually, I think that the prominence of that lead title, which is gradually emerging more and more because I think, and I can relate to this, for a lot of people, it's not necessarily appropriate to give that manager title. I think it's often the issue that product management has as well of product managers often end up being treated as if they're the manager of the team, which they shouldn't be, and it doesn't really help anyone. I think delivery leads is starting to appear in more and more organizations of all different shapes, sizes, scales, and certainly across government organizations in probably places, as I say, like Canada and Australia, certainly in the UK though. It's one of those things, the leading charge off the back of the book really, is that I think if any teams are struggling or certainly organizations thinking, maybe our teams could be achieving more or slightly more effective, I think efficiency is not the right idea. It's more about effectiveness and achieving outcomes. Then again, I would struggle to argue the case that a delivery manager or someone applying delivery management wouldn't help. I think inevitably if you've got someone in that enabling space, whatever their job title might be, how could that not help? Jonathan: I don't know what it's like in the UK. I don't know what the general public awareness or feeling is about the government, but as an American, I don't think about government programs and think agility and think efficiency, it's like when I hear about a government program in the US that's efficient and agile, it's like, wow, that's noteworthy. I don't know if it's the same in the UK, but just assuming that some of our listeners have the same concept that I do, that government means slow, bloat, bureaucracy. Can you give us an example of where delivery management has been effective in your experience in the UK government? Jonny: Yes, that is such a good point and I think that it's something that actually Marty Cagan pointed out and he was like, you probably don't want to be talking about delivery management just in terms of public sector. I completely agreed with that and I was like, yes, this is not specific to public sector stuff. Where it has helped and again, to lean into the Department for Work and Pensions. I think some of the successes that I've seen, whether it be gov.uk, which I would urge people just to look at the story and the history there and some of the great people who've worked in that space and especially the achievements around actually delivering accessible software solutions for citizens. Stuff that is really easy to use beyond just gov.uk, the website, but also stuff like Notify, which is a service that was created by government digital service that basically it's is consumed, it's a component that lots of other parts of government can consume to send out text alerts and stuff like that. It completely simplified a space that was really hideous and complex. The classic thing of look at an organization, the odds are they'll have 26 different address lookup services or something ridiculous and actually I think looking at simplification and considering stuff like bounded context and these sorts of things are spaces where actually delivering management, again, it helps because it's coaching towards things being more effective and really honing in on what outcomes people are trying to achieve. That space of government digital service is a key one but I think also I always talk about in the Department of Work and Pensions, so we have a thing called Universal Credit, which effectively is like the benefits payment solution and that was a space that was really struggling because it was a very ambitious policy, which was it completely tied into that space of bloated government programs that weren't really going anywhere treading water. It was this space where they moved away from big bang, let's design some massive plan on a wall and actually shifted much more towards, well, what's the smallest valuable thing that we could deliver? So actually, Universal Credit is an incredibly modular solution, which when we hit the pandemic and we needed to shift the model of benefits payments. Of course, when we talk about benefits claimants, the largest group of people receiving benefits are pensioners in the UK, and oftentimes we look at pensioners as being completely separate and distinct, but actually, these are people still receiving payments on a day-to-day or weekly basis. We had to change the model almost completely. I say we, UK government and people working, doing incredibly long hours to get this done over the course of the pandemic in the Department of Work and Pensions. It was because of that modular construction, because of the way that it was designed to actually be iterative and incremental that enabled something that normally when we look at government, it is, and I've experienced this firsthand, there's aspects in the book where I talk about large scale transformations that were just destined to die a hideous death whilst wasting loads of taxpayers money because of the fact they were trying to do this big bang insane stuff without really thinking about culture or whether people are ready. I think instead about the stuff with Universal Credit, for instance, just as one example where to create something is that large and provides that much value to citizens of a country but actually could scale and shift and mold itself rapidly in an emergency. I think that really shows the fact that actually governments can move in a more agile direction. They can deliver stuff in a more incremental, iterative way and really harness the learnings as well of successful private sector organizations because it's not that the private sector gets everything right. I think we're all eagerly awaiting the outcomes and stuff, like Twitter for instance as well. I know all of the chaos that's happening there which feels like it could be a bet that turns out in the direction that a lot of people are thinking it won't, but equally feels like it goes against a lot of my beliefs personally at least. Jonathan: Yes. I'm not placing bets either way on that one. Jonny: No, I'm keeping my money in my pocket, personally. The money is staying in my hands. I'd rather not. I'd have to have a really good spread bet I think to ensure that I didn't lose out right. I think it's a good example though where actually the core principles really for what I've seen in government, which are probably more important for private sector organizations than for the people that look at government as well and go, bureaucracy and slow delivery effectively and not actually achieving something valuable. The key difference in the stuff that I've seen, which I now champion, this is one of the big things that I do for work, is trying to get people to move away from that. It's definitely an uphill battle, but there are really good people who are trying to learn from industry and actually read books. That's one of the things that does frustrate me sometimes is when we talk with senior executives and leaders and it's just like, when was the last time you read a book? I think you can tell a lot from people. It doesn't have to be a book, it could be an audiobook or read blog posts or whatever it looks like, or just follow people on LinkedIn, but the less that those people are engaged with ideas, the less likely it is that they'll actually be able to support an organization to perform effectively. Working with people who really champion change is what I love doing and those people do exist even in slightly more hostile environments where the waterfall is still the defined way of doing things. Jonathan: That's a great segue. You mentioned waterfall. What is the relationship? We've talked touched on this, but I want to make it more clear to the listener. What's the relationship between delivery management and Agile software development? Is it an Agile framework, methodology? Is there overlap? Are there differences? How do you describe that? Jonny: I don't intrinsically tie it to agility. I think this is something that previous attempts to describe the discipline. I think Emily Webber's description of it previously where she talks, one of the key elements is Agile and Lean practices or ensuring that teams are able to apply Agile and Lean approaches for one thing. I think actually Agile is often something that's, people turn their nose up at it a little bit and I think Lean less so because it's easier for it to be validated in that manufacturing context where really it is proven time and time again. I would argue that agility isn't Agile, but I think capital A Agile has ended up really limiting the progress in that movement and moving us away from some of the stuff in the manifesto. I had a really good conversation with someone a while back about DevOps really being quite an organic evolution of Agile really it's kind of the same thing but just with slightly more defined cultural aspects really. I like talking about DevOps as an approach more than anything else as well but it's fascinating to see as well, DevOps is falling out of favor with some people and now they're talking about platform engineering, and after that there'll be something else as well. It will always churn. There'll be always a new thing emerging, whether it's driven by the big four or whether it's driven by people on the ground, whether it's driven through companies like GitLab for instance when I did their team ops training the other day, which is very similar principles, it's very similar content but with a new badge, with a new title. For me, I think that delivery management isn't intrinsically about agility or about Lean, in fact I should say Agile and probably lean into big A Agile because it is about agility but probably in the looser sense and true business agility of really delivering value because that's what business agility is all about. I don't think you have to be an Agile and Lean or consider yourself at least to be an Agile and Lean practitioner to harness this. I think a lot of stuff, I did read a great thing the other day, it might have just been a simple tweet, but someone said, common sense doesn't really exist because common sense is purely objective. It is about your lived reality and your lived experience. I would almost avoid saying that a lot of this stuff in the book feels like common sense because feels like common sense to me because I've seen teams succeed and I've seen teams not succeed. I wouldn't like to say fail, but maybe not do as much as they could have done. I think a lot of the stuff in the book and in terms of delivery management as a discipline, as soon as it's in motion, it becomes really apparent why this works, why it makes sense to build an environment where people feel like they trust each other, where they feel psychologically safe and that isn't something that is prescriptively tied to Agile or prescriptively tied to Lean or any framework. It is stuff that really that for one example of building a space where people actually feel like themselves, where they feel okay, that is universal or at least it should be and actually I think that means it doesn't just have to be people who are operating in this space where maybe they've certifications and they're Scrum masters or they're working in product teams in certain organizations. I think again, there is a universality to coaching, enablement, facilitation as things that can really support any team to do better work to achieve more and also to do it sustainably. I think that's a key part as well, is it doesn't have to be tied to Agile because of the fact that really any organization should be looking to deliver value in a sustainable fashion and achieve valuable outcomes ultimately because otherwise, the question is why do they exist? If they exist to deliver value, I think delivery management can help. Jonathan: Does delivery management work for non-software projects or is it specifically a software discipline? Jonny: That is a really cool question because I have some fantastic examples that I jumped into further whilst I was writing the book. Actually, it gave me a good kick up the backside to not just write about software because platform engineering and working with teams that are doing stuff around OpenShift and Kubernetes is what I'm doing day in and day out at the moment. I'm in my rabbit hole of software and quite complex technical delivery working on some middleware stuff as well at the moment which is deeply technical and quite interesting. I've actually worked with people where delivery management was applied in a way that's really well aligned to the book in a marketing context which is fascinating. I think really looking at marketing as more of a product and shifting away from it being again that almost the traditional way that the business IT paradigm existed and still exists in some organizations. I think marketing is often looked at that way as well, but really treating a marketing offer as more of a service with intrinsic products within it aligns really nicely with delivery management because I think again, to have someone who's there enabling a team to collaborate, support each other and move towards valuable outcomes that are clearly defined all of that stuff, and especially in marketing context as well, they still have the questions of when will it be done? Bringing some of these principles and practices to that space is really interesting. The other one as well, which is a good example which I think really feels beyond software but actually is quite closely linked. I talk in the book, I refer back to that classic idea of software eating the world. I think everything pretty much is software nowadays but the few things that sometimes feel like they aren't software, policy was a great example and there's a fantastic guy, he's on Twitter called James Cattle, who does loads of brilliant community work across UK public sector, but shares a lot of really insightful things. James Cattle actually called someone out a while ago saying, "Don't talk about delivery management as if it's purely for software teams or product teams." I'm working with a policy team at the moment who are doing psychological work. This was his big statement. We are working with psychologists, we're working with user researchers, we're working with people who are defining really detailed and difficult policy and we're doing great delivery management. I thought that was fantastic and I love the fact that you called it out as well in a really blunt way. It could be a team of psychologists, a team of marketers. I think again having that enabling function and discipline in a team is sure to help them. Jonathan: I think it's pretty clear from the context of what you've been describing the answer to my question, but I want to just make it explicit for anybody listening, the title delivery management almost sounds like it's a last mile job. You do all the design, you do all the building, you do all the testing, and then you deliver. That's not what you're talking about though. You're talking about more of a holistic approach and maybe just address that a little bit and make that clear for anybody listening that this isn't just like a last mile discipline. Jonny: Yes, definitely. That way of viewing delivery is almost like framing a marathon as being just the moment that you crossed the finish line. I think what's really interesting with the way that we often talk about delivery is that moment where something moves on the Kanban board to done, but actually what about all of the stuff before that? I think just like with a marathon, it isn't even just when you start the race, it's all of the other stuff as well. It's all of your training, it's all of your prep, it's all of the ways the shoes that you're buying to run in. I knew a guy who recently ran a marathon cause he was trying to break his record. He bought a blood sugar monitor that was plugged in. Whether it's the small things or the big things, I would personally look at all of that and say that's still delivery. Because really delivery isn't about when you move the thing over in the column to done or when it goes into prod. This is something I've talked about quite a few times is, can you really say anything is done if it's not running in prod or if users aren't even touching it. Is anything done until actually it's interacted with? All of the stuff that comes before that moment of someone picking it up and playing with it or pushing buttons or clicking on it. All of the stuff that comes before then in my mind is also delivery. I think it's a challenge for some people to look at it that way because oftentimes we talk about the user research or the design before we move into a delivery phase. I think all of the things that come before that "delivery phase" are so intrinsically linked to realizing and achieving valuable outcomes that you'd be insane not to join up those dots and ensure that everything that comes before that is supported and actually easy to accomplish as well. Jonathan: I think anybody listening is probably familiar with a lot of the baggage and bad habits that come with terms like DevOps and Agile. You mentioned story points that's taking on that feeling in a lot of corners. The story points are remnant of the past or maybe they're at least not done well, maybe there's a good way to do it but they're not done well. Do you have the same thing in delivery management or is it early for that and if so, can you give examples of some bad habits or cargo culting that might happen around in that discipline? Jonny: Sooner Safer Happier was a big influence on the book and the stuff that Jon Smart's written about. Thinking about anti-patterns and patterns was something that came to mind quite frequently whilst I was writing the book. I think some of those anti-patterns are when people might feel that they're inhabiting that delivery management space. This is a reason I talked about it as a discipline rather than a job title because I think it's easy for someone to have that job title but actually be working as a project manager. For me, that feels very different. Those are very different things and I know Allan Kelly's book, for instance, Project Myopia where I think he talked about the fact that projects and Agile are intrinsically at odds. It's very difficult to reconcile those things because projects are fixed and limited and about command and project management is very much about top-down stuff. I think for me, as much as project managers can add a lot of value in organizations, one of the biggest anti-patterns is someone who's wearing that hat of delivery manager, but actually, under the hood, they're working as a project manager. I think the other aspect that comes with that is even if you are attempting to apply the discipline of delivery management regardless of your job title regardless of role, it's misunderstandings around the coaching aspects and coaching can be really difficult. I think it's very tough to be an effective coach whether you are working as a technical coach, someone who's in that directive coaching role. I talk about the difference a little bit between someone who's like a football coach who's more directive. You help people learn the plays, you help them understand where they need to be stood on the field as opposed to non-directive coaching which involves more like that professional coaching stance of asking open-ended questions, powerful questions that help people uncover stuff for themselves and maximize their potential by seeing the stuff that was in themselves for the whole time. I think really understanding that coaching function is one of the biggest challenges for effective delivery management. One of the largest sources of anti-patterns that I've seen is where people are dogmatic or almost too directive because I think as soon as you are the person who's saying to the team, you need to do this, you need to do that and especially the biggest thing that I've seen that really I struggle with, which aligns with that point I made around project management, the idea of someone who says that they're applying the discipline of delivery management whilst dishing out tickets and telling people what they're doing for the day, I just think is out and out wrong. I just don't think that helps a team to really deliver value or achieve the outcomes they're working towards because they're a room full of adults and adults don't need to be given stuff in that way. They're not robots, they're not machines. Moving away from Taylorism and that aspect of some manager stood at the back of the room bossing everyone around, if you're doing anything that looks or feels like that, then you're not doing delivery management. Jonathan: Let's talk to the listener who thinks that delivery management might be something that they could benefit from. Maybe they're not doing it or maybe they're not doing all of it yet and they think they could benefit. How can they get started in exploring this? Obviously, they can buy your book and we'll provide details on that at the end of the show. Let's say that they're in management and they have the authority to start making some changes along this way. What should they do? How do they get started on this journey? Jonny: For me personally, I think the best advice I'd give almost with anything, any type of change, is just start small and find the place where you can affect change that's the most minimal, smallest possible thing, the smallest slice of value that you can look at. Thinking about delivery management as a discipline in terms of those three aspects of enablement and coming really back to the heart of delivery management being about enabling other people considering those aspects of impediment removal and coaching and fascilitation, it could just be starting with something really small. I'm big fan of the book The Coaching Habit , and I talk about that briefly in the book. Reframing your management stance away from being a manager, let's say, if that's the role that you're in or something that's maybe a more traditional role where actually you want to move towards being an enabler rather than a director, let's say. I think that moving towards stuff of using powerful questions for instance and applying a listening stance rather than a directive stance. Certainly one of the things, a really tiny thing that I'm a huge fan of is if you're in a room full of people, it's some of that leaders eat last mentality. Rather than saying, here's what I think now, what do you think? It's even that small switch, which aligns really nicely with some of the stuff in the book to saying, "What do you all think first? Then saying, "Great taking that on board, here's how I think maybe we could apply that." Again, going back out to say, not necessarily to get consensus, but at least to ensure that it's been communicated and that people understand where we are. For me personally, it's the really small things. For instance, with facilitation that ties in directly to what I've just said of just find those ways to give other people a platform and move away from being big boss. I think as well the book Turn the Ship Around shifting towards intent-based leadership where really it's about saying, "What do you want to do? How are you going to achieve this outcome?" Ensuring that people have got a clear vision, a clear direction they're heading in. If you are supporting all of that stuff, then I'd argue you're probably moving in the direction of delivering management already. There's a load of ways you can implement it, even in the smallest spaces of your organization. If you can harness it fully, I think the way it can move teams forward is just dramatic and really powerful. Jonathan: Now for other listeners, maybe someone listening is-- Maybe they're a Scrum master, an Agile coach, or they have an inclination in that direction. They're thinking, "Hey, this delivery management thing sounds pretty cool. I'd like to learn more about that as a practice and it's a discipline." How do they go about that? Can they get certified somewhere? What kind of training is available? Where do they go? Jonny: That is a really good question as well. I think obviously, really basic plug, I'd obviously be really keen to point people towards my book and give that a look and have a think. I think the title of the book says it all. It is Delivery Management: Enabling Team to Deliver Value . If that's what people are into, whether as a Scrum master or an Agile coach, then take a look. I would say beyond that, there is some training available from ICAgile, have a delivery management track. I've talked with them, actually had some really interesting conversations because at the moment their track involves their, I believe it's the Agile project and delivery management smaller certification, which is badged as I believe it's ICPAPM. I think there's loads of great content in that, but for me personally, I'm very keen on decoupling delivery management from project management, including Agile project management as well because I think seeing them as distinct and separate is valuable. Especially as for me personally, I think delivery management is better aligned to products and tying in some of the stuff like Mik Kersten's book Project to Product . Really for me, I think that those long-lived teams, long-lived products, value streams, all of that stuff fits very neatly with delivery management as opposed to with delivering something up to an end date, which is much more closely aligned with project management, both of a traditional flavor or an Agile flavor. I think that that training is really good. There is a load of really interesting content on that. I'd say if people are interested, check out the learning outcomes that are on that track. Broadly speaking as well, I think some of the facilitation training that's out there as well is a great stepping stone and coaching training is a great stepping stone to help people harness delivery management. The other thing that I'd urge people to do really is just consider those spaces, which I certainly think for Scrum masters especially, but Agile coaches do this as well, is to really reflect on where they have removed impediments, removed blockers and enabled teams to-- It's the stuff as well of don't just manage dependencies, remove them, kill them, cut them off at the neck. It's stuff like that where if you can reflect, I don't think you can ever really get full deep detail training on removing impediments, but what you can do is learn lessons and gradually transition from knowledge to wisdom, embed that stuff in, really reflect on it, really consider what is going to unlock that capability both in you but also in a team. I talk about the Pareto principle in the book. Impediment removal is almost always going to be the thing that gobbles up 80% of the time, even if it only achieves 20% of the value that can be achieved. Whereas I think the coaching and facilitation aspects end up being a smaller part of the role, but probably the one that unlocks the most value in the long term. Be prepared for really tough impediment removal because it can take months if not years to remove an impediment, but when it's done, it opens up the doors to faster flow of change. I think especially as well, it's an interesting challenge for people to see between that space of Scrum mastery a | 2026-01-13T08:47:52 |
https://dev.to/devdiscuss/s7-e6-what-a-quantitative-trader-can-teach-you-about-a-b-testing-and-beyond | S7:E6 - What a Quantitative Trader Can Teach You About A/B Testing and Beyond - DEV Community Forem Feed Follow new Subforems to improve your feed DEV Community Follow A space to discuss and keep up software development and manage your software career Future Follow News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Open Forem Follow A general discussion space for the Forem community. If it doesn't have a home elsewhere, it belongs here Gamers Forem Follow An inclusive community for gaming enthusiasts Music Forem Follow From composing and gigging to gear, hot music takes, and everything in between. Vibe Coding Forem Follow Discussing AI software development, and showing off what we're building. Popcorn Movies and TV Follow Movie and TV enthusiasm, criticism and everything in-between. DUMB DEV Community Follow Memes and software development shitposting Design Community Follow Web design, graphic design and everything in-between Security Forem Follow Your central hub for all things security. From ethical hacking and CTFs to GRC and career development, for beginners and pros alike Golf Forem Follow A community of golfers and golfing enthusiasts Crypto Forem Follow A collaborative community for all things Crypto—from Bitcoin to protocol development and DeFi to NFTs and market analysis. Parenting Follow A place for parents to the share the joys, challenges, and wisdom that come from raising kids. We're here for them and for each other. Forem Core Follow Discussing the core forem open source software project — features, bugs, performance, self-hosting. Maker Forem Follow A community for makers, hobbyists, and professionals to discuss Arduino, Raspberry Pi, 3D printing, and much more. HMPL.js Forem Follow For developers using HMPL.js to build fast, lightweight web apps. A space to share projects, ask questions, and discuss server-driven templating Dropdown menu Dropdown menu Skip to content Navigation menu Search Powered by Algolia Search Log in Create account DEV Community Close DevDiscuss Follow S7:E6 - What a Quantitative Trader Can Teach You About A/B Testing and Beyond Dec 15 '21 play In this episode, we talk about A/B testing with David Sweet, adjunct professor at yeshiva university, and author of the book, Tuning Up: From A/B testing to Bayesian Optimization. After listening, if you would like a 35% discount on Tuning Up: From A/B testing to Bayesian Optimization, go to the link in our show notes and use offer code devdsrf-38BF. Show Notes Vultr (sponsor) DevNews (sponsor) CodeNewbie (sponsor) New Relic (sponsor) Microsoft 30 Days to Learn It (DevDiscuss) (sponsor) Tuning Up: From A/B testing to Bayesian Optimization David Sweet David Sweet is a quantitative trader at 3Red Partners, adjunct professor at yeshiva university, and author of the book, Tuning Up: From A/B testing to Bayesian Optimization. Episode source Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Your browser does not support the audio element. 1x initializing... × 💎 DEV Diamond Sponsors Thank you to our Diamond Sponsors for supporting the DEV Community Google AI is the official AI Model and Platform Partner of DEV Neon is the official database partner of DEV Algolia is the official search partner of DEV DEV Community — A space to discuss and keep up software development and manage your software career Home DEV++ Podcasts Videos DEV Education Tracks DEV Challenges DEV Help Advertise on DEV DEV Showcase About Contact Free Postgres Database Software comparisons Forem Shop Code of Conduct Privacy Policy Terms of Use Built on Forem — the open source software that powers DEV and other inclusive communities. Made with love and Ruby on Rails . DEV Community © 2016 - 2026. We're a place where coders share, stay up-to-date and grow their careers. Log in Create account | 2026-01-13T08:47:52 |
https://ruul.io//blog/is-upwork-legit-things-you-need-to-know-about-it | Is Upwork Legit and Trustworthy? 6 Things to Know Product Payment Requests Get paid anywhere. Sell Services Make your services buyable Sell Products Create once sell forever Subscriptions Get paid on repeat Ruul Space Your personel storefront. One link for everything you offer. Learn more Pricing Resources Partner Programs Referral Program Get 1% for life. Seriously. Affiliate Program Bring users, get paid Partners Let’s grow together. More Blog About us Support Brand Kit For Customers Log in Sign up For Businesses Login Sign up grow Is Upwork Legit? 6 Things You Need To Know About It Wondering if Upwork is legit? Discover the top 6 things every freelancer and business owner should know. Read on for more information! Canan Başer 5 min read RUUL FOR INDEPENDENCE You chose independence.We make sure you keep it. Sell your time, your talent, whatever you create or build always on your terms. Get started See Example This is also a heading This is a heading Key Points Upwork was founded in 2013 through the merger of Elance and oDesk. The platform has 18 million freelancers and around 1 million clients. Major companies like Microsoft and Airbnb actively use Upwork. Legally binding contracts protect all projects. The Milestone System allows projects to be completed and paid in phases. The Escrow system ensures clients fund projects before work begins. Hourly Payment Protection tracks work through the Upwork desktop app. Dispute resolution services provide support for both parties. NDAs are optional and can be used when desired. A 10% service fee is deducted from freelancers’ earnings. Clients have between 3% and 5% deducted from their payments. Criticisms include high fees, intense competition, and lack of support. Starting April 3, 2025, a $4.99 fee will apply to contracts of $100 or less. Is Upwork really "legit"? I mean, do people actually make money there? Or is it all just a big hype? "Is Upwork trustworthy?" or, more accurately, "Is this really happening?" After all, no one has time on their hands. Time is money. That's why we're giving you 7 things to know about Upwork. 1. What is Upwork? Upwork is a massive freelancing marketplace. It has 18 million freelancers and nearly 1 million clients . It often draws comparisons with Freelancer.com and Fiverr . But Upwork is more corporate than the others. That's why Microsoft, Airbnb, and Automattic choose it. For instance, Microsoft has 10,000 projects under way here. Source 2. The birth of Upwork Do you remember Elance and oDesk ? Two once popular platforms. And you can guess what happened. In 2013, they merged, and the result was this thing: Upwork. 3. Payment and security systems Whether you're a freelancer or a client on Upwork, it doesn't matter. Keeping you paid is paramount because you don't want to get scammed. Rest assured: You probably won't get scammed. The risk of getting scammed is minimized by Upwork's payment and security system. P.S. Freelancers want to work, not chase payments. Let Ruul handle Billing & Payment Collection with its top-notch cloud system—so you can focus on what you do best. Milestone system The milestone system is a great invention for freelancers and clients. It's an Upwork feature designed for a structure that makes you feel completely secure. How does it work? The project is done in parts and paid for in parts . Simple example: Milestone 1: Design of the homepage - Payment: $100 Milestone 2: Coding all pages - Payment: $200 Milestone 3: Publish and test the site - Payment: $100 Thus, both the employer and the freelancer feel safe at every step: If you are a freelancer, you don't need to finish the whole project without security. You get paid after completing a part. If you are a client , you don't have to risk the entire project budget. You pay as you approve each project step. Escrow system The escrow system is used for mutual security. Here's how it works: If a project agreement has been reached, the client has to finance the project: Full project budget, or Min 2 milestones. And until the freelancer completes the work, the money you paid remains in escrow . If you are the client and have reviewed the project, you can approve the project or milestones and transfer the budget to the freelancer. If you do nothing, you give your approval. The funds are transferred to the freelancer after 14 days . Note that at this point you have 14 days to appeal. What are the benefits? The freelancer is assured of payment and works with peace of mind. The client pays as they see the project and stays on budget. However, everything takes time here. That’s where Ruul shines out. Benefit of Ruul: Getting paid is easy, just submit your payment request. Ruul handles invoicing & payment collection and transfers payments to your preferred account in 24 hours. Upwork’s hourly payment protection Hourly contracts can be risky. You want to make sure that the freelancer you hire is actually working. Upwork has found a solution for that. Thanks to the "Upwork Desktop App", which allows time tracking, it allows you to protect hourly payments. How it works? The freelancer and the client use time-tracking via the desktop app. The freelancer's desktop screen takes 6 random images per hour. Keystrokes, mouse movements, and screen scrolls are tracked. If you are a freelancer, here's a note: the app shows your click count, but not what you clicked. It sees your keystrokes, but not what you typed. How to install it? Install on the desktop: Available for Windows , Mac OS (works better on OS X 12 and above), and Linux . You can download an appropriate version for your operating system from the Upwork website by clicking here . How does it help employers? As an employer, you can track the freelancer's work activity with time tracking. You will be able to present the recorded activities as evidence in the event of a dispute. Dispute resolution service There may be disagreements. The important thing is to find solutions. As a freelancer or client, you can contact Upwork's dispute resolution service if you feel you have been wronged. When is it needed? As a freelancer; When the client claims that the work you deliver is not of the expected quality. When the client keeps making new requests instead of guiding the project. When the client cannot be contacted during the work process. When the client changes the project but expects the same fee. As a client; If the freelancer charges additional fees for work that he/she does not do. If the freelancer demands payment before the work is completed. If there is no regular communication with the freelancer. If the freelancer has missed the deadline. If project requirements are not fully met. How to open a dispute? Go to the All Jobs section of your Upwork account to open a dispute. Find the job you are having a problem with. Select the dispute. Upwork's goal is usually to resolve the issue between the freelancer and the employer. However, Upwork's mediation process kicks in if you can't find a solution. If you wish, you can withdraw or update a dispute later. Upwork's page about disputes can help you. 4. Legal protections and policies There are a number of legal protections and policies that contribute to Upwork's legitimacy. Freelancers and clients agree to legally binding contracts when starting a project. This promises that both parties will fulfill their obligations. Upwork's Terms of Service outlines the rights and responsibilities of both parties, including intellectual property rights, confidentiality agreements, and dispute resolution processes. Most important policies Upwork has policies on many things. But some are more critical. In fact, these are things that should be on every platform. In particular, if a client or freelancer is harassing you because of your language, religion, race, gender, or sexual orientation, you should report it to Upwork to protect your rights. You can also speak up if there is any violence, threats, or incitement to violence. Confidentiality agreements Your work may require some of your projects to be conducted in secret. In such a case, the easiest way to provide the freelancer with important information about your project is to implement an optional confidentiality agreement. However, keep this in mind. Upwork does not make you sign a contract on the site. It only states that you can do that. So if you want to keep your project secret, you have to deal with freelancers. 5. Costs and fees Now we come to one of the most important questions. Nobody wants to work on a platform where they have to pay for everything and everything is profit driven. So, are Upwork's fees too high for freelancers and clients? Let us break this topic down into two parts - one for freelancers and one for clients. Cost & fee for freelancers There is no signup fee for you. But that doesn't make Upwork totally free. Here are 3 important costs for you: Buy Connects (to bid) Fee on earnings Withdrawal fees Happy to share: Ruul has no subscription pricing. We’re using a pay-as-you-go model . Easy, open your account and get started for free. Let’s get back to the Upwork pricing model. Connects Upwork has a bidding system. This system is based on freelancers bidding on project requests. And it isn't free. What will you do? Of course, you need to buy Connects. Current Connects prices: Or you can buy Upwork's Freelancer Plus plan , which automatically credits 100 Connects per month to your account. Upwork Freelancer Plus subscription will cost you $19.99 per month. This plan includes: Upwork's UMA AI feature: It helps you write better proposal texts and supports your job-hunting process. Custom profile URL: A URL in your own name - for those who want to create a personal brand. View competitor bids: You can see how other freelancers are bidding. Fee on earnings Upwork typically takes a 10% cut of every dollar freelancers earn. By comparison, Freelancer.com charges the same fee . But Fiverr used to charge 20%. If you make $500, you get $450. If you earn $1000, you get $900. If you earn $2000, you get $1800. You don't have to do anything, they automatically take this fee from your balance. And, this rate applies to every contract, whether it is hourly, fixed, or project catalog. Withdrawal costs Among other costs, withdrawal costs should not be ignored. We will provide these fees with payment methods . Instant payment for US residents: $2 To local bank outside the US: $0.99 Direct to US Bank: free USD Wire Transfer: $50 Other apps you can get paid: PayPal (Most common) Payoneer (outside the US) M-Pesa (Kenya Only) Cost & fee for clients You can create your Upwork account for free. And after that? Naturally, this isn't free. Let's zoom in on all the costs you might incur. Typical service fee Upwork typically charges a 3% or 5% fee when you hire. However, this rate can vary depending on the plan you have. You can see it here: In the meantime, let's make an important Upwork notification. The latest news is that Upwork will charge a $4.99 fee for Business Plus contracts of $100 or less. It's called the "Contract initiation fee". As of April 3, 2025, it will be applied. 6. User reviews for Upwork No matter how much we talk about it, the real truth is to ask the users. Do they agree that Upwork is legitimate? First, let's look at Upwork's rating on popular review sites. G2 - 4.6 Gartner - 3.9 Mobile apps? App Store - 4.6 Google Play Store 3.9 What do users like? User-friendly interface (mentioned in many reviews) Opportunity to find jobs in a wide range of categories Easy customer communication Filtering options What do users dislike? High service fees Intense competition Lack of customer support Connects cost Policy changes Source of comments What about Ruul Users? Besides more than 100,00 freelancers , leading companies trust Ruul as well. To expand your business with effective co-marketing join our partner program . ABOUT THE AUTHOR Canan Başer Developing and implementing creative growth strategies. At Ruul, I focus on strengthening our brand and delivering real value to our global community through impactful content and marketing projects. More What Is Linktree And How Freelancers Use It To Get Paid? Discover how Linktree helps content creators monetize their audience and why freelancers are switching to Ruul Space for invoicing, payments, and tax compliance. Read more Latest global visa regulations for digital nomads and remote workers Want to travel the world while you work? Discover the power of digital nomad visas and how they can help you make your remote work dreams a reality. Read more 7 podcast episodes that will boost your creativity Discover the best motivational and informative podcasts to expand your brain's limits and improve your creativity in 2022. Read more MORE THAN 120,000 Independents Over 120,000 independents trust Ruul to sell their services, digital products, and securely manage their payments. FROM 190 Countries Truly global coverage: trusted across 190 countries with seamless payouts available in 140 currencies. PROCESSED $200m+ of Transactions Over $200M successfully processed, backed by an 8-year legacy of secure, reliable transactions trusted by independents worldwide. FREQUENTLY ASKED QUESTIONS Everything you need to know. Get clear, straightforward answers to the most common questions about using Ruul. hey@ruul.io What is Ruul? Ruul is a merchant-of-record platform helping freelancers and creators globally sell services, digital products, subscriptions, and easily get paid. Who is Ruul for? Ruul is designed for freelancers, creators, and independent professionals who want a simple way to sell online and get paid globally. How does Ruul work? Open an account, complete a quick verification (KYC), and link your payout account. Then, start selling through your store or send payment requests to customers instantly. How does pricing work? Signing up is free. There are no subscription or hidden fees. Ruul charges a small commission only when you sell or get paid through the platform. What is a Merchant of Record? A merchant of record is the legal seller responsible for processing payments, handling taxes, and managing compliance for each transaction. What can I sell on Ruul? You can sell services, digital products, license keys, online courses, subscriptions, and digital memberships. How do I get paid on Ruul? Add your preferred bank account, digital wallet, or receive payouts in stablecoins as crypto. Funds arrive within 24 hours after a payout is triggered. OPEN AN ACCOUNT START MAKING MONEY TODAY ruul.space/ Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. Trustpilot Product Payment Requests Sell Services Sell Products Subscriptions Ruul Space Pricing For Businesses Resources Blog About Contact Support Referral Program Affiliate Program Partner Program Tools Invoice Generator NDA Generator Service Agreement Generator Freelancer Hourly Rate Calculator All Rights Reserved © 2025 Terms Of Use Privacy Policy | 2026-01-13T08:47:52 |
http://www.eeoc.gov/facts/qanda.html | Federal Laws Prohibiting Job Discrimination Questions And Answers | U.S. Equal Employment Opportunity Commission Skip to main content An official website of the United States government Here’s how you know Here’s how you know Official websites use .gov A .gov website belongs to an official government organization in the United States. Secure .gov websites use HTTPS A lock ( Lock A locked padlock ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites. U.S. Equal Employment Opportunity Commission Menu Any of these words (optional) Search About EEOC About EEOC Overview The Commission and The General Counsel Meetings of the Commission Commission Votes EEOC History News and Information Newsroom What You Should Know Legislative Affairs Publications Outreach and Education FOIA Laws and Enforcement EEOC Legal Resources Mediation Litigation Systemic Enforcement Commissioner Charges Directed Investigations Programs and Performance Budget and Performance Initiatives Interagency Programs State and Local Programs Task Forces Tribal Programs Data and Analytics Overview Data Governance EEO Data Collections Data and Statistics Data Tools and Products No FEAR Act Data Inside EEOC Careers Office for Civil Rights Doing Business with EEOC AI Governance Privacy Office of Inspector General Employees & Job Applicants Employees & Applicants Overview Coverage Timeliness Prohibited Practices Filing a Charge of Discrimination Filing a Charge How to File After You File a Charge Confidentiality Mediation Remedies Existing Charges Filing a Lawsuit Discrimination by Type Age Disability Equal Pay Genetic Information Harassment National Origin Discrimination Pregnancy Discrimination Race/Color Discrimination Religious Discrimination Retaliation Sex Sexual Harassment Employers / Small Business Employers / Small Business Overview Coverage After a Charge is Filed Resolving a Charge Commissioner Charges Directed Investigations Remedies Small Business Resource Center Small Business Home Small Business Requirements Frequently Asked Questions Tips for Small Businesses Making an Employment Decision? EEOC Resources Small Business Assistance Small Business Fact Sheet Small Business Videos EEOC Glossary Contact Us Discrimination by Type Age Disability Equal Pay Genetic Information Harassment National Origin Pregnancy Race/Color Religion Retaliation Sex Sexual Harassment Prohibited Practices Recordkeeping EEO Data Collections "Know Your Rights" Poster Training Other Employment Issues Federal Sector Federal Agencies Overview Federal EEO Coordination Federal Agency EEO Directors EEOC Legal Resources Management Directives & Federal Sector Guidance Federal Training & Outreach Resources Federal Employees & Job Applicants Overview Federal Complaint Process Federal Sector Alternative Dispute Resolution Prohibited Practices Resources Contact Us Contact EEOC Find Your Nearest Office Office Operating Status Languages English Español (Spanish) Resources in Other Languages عربي (Arabic) 简体中文 (Chinese, Simplified) 繁體中文 - Chinese (Traditional) Kreyòl Ayisyen (Haitian Creole) 한국어 (Korean) Русском (Russian) Português (Portuguese) Tagalog (Tagalog) ไทย (Thai) Tiếng Việt (Vietnamese) فارسی (Persian. Farsi) پښتو (Pashto) Home fact sheet Federal Laws Prohibiting Job Discrimination Questions And Answers Federal Laws Prohibiting Job Discrimination Questions And Answers Federal Equal Employment Opportunity (EEO) Laws I. What Are the Federal Laws Prohibiting Job Discrimination? Title VII of the Civil Rights Act of 1964 (Title VII), which prohibits employment discrimination based on race, color, religion, sex, or national origin; the Equal Pay Act of 1963 (EPA), which protects men and women who perform substantially equal work in the same establishment from sex-based wage discrimination; the Age Discrimination in Employment Act of 1967 (ADEA), which protects individuals who are 40 years of age or older; Title I and Title V of the Americans with Disabilities Act of 1990, as amended (ADA), which prohibit employment discrimination against qualified individuals with disabilities in the private sector, and in state and local governments; Sections 501 and 505 of the Rehabilitation Act of 1973, which prohibit discrimination against qualified individuals with disabilities who work in the federal government; Title II of the Genetic Information Nondiscrimination Act of 2008 (GINA), which prohibits employment discrimination based on genetic information about an applicant, employee, or former employee; and the Civil Rights Act of 1991, which, among other things, provides monetary damages in cases of intentional employment discrimination. The U.S. Equal Employment Opportunity Commission (EEOC) enforces all of these laws. EEOC also provides oversight and coordination of all federal equal employment opportunity regulations, practices, and policies. Other federal laws, not enforced by EEOC, also prohibit discrimination and reprisal against federal employees and applicants. The Civil Service Reform Act of 1978 (CSRA) contains a number of prohibitions, known as prohibited personnel practices, which are designed to promote overall fairness in federal personnel actions. 5 U.S.C. 2302. The CSRA prohibits any employee who has authority to take certain personnel actions from discriminating for or against employees or applicants for employment on the bases of race, color, national origin, religion, sex, age or disability. It also provides that certain personnel actions can not be based on attributes or conduct that do not adversely affect employee performance, such as marital status and political affiliation. The CSRA also prohibits reprisal against federal employees or applicants for whistle-blowing, or for exercising an appeal, complaint, or grievance right. The CSRA is enforced by both the Office of Special Counsel (OSC) and the Merit Systems Protection Board (MSPB). Additional information about the enforcement of the CSRA may be obtained from OSC at (202) 653-7188 or at http://www.osc.gov/; and from MSPB at (202) 653-6772 or at http://www.mspb.gov/ . Discriminatory Practices II. What Discriminatory Practices Are Prohibited by These Laws? Under Title VII, the ADA, GINA, and the ADEA, it is illegal to discriminate in any aspect of employment, including: hiring and firing; compensation, assignment, or classification of employees; transfer, promotion, layoff, or recall; job advertisements; recruitment; testing; use of company facilities; training and apprenticeship programs; fringe benefits; pay, retirement plans, and disability leave; or other terms and conditions of employment. Discriminatory practices under these laws also include: harassment on the basis of race, color, religion, sex, national origin, disability, genetic information, or age; retaliation against an individual for filing a charge of discrimination, participating in an investigation, or opposing discriminatory practices; employment decisions based on stereotypes or assumptions about the abilities, traits, or performance of individuals of a certain sex, race, age, religion, or ethnic group, or individuals with disabilities, or based on myths or assumptions about an individual's genetic information; and denying employment opportunities to a person because of marriage to, or association with, an individual of a particular race, religion, national origin, or an individual with a disability. Title VII also prohibits discrimination because of participation in schools or places of worship associated with a particular racial, ethnic, or religious group. Employers are required to post notices to all employees advising them of their rights under the laws EEOC enforces and their right to be free from retaliation. Such notices must be accessible, as needed, to persons with visual or other disabilities that affect reading. Note: Many states and municipalities also have enacted protections against discrimination and harassment based on sexual orientation, status as a parent, marital status and political affiliation. For information, please contact the EEOC District Office nearest you. III. What Other Practices Are Discriminatory Under These Laws? Title VII Title VII prohibits not only intentional discrimination, but also practices that have the effect of discriminating against individuals because of their race, color, national origin, religion, or sex. National Origin Discrimination It is illegal to discriminate against an individual because of birthplace, ancestry, culture, or linguistic characteristics common to a specific ethnic group. A rule requiring that employees speak only English on the job may violate Title VII unless an employer shows that the requirement is necessary for conducting business. If the employer believes such a rule is necessary, employees must be informed when English is required and the consequences for violating the rule. The Immigration Reform and Control Act (IRCA) of 1986 requires employers to assure that employees hired are legally authorized to work in the U.S. However, an employer who requests employment verification only for individuals of a particular national origin, or individuals who appear to be or sound foreign, may violate both Title VII and IRCA; verification must be obtained from all applicants and employees. Employers who impose citizenship requirements or give preferences to U.S. citizens in hiring or employment opportunities also may violate IRCA. Additional information about IRCA may be obtained from the Office of Special Counsel for Immigration-Related Unfair Employment Practices at 1-800-255-7688 (voice), 1-800-237-2515 (TTY for employees/applicants) or 1-800-362-2735 (TTY for employers) or at http://www.usdoj.gov/crt/osc . Religious Accommodation An employer is required to reasonably accommodate the religious belief of an employee or prospective employee, unless doing so would impose an undue hardship. Sex Discrimination Title VII's broad prohibitions against sex discrimination specifically cover: Sexual Harassment - This includes practices ranging from direct requests for sexual favors to workplace conditions that create a hostile environment for persons of either gender, including same sex harassment. (The "hostile environment" standard also applies to harassment on the bases of race, color, national origin, religion, age, and disability.) Pregnancy Based Discrimination - Pregnancy, childbirth, and related medical conditions must be treated in the same way as other temporary illnesses or conditions. Discrimination because of sexual orientation or transgender status. Additional rights are available to parents and others under the Family and Medical Leave Act (FMLA), which is enforced by the U.S. Department of Labor. For information on the FMLA, or to file an FMLA complaint, individuals should contact the nearest office of the Wage and Hour Division, Employment Standards Administration, U.S. Department of Labor. The Wage and Hour Division is listed in most telephone directories under U.S. Government, Department of Labor or at https://www.dol.gov/agencies/whd . Age Discrimination in Employment Act The ADEA's broad ban against age discrimination also specifically prohibits: statements or specifications in job notices or advertisements of age preference and limitations. An age limit may only be specified in the rare circumstance where age has been proven to be a bona fide occupational qualification (BFOQ); discrimination on the basis of age by apprenticeship programs, including joint labor-management apprenticeship programs; and denial of benefits to older employees. An employer may reduce benefits based on age only if the cost of providing the reduced benefits to older workers is the same as the cost of providing benefits to younger workers. Equal Pay Act The EPA prohibits discrimination on the basis of sex in the payment of wages or benefits, where men and women perform work of similar skill, effort, and responsibility for the same employer under similar working conditions. Note that: Employers may not reduce wages of either sex to equalize pay between men and women. A violation of the EPA may occur where a different wage was/is paid to a person who worked in the same job before or after an employee of the opposite sex. A violation may also occur where a labor union causes the employer to violate the law. Titles I and V of the Americans with Disabilities Act, as amended The ADA prohibits discrimination on the basis of disability in all employment practices. It is necessary to understand several important ADA definitions to know who is protected by the law and what constitutes illegal discrimination: Individual with a Disability An individual with a disability under the ADA is a person who has a physical or mental impairment that substantially limits one or more major life activities, has a record of such impairment, or is regarded as having a disability. An entity subject to the ADA regards someone as having a disability when it takes an action prohibited by the ADA based on an actual or perceived impairment, except if the impairment is both transitory (lasting or expected to last six months or less) and minor. Major life activities are basic activities that most people in the general population can perform with little or no difficulty such as walking, breathing, seeing, hearing, speaking, learning, thinking, and eating. Major life activities also include the operation of a major bodily function, such as functions of the immune system normal cell growth, brain, neurological, and endocrine functions. "Qualified" An individual with a disability is "qualified" if he or she satisfies skill, experience, education, and other job-related requirements of the position held or desired, and who, with or without reasonable accommodation, can perform the essential functions of that position. Reasonable Accommodation Reasonable accommodation may include, but is not limited to, making existing facilities used by employees readily accessible to and usable by persons with disabilities; job restructuring; modification of work schedules; providing additional unpaid leave; reassignment to a vacant position; acquiring or modifying equipment or devices; adjusting or modifying examinations, training materials, or policies; and providing qualified readers or interpreters. Reasonable accommodation may be necessary to apply for a job, to perform job functions, or to enjoy the benefits and privileges of employment that are enjoyed by people without disabilities. An employer is not required to lower production standards to make an accommodation. An employer generally is not obligated to provide personal use items such as eyeglasses or hearing aids. A person who only meets the "regarded as" definition of disability is not entitled to receive a reasonable accommodation. Undue Hardship An employer is required to make a reasonable accommodation to a qualified individual with a disability unless doing so would impose an undue hardship on the operation of the employer's business. Undue hardship means an action that requires significant difficulty or expense when considered in relation to factors such as a business' size, financial resources, and the nature and structure of its operation. Prohibited Inquiries and Examinations Before making an offer of employment, an employer may not ask job applicants about the existence, nature, or severity of a disability. Applicants may be asked about their ability to perform job functions. A job offer may be conditioned on the results of a medical examination, but only if the examination is required for all entering employees in the same job category. Medical examinations of employees must be job-related and consistent with business necessity. Drug and Alcohol Use Employees and applicants currently engaging in the illegal use of drugs are not protected by the ADA when an employer acts on the basis of such use. Tests for illegal use of drugs are not considered medical examinations and, therefore, are not subject to the ADA's restrictions on medical examinations. Employers may hold individuals who are illegally using drugs and individuals with alcoholism to the same standards of performance as other employees. The Civil Rights Act of 1991 The Civil Rights Act of 1991 made major changes in the federal laws against employment discrimination enforced by EEOC. Enacted in part to reverse several Supreme Court decisions that limited the rights of persons protected by these laws, the Act also provides additional protections. The Act authorizes compensatory and punitive damages in cases of intentional discrimination, and provides for obtaining attorneys' fees and the possibility of jury trials. It also directs the EEOC to expand its technical assistance and outreach activities. Title II of the Genetic Information Nondiscrimination Act of 2008 GINA prohibits discrimination against applicants, employees, and former employees on the basis of genetic information. This includes a prohibition on the use of genetic information in all employment decisions; restrictions on the ability of employers and other covered entities to request or to acquire genetic information, with limited exceptions; and a requirement to maintain the confidentiality of any genetic information acquired, with limited exceptions. Employers And Other Entities Covered By EEO Laws IV. Which Employers and Other Entities Are Covered by These Laws? Title VII, the ADA, and GINA cover all private employers, state and local governments, and education institutions that employ 15 or more individuals. These laws also cover private and public employment agencies, labor organizations, and joint labor management committees controlling apprenticeship and training. The ADEA covers all private employers with 20 or more employees, state and local governments (including school districts), employment agencies and labor organizations. The EPA covers all employers who are covered by the Federal Wage and Hour Law (the Fair Labor Standards Act). Virtually all employers are subject to the provisions of this Act. Title VII, the ADEA, GINA, and the EPA also cover the federal government. In addition, the federal government is covered by Sections 501 and 505 of the Rehabilitation Act of 1973, as amended, which incorporate the requirements of the ADA. However, different procedures are used for processing complaints of federal discrimination. For more information on how to file a complaint of federal discrimination, contact the EEO office of the federal agency where the alleged discrimination occurred. The CSRA (not enforced by EEOC) covers most federal agency employees except employees of a government corporation, the Federal Bureau of Investigation, the Central Intelligence Agency, the Defense Intelligence Agency, the National Security Agency, and as determined by the President, any executive agency or unit thereof, the principal function of which is the conduct of foreign intelligence or counterintelligence activities, or the General Accounting Office. The EEOC'S Charge Processing Procedures Federal employees or applicants for employment should see the fact sheet about Federal Sector Equal Employment Opportunity Complaint Processing. V. Who Can File a Charge of Discrimination? Any individual who believes that his or her employment rights have been violated may file a charge of discrimination with EEOC. In addition, an individual, organization, or agency may file a charge on behalf of another person in order to protect the aggrieved person's identity. VI. How Is a Charge of Discrimination Filed? A charge may be filed by mail or in person at the nearest EEOC office. Individuals may consult their local telephone directory (U.S. Government listing) or call 1-800-669-4000 (voice) or 1-800-669-6820 (TTY) to contact the nearest EEOC office for more information on specific procedures for filing a charge. Individuals who need an accommodation in order to file a charge (e.g., sign language interpreter, print materials in an accessible format) should inform the EEOC field office so appropriate arrangements can be made. Federal employees or applicants for employment should see the fact sheet about Federal Sector Equal Employment Opportunity Complaint Processing. VII. What Information Must Be Provided to File a Charge? The complaining party's name, address, and telephone number; The name, address, and telephone number of the respondent employer, employment agency, or union that is alleged to have discriminated, and number of employees (or union members), if known; A short description of the alleged violation (the event that caused the complaining party to believe that his or her rights were violated); and The date(s) of the alleged violation(s). Federal employees or applicants for employment should see the fact sheet about Federal Sector Equal Employment Opportunity Complaint Processing. VIII. What Are the Time Limits for Filing a Charge of Discrimination? All laws enforced by EEOC, except the Equal Pay Act, require filing a charge with EEOC before a private lawsuit may be filed in court. There are strict time limits within which charges must be filed: A charge must be filed with EEOC within 180 days from the date of the alleged violation, in order to protect the charging party's rights. This 180-day filing deadline is extended to 300 days if the charge also is covered by a state or local anti-discrimination law. For ADEA charges, only state laws extend the filing limit to 300 days. These time limits do not apply to claims under the Equal Pay Act, because under that Act persons do not have to first file a charge with EEOC in order to have the right to go to court. However, since many EPA claims also raise Title VII sex discrimination issues, it may be advisable to file charges under both laws within the time limits indicated. To protect legal rights, it is always best to contact EEOC promptly when discrimination is suspected. Federal employees or applicants for employment should see the fact sheet about Federal Sector Equal Employment Opportunity Complaint Processing. IX. What Agency Handles a Charge that is also Covered by State or Local Law? Many states and localities have anti-discrimination laws and agencies responsible for enforcing those laws. EEOC refers to these agencies as "Fair Employment Practices Agencies (FEPAs)." Through the use of "work sharing agreements," EEOC and the FEPAs avoid duplication of effort while at the same time ensuring that a charging party's rights are protected under both federal and state law. If a charge is filed with a FEPA and is also covered by federal law, the FEPA "dual files" the charge with EEOC to protect federal rights. The charge usually will be retained by the FEPA for handling. If a charge is filed with EEOC and also is covered by state or local law, EEOC "dual files" the charge with the state or local FEPA, but ordinarily retains the charge for handling. X. What Happens after a Charge is Filed with EEOC? The employer is notified that the charge has been filed. From this point there are a number of ways a charge may be handled: A charge may be assigned for priority investigation if the initial facts appear to support a violation of law. When the evidence is less strong, the charge may be assigned for follow up investigation to determine whether it is likely that a violation has occurred. EEOC can seek to settle a charge at any stage of the investigation if the charging party and the employer express an interest in doing so. If settlement efforts are not successful, the investigation continues. In investigating a charge, EEOC may make written requests for information, interview people, review documents, and, as needed, visit the facility where the alleged discrimination occurred. When the investigation is complete, EEOC will discuss the evidence with the charging party or employer, as appropriate. The charge may be selected for EEOC's mediation program if both the charging party and the employer express an interest in this option. Mediation is offered as an alternative to a lengthy investigation. Participation in the mediation program is confidential, voluntary, and requires consent from both charging party and employer. If mediation is unsuccessful, the charge is returned for investigation. A charge may be dismissed at any point if, in the agency's best judgment, further investigation will not establish a violation of the law. A charge may be dismissed at the time it is filed, if an initial in-depth interview does not produce evidence to support the claim. When a charge is dismissed, a notice is issued in accordance with the law which gives the charging party 90 days in which to file a lawsuit on his or her own behalf. Federal employees or applicants for employment should see the fact sheet about Federal Sector Equal Employment Opportunity Complaint Processing. XI. How Does EEOC Resolve Discrimination Charges? If the evidence obtained in an investigation does not establish that discrimination occurred, this will be explained to the charging party. A required notice is then issued, closing the case and giving the charging party 90 days in which to file a lawsuit on his or her own behalf. If the evidence establishes that discrimination has occurred, the employer and the charging party will be informed of this in a letter of determination that explains the finding. EEOC will then attempt conciliation with the employer to develop a remedy for the discrimination. If the case is successfully conciliated, or if a case has earlier been successfully mediated or settled, neither EEOC nor the charging party may go to court unless the conciliation, mediation, or settlement agreement is not honored. If EEOC is unable to successfully conciliate the case, the agency will decide whether to bring suit in federal court. If EEOC decides not to sue, it will issue a notice closing the case and giving the charging party 90 days in which to file a lawsuit on his or her own behalf. In Title VII and ADA cases against state or local governments, the Department of Justice takes these actions. Federal employees or applicants for employment should see the fact sheet about Federal Sector Equal Employment Opportunity Complaint Processing. XII. When Can an Individual File an Employment Discrimination Lawsuit in Court? A charging party may file a lawsuit within 90 days after receiving a notice of a "right to sue" from EEOC, as stated above. Under Title VII, the ADA, and GINA, a charging party also can request a notice of "right to sue" from EEOC 180 days after the charge was first filed with the Commission, and may then bring suit within 90 days after receiving this notice. Under the ADEA, a suit may be filed at any time 60 days after filing a charge with EEOC, but not later than 90 days after EEOC gives notice that it has completed action on the charge. Under the EPA, a lawsuit must be filed within two years (three years for willful violations) of the discriminatory act, which in most cases is payment of a discriminatory lower wage. Federal employees or applicants for employment should see the fact sheet about Federal Sector Equal Employment Opportunity Complaint Processing. XIII. What Remedies Are Available When Discrimination Is Found? The "relief" or remedies available for employment discrimination, whether caused by intentional acts or by practices that have a discriminatory effect, may include: back pay, hiring, promotion, reinstatement, front pay, reasonable accommodation, or other actions that will make an individual "whole" (in the condition s/he would have been but for the discrimination). Remedies also may include payment of: attorneys' fees, expert witness fees, and court costs. Under most EEOC-enforced laws, compensatory and punitive damages also may be available where intentional discrimination is found. Damages may be available to compensate for actual monetary losses, for future monetary losses, and for mental anguish and inconvenience. Punitive damages also may be available if an employer acted with malice or reckless indifference. Punitive damages are not available against the federal, state or local governments. In cases concerning reasonable accommodation under the ADA, compensatory or punitive damages may not be awarded to the charging party if an employer can demonstrate that "good faith" efforts were made to provide reasonable accommodation. An employer may be required to post notices to all employees addressing the violations of a specific charge and advising them of their rights under the laws EEOC enforces and their right to be free from retaliation. Such notices must be accessible, as needed, to persons with visual or other disabilities that affect reading. The employer also may be required to take corrective or preventive actions to cure the source of the identified discrimination and minimize the chance of its recurrence, as well as discontinue the specific discriminatory practices involved in the case. The Commission XIV. What Is EEOC and How Does It Operate? EEOC is an independent federal agency originally created by Congress in 1964 to enforce Title VII of the Civil Rights Act of 1964. The Commission is composed of five Commissioners and a General Counsel appointed by the President and confirmed by the Senate. Commissioners are appointed for five-year staggered terms; the General Counsel's term is four years. The President designates a Chair and a Vice-Chair. The Chair is the chief executive officer of the Commission. The Commission has authority to establish equal employment policy and to approve litigation. The General Counsel is responsible for conducting litigation. EEOC carries out its enforcement, education and technical assistance activities through 53 field offices serving every part of the nation. The nearest EEOC field office may be contacted by calling: 1-800-669-4000 (voice) or 1-800-669-6820 (TTY). Information And Assistance Available From EEOC XV. What Information and Other Assistance Is Available from EEOC? EEOC provides a range of informational materials and assistance to individuals and entities with rights and responsibilities under EEOC-enforced laws. Most materials and assistance are provided to the public at no cost. Additional specialized training and technical assistance are provided on a fee basis under the auspices of the EEOC Education, Technical Assistance, and Training Revolving Fund Act of 1992. For information on educational and other assistance available, contact the nearest EEOC office by calling: 1-800-669-4000 (voice) or 1-800-669-6820 (TTY). The EEOC has a number of fact sheets and other publications available free of charge. These may be downloaded from the Publications page. Information about EEOC and the laws it enforces also can be found at the following internet address: http://www.eeoc.gov . This page was last modified on November 21, 2009. Enabled In-page Navigation Return to top U.S. Equal Employment Opportunity Commission EEOC Headquarters 131 M Street, NE Washington, DC 20507 1-800-669-6820 (TTY) 1-844-234-5122 (ASL Video Phone) Questions? Call 1-800-669-4000 For Deaf/Hard of Hearing callers: 1-800-669-6820 (TTY) 1-844-234-5122 (ASL Video Phone) info@eeoc.gov Find your nearest EEOC office Connect With Us FOIA Privacy Policy Disclaimer Accessibility Office of Inspector General USA.gov | 2026-01-13T08:47:52 |
https://discourse.llvm.org/t/rfc-forming-a-working-group-on-formal-specification-for-llvm/89056?u=nikic | RFC: Forming a Working Group on Formal Specification for LLVM - LLVM Project - LLVM Discussion Forums LLVM Discussion Forums RFC: Forming a Working Group on Formal Specification for LLVM LLVM Project alina December 5, 2025, 8:28am 1 Hi LLVM Community, We propose forming a new working group to focus on formal specification for LLVM IR. We have briefly discussed this at an impromptu roundtable ( LLVM Developer's Meeting 2025: Roundtable on formal sematics for LLVM (notes) - Google Docs ) at the US LLVM Developer’s Meeting this year and additionally offline with a group of people interested in this topic. The goal is to bring together experts from multiple programming language communities and academia to dive into more detailed discussions and coordinate efforts from open source contributors and research groups on the topic of LLVM’s formal specification and it’s semantic model. Logistics Meetings: We tentatively plan to have a first kick off meeting next week (exact time and day to follow) and then continue next year, starting mid January 2026, with 1h bi-weekly syncs. We are doing our best to accommodate a wide range of timezones (GMT-8h to GMT+1h) and other scheduling restrictions. Communication: We plan to keep meeting notes that can be read offline by interested parties. As a forum for additional discussions, we’re looking to initially use discourse, email and impromptu syncs where necessary to make progress. We’re looking into also having a Discord channel. Participants We encourage anyone interested to participate in this group. The meetings will be public, as well as the notes doc. Sharing also the group of folks who we’ve discussed with in more depth on the first iteration of this working group. Alina Sbirlea - Google Burak Emir - Google Dmytro Hrybenko - Google Chandler Carruth - Google James Y Knight - Google John McCall - Apple John Regehr - University of Utah Kayvan Memarian - University of Cambridge Nikita Popov - Red Hat Nuno Lopes - University of Lisbon Peter Sewell - University of Cambridge Ralf Jung - ETH Zürich Richard Smith - Google Steve Zdancewic - Pennsylvania State University Tobias Grosser - University of Cambridge Initial write-ups Referencing the following for additional background and to guide the initial discussions: * https://hackmd.io/@nikic/SJBt4mFCll * LLVM IR semantic changes for safety Looking forward to hearing your thoughts on this! 18 Likes LLVM Weekly - #623, December 8th 2025 alina December 6, 2025, 4:39pm 2 Hello, We’re planning a kick off meeting next week, Monday, December 8th at 8:30am PT / 11:30am ET / 4:30pm GMT / 5:30pm GMT+1. For next week, the meet link is: meet.google.com/rqd-yggb-tux . I added this to the LLVM Calendar. We’ll pick it back up in January with the first 2026 meeting on Monday, January 12th at 8:30am PT / 11:30am ET / 4:30pm GMT / 5:30pm GMT+1. This will be a recurring meeting using: meet.google.com/yfe-xbnv-acb . I added this to the LLVM Calendar as well. Thank you, Alina 6 Likes alina January 10, 2026, 1:07am 3 We will have the first meeting of 2026 next Monday, January 12th at 8:30am PT / 11:30am ET / 4:30pm GMT / 5:30pm GMT+1., as previously scheduled. The meeting is shared with the LLVM calendar for easy access ( calendar@llvm.org ). The notes doc has a list of pre-reading material on the byte type which I would like to discuss during this meeting. If you would like to bring up additional discussion topics for either next or subsequent meetings, please add these to the notes. 1 Like Related topics Topic Replies Views Activity RFC: Forming LLVM Working Group on Memory Safety LLVM Project 34 2536 November 25, 2025 LLVM Embedded Toolchains Working Group call this Thursday, Jun 20 Community 0 71 June 17, 2024 LLVM GPU Working Group -- First Meeting -- This Friday 10am CST LLVM Dev List Archives 1 119 January 10, 2022 LLVM European User Group Meeting 2011 - Call For Participation LLVM Dev List Archives 0 87 July 8, 2011 LLVM Project Council Meeting - December 10, 2025 LLVM Project 2 247 January 5, 2026 Home Categories Guidelines Terms of Service Privacy Policy Powered by Discourse , best viewed with JavaScript enabled | 2026-01-13T08:47:52 |
https://humanitec.com/blog/what-is-dynamic-configuration-management | What is Dynamic Configuration Management? | Humanitec 🚀 Build your Minimum Viable Platform (MVP) with our playbook. Start now Product Self-Hosted Products Product Overview Arrow Right Use them all or combine them. Products Platform Orchestrator A graph-based backend for your IDP. Automate and standardize at scale. Portal The frontend of your IDP. Service catalog, scaffolding and self-service. OSS BUILDING BLOCKS Score Code-based interface of your IDP. A familiar interface for developers. Resource Definitions Pre-configured infra modules. Easily integrated with your existing IaC. Reference Architectures Blueprints for enteprise-grade Internal Developer Platforms. Features Environment Management Developer Self-service RBAC and Governance Deployment Management Insights & Engineering Intelligence Cost control Infrastructure Orchestration Cluster & GPU Orchestration Ephemeral Environments Use Cases Use CASES Build Internal Developer Platforms (IDPs) Feed your developer portal with a single platform backend Catch and fix infra drift Detect drift early and realign environments with one redeploy Rollback application and infrastructure Restore any environment to a known-good state in seconds Reduce risk with progressive infra rollouts Gradually apply updates across environments with full control and instant rollback. Enable developer self-service Kill waiting times. Self-serve the tech you need to run your apps Eliminate ticket ops No more ticket ops and repetitive tasks, slash lead time Understand the blast radius Instantly see which workloads and environments are impacted by infra issues Build an MVP in days Arrow Right A structured approach to get you to your
minimum viable platform in four phases. Users Application Developers True self-service. No waiting times Infrastructure and Operations Configure once. Enforce everywhere Security Build the DevSecOps platform for you Executives Build a leading organization. Cut time to market. Platform Engineers Infrastructure Platform engineers Build a backend for everyone DevEx Platform Engineers Craft amazing DevEx flows Pricing Learn 5 minutes IDP Arrow Right Build a fully functional test platform on your local machine in five minutes Resources Blog Check out our latest articles and product releases Videos Check our video library and learn how to build a platform ROI Calculator What is the ROI of building a platform with Humanitec? Whitepapers Industry reports and benchmarking studies Security Learn about Humanitec's enterprise-grade security standards Community Events Sign up for our weekly events or check out past recordings Partners Check out our ecosystem of implementation partners Reference architecture What is Platform Engineering? Learn everything about Platform Engineering, the next evolution of DevOps What is an Internal Developer Platform? All you need to know about Internal Developer Platforms Reference Architectures Blueprints for enteprise-grade Internal Developer Platforms. Docs Login Book a demo Customers Pricing Learn 5 minutes IDP Arrow Right Build a fully functional test platform on your local machine in five minutes Resources Blog Check out our latest articles and product releases Videos Check our video library and learn how to build a platform ROI Calculator What is the ROI of building a platform with Humanitec? Whitepapers Industry reports and benchmarking studies Security Learn about Humanitec's enterprise-grade security standards Community Events Sign up for our weekly events or check out past recordings Partners Check out our ecosystem of implementation partners Reference architecture What is Platform Engineering? Learn everything about Platform Engineering, the next evolution of DevOps What is an Internal Developer Platform? All you need to know about Internal Developer Platforms Reference Architectures Blueprints for enteprise-grade Internal Developer Platforms. Docs Login Try the sandbox All blogs What is Dynamic Configuration Management? What is Dynamic Configuration Management? Chris Stephenson February 7, 2023 Dynamic Configuration Management (DCM) is a methodology used to structure the configuration of compute workloads. Developers create workload specifications, describing everything their workloads need to run successfully. The specification is then used to dynamically create the configuration, to deploy the workload in a specific environment. With DCM, developers do not need to define or maintain any environment-specific configuration for their workloads. ⚠️ This post covers Platform Orchestrator v1. v2 is now available with simplified architecture and support for any compute target. See differences between the two products here Table of contents Example H2 Example H3 Example H4 Example H5 Example H6 Dynamic Configuration Management (DCM) is a methodology used to structure the configuration of compute workloads. Developers create workload specifications, describing everything their workloads need to run successfully. The specification is then used to dynamically create the configuration, to deploy the workload in a specific environment. With DCM, developers do not need to define or maintain any environment-specific configuration for their workloads. For developers , DCM enables workload-centric development, meaning that workloads can be deployed with their resources and configuration to all environments, using a single workload specification. For platform engineers , DCM helps define how and where to provision resources and workloads; this helps improve consistency and compliance in an organization. It also makes delivering a self-service Internal Developer Platform (IDP) much more accessible. The alternative to DCM is a static, infrastructure-centric approach where a developer must maintain separate configuration files per environment and manage infrastructure autonomously, or outsource to other teams (TicketOps). Advantages of Dynamic Configuration Management Standardization of configuration DCM enables workload-centric development, at the center of which sits the workload specification. A workload specification is a structured file that describes everything a workload needs to run successfully without environment-specific configuration. Platform teams can use it to define how to deploy workloads from standard base configurations, which helps eliminate configuration drift. Configuration drift happens when teams create new workloads by copying the structure of the configuration from an existing workload, and then customizing it to fit their needs. Over time, these customizations compound, resulting in subtle configuration differences between workloads. This then makes it challenging to perform bulk updates across workloads. The environment-agnostic nature of workload specifications helps eliminate configuration drift and mitigate cognitive load. A platform team defines how to provision the environment-specific resources and configuration for the workload, and developer teams declare everything they need in a single workload specification that applies to all environments. Separation of concerns DCM enforces a strict separation between environment-specific and environment-agnostic configuration. Depending on the engineering organization, the same or different people may be responsible for managing shared resources such as databases, provisioning infrastructure, and running workloads. DCM does not have an opinion on how to organize the engineering team, but it does provide the structure for teams to work better together. In regulated industries, it's vital to tightly control data access. This typically requires setting up a centralized data or database administrator (DBA) team. In a static approach, there would need to be some interaction between the developer and the DBA team if a workload needs a database. The developer would then have to take custody of the connection string—which would likely contain secret information in the form of credentials. This interaction is needed because otherwise, there is no way for the DBA team to know that a developer would need a new database. In the DCM world, the workload specification declares the need for a database as a dependency. Automated tooling can notify the DBA team when a new database is needed. In more sophisticated cases, the whole process can be automated—provisioning databases at deployment time, as and when required by workloads. Databases are also "environment-specific," and the DBA team can fully own them. The developer can configure the connection string in the workload with a placeholder. This way, the developer doesn't need to worry about taking custody of the connection string, and the DBA team can optimize their provisioning processes. Better developer experience Implementing a DCM approach reduces developer cognitive load. When paired with a dynamic Internal Developer Platform (IDP) , developers only need to maintain the workload specification, since the IDP ensures that the correct resources are provisioned and wired to the workload. DCM also improves promotion between environments. When promoting a workload with configuration changes, an engineer must figure out changes vs. configuration. This predicament occurs because most static configurations require individual configurations per environment. At best, this is a slow process requiring in-depth knowledge of how the workload is configured. At worst, it can introduce hard-to-debug errors involving environment cross-linking. DCM solves this issue with a strict separation between environment-specific and environment-agnostic configuration. New possibilities of working DCM provides most value in situations where tooling is used to manage the dynamic configuration that is generated. This opens up new possibilities such as: Provisioning (and cleaning up) infrastructure based on what a workload actually needs Setting up ephemeral environments, for example on every PR Centralized change of resources that are shared by workloads managed by different teams Summary DCM is firmly rooted in the platform engineering movement. The methodology has been adopted across industries from Silicon Valley tech giants to financial institutions in New York, to international retailers. Teams from startups to Fortune 100 companies are adopting the methodology and feeding that experience back into the community. This in turn is helping drive awareness, and enabling other organizations to make more informed decisions when considering DCM, and the business value it can bring. Chris Stephenson CTO at Humanitec LinkedIn Chris is fascinated by the tackling of tough questions in cloud-native development. He headed the high-performance computing group at Lloyds of London, played several integral roles in building a number of tech-setups at startups, and acted as a product manager at Google working on an internal developer platform used across the company. At Humanitec Chris is responsible for all things technical. He holds a degree in Information and Computer Engineering from the University of Cambridge and also studied at the Massachusetts Institute of Technology. Upcoming events No items found. See all events Recommended articles No items found. Join our Newsletter By submitting this form you agree to our privacy policy . Thank you! Your submission has been received! Oops! Something went wrong while submitting the form. WHY Why Platform Engineering Why Internal Developer Platform Why Humanitec PRODUCT Product overview Platform Orchestrator Score Portal Integrations Pricing Features Environment management Deployment management Infrastructure orchestration Developer self-service RBAC & governance Use Cases Use cases overview Eliminate ticket Ops End-to-end self service Build developer portals Company About Humanitec Careers Hiring Customers Professional Services Partners Contact Resources Docs Blog Whitepapers FAQ Start free trial Community Slack Events Reference ARCHITECTURES AWS Azure GCP Red Hat OpenShift ©2025 Humanitec. All Rights Reserved. Imprint Support Security Status Policies Technical Definitions Whistleblowing | 2026-01-13T08:47:52 |
https://crypto.forem.com/terms | Web Site Terms and Conditions of Use - Crypto Forem Forem Feed Follow new Subforems to improve your feed DEV Community Follow A space to discuss and keep up software development and manage your software career Future Follow News and discussion of science and technology such as AI, VR, cryptocurrency, quantum computing, and more. Open Forem Follow A general discussion space for the Forem community. If it doesn't have a home elsewhere, it belongs here Gamers Forem Follow An inclusive community for gaming enthusiasts Music Forem Follow From composing and gigging to gear, hot music takes, and everything in between. Vibe Coding Forem Follow Discussing AI software development, and showing off what we're building. Popcorn Movies and TV Follow Movie and TV enthusiasm, criticism and everything in-between. DUMB DEV Community Follow Memes and software development shitposting Design Community Follow Web design, graphic design and everything in-between Security Forem Follow Your central hub for all things security. From ethical hacking and CTFs to GRC and career development, for beginners and pros alike Golf Forem Follow A community of golfers and golfing enthusiasts Crypto Forem Follow A collaborative community for all things Crypto—from Bitcoin to protocol development and DeFi to NFTs and market analysis. Parenting Follow A place for parents to the share the joys, challenges, and wisdom that come from raising kids. We're here for them and for each other. Forem Core Follow Discussing the core forem open source software project — features, bugs, performance, self-hosting. Maker Forem Follow A community for makers, hobbyists, and professionals to discuss Arduino, Raspberry Pi, 3D printing, and much more. HMPL.js Forem Follow For developers using HMPL.js to build fast, lightweight web apps. A space to share projects, ask questions, and discuss server-driven templating Dropdown menu Dropdown menu Skip to content Navigation menu Search Powered by Algolia Search Log in Create account Crypto Forem Close Web Site Terms and Conditions of Use 1. Terms By accessing this web site, you are agreeing to be bound by these web site Terms and Conditions of Use, our Privacy Policy , all applicable laws and regulations, and agree that you are responsible for compliance with any applicable local laws. If you do not agree with any of these terms, you are prohibited from using or accessing this site. The materials contained in this web site are protected by applicable copyright and trade mark law. 2. Use License Permission is granted to temporarily download one copy of the materials (information or software) on DEV Community's web site for personal, non-commercial transitory viewing only. This is the grant of a license, not a transfer of title, and under this license you may not: modify or copy the materials; use the materials for any commercial purpose, or for any public display (commercial or non-commercial); attempt to decompile or reverse engineer any software contained on DEV Community's web site; remove any copyright or other proprietary notations from the materials; or transfer the materials to another person or "mirror" the materials on any other server. This license shall automatically terminate if you violate any of these restrictions and may be terminated by DEV Community at any time. Upon terminating your viewing of these materials or upon the termination of this license, you must destroy any downloaded materials in your possession whether in electronic or printed format. 3. Disclaimer The materials on DEV Community's web site are provided "as is". DEV Community makes no warranties, expressed or implied, and hereby disclaims and negates all other warranties, including without limitation, implied warranties or conditions of merchantability, fitness for a particular purpose, or non-infringement of intellectual property or other violation of rights. Further, DEV Community does not warrant or make any representations concerning the accuracy, likely results, or reliability of the use of the materials on its Internet web site or otherwise relating to such materials or on any sites linked to this site. 4. Limitations In no event shall DEV Community or its suppliers be liable for any damages (including, without limitation, damages for loss of data or profit, or due to business interruption,) arising out of the use or inability to use the materials on DEV Community's Internet site, even if DEV Community or an authorized representative has been notified orally or in writing of the possibility of such damage. Because some jurisdictions do not allow limitations on implied warranties, or limitations of liability for consequential or incidental damages, these limitations may not apply to you. 5. Revisions and Errata The materials appearing on DEV Community's web site could include technical, typographical, or photographic errors. DEV Community does not warrant that any of the materials on its web site are accurate, complete, or current. DEV Community may make changes to the materials contained on its web site at any time without notice. DEV Community does not, however, make any commitment to update the materials. 6. Links DEV Community has not reviewed all of the sites linked to its Internet web site and is not responsible for the contents of any such linked site. The inclusion of any link does not imply endorsement by DEV Community of the site. Use of any such linked web site is at the user's own risk. 7. Copyright / Takedown Users agree and certify that they have rights to share all content that they post on DEV Community — including, but not limited to, information posted in articles, discussions, and comments. This rule applies to prose, code snippets, collections of links, etc. Regardless of citation, users may not post copy and pasted content that does not belong to them. DEV Community does not tolerate plagiarism of any kind, including mosaic or patchwork plagiarism. Users assume all risk for the content they post, including someone else's reliance on its accuracy, claims relating to intellectual property, or other legal rights. If you believe that a user has plagiarized content, misrepresented their identity, misappropriated work, or otherwise run afoul of DMCA regulations, please email support@dev.to. DEV Community may remove any content users post for any reason. 8. Site Terms of Use Modifications DEV Community may revise these terms of use for its web site at any time without notice. By using this web site you are agreeing to be bound by the then current version of these Terms and Conditions of Use. 9. DEV Community Trademarks and Logos Policy All uses of the DEV Community logo, DEV Community badges, brand slogans, iconography, and the like, may only be used with express permission from DEV Community. DEV Community reserves all rights, even if certain assets are included in DEV Community open source projects. Please contact support@dev.to with any questions or to request permission. 10. Reserved Names DEV Community has the right to maintain a list of reserved names which will not be made publicly available. These reserved names may be set aside for purposes of proactive trademark protection, avoiding user confusion, security measures, or any other reason (or no reason). Additionally, DEV Community reserves the right to change any already-claimed name at its sole discretion. In such cases, DEV Community will make reasonable effort to find a suitable alternative and assist with any transition-related concerns. 11. Content Policy The following policy applies to comments, articles, and all other works shared on the DEV Community platform: Users must make a good-faith effort to share content that is on-topic, of high-quality, and is not designed primarily for the purposes of promotion or creating backlinks. Posts must contain substantial content — they may not merely reference an external link that contains the full post. If a post contains affiliate links, that fact must be clearly disclosed. For instance, with language such as: “This post includes affiliate links; I may receive compensation if you purchase products or services from the different links provided in this article.” DEV Community reserves the right to remove any content that it deems to be in violation of this policy at its sole discretion. Additionally, DEV Community reserves the right to restrict any user’s ability to participate on the platform at its sole discretion. 12. Fees, Payment, Renewal Fees for Paid Services .Fees for Paid Services. Some of our Services may be offered for a fee (collectively, “Paid Services”). This section applies to any purchases of Paid Services. By using a Paid Service, you agree to pay the specified fees. Depending on the Paid Service, there may be different kinds of fees, for instance some that are one-time, recurring, and/or based on an advertising campaign budget that you set. For recurring fees (AKA Subscriptions), your subscription begins on your purchase date, and we’ll bill or charge you in the automatically-renewing interval (such as monthly, annually) you select, on a pre-pay basis until you cancel, which you can do at any time by contacting plusplus@dev.to . Payment. You must provide accurate and up-to-date payment information. By providing your payment information, you authorize us to store it until you request deletion. If your payment fails, we suspect fraud, or Paid Services are otherwise not paid for or paid for on time (for example, if you contact your bank or credit card company to decline or reverse the charge of fees for Paid Services), we may immediately cancel or revoke your access to Paid Services without notice to you. You authorize us to charge any updated payment information provided by your bank or payment service provider (e.g., new expiration date) or other payment methods provided if we can’t charge your primary payment method. Automatic Renewal. By enrolling in a subscription, you authorize us to automatically charge the then-applicable fees for each subsequent subscription period until the subscription is canceled. If you received a discount, used a coupon code, or subscribed during a free trial or promotion, your subscription will automatically renew for the full price of the subscription at the end of the discount period. This means that unless you cancel a subscription, it’ll automatically renew and we’ll charge your payment method(s). The date for the automatic renewal is based on the date of the original purchase and cannot be changed. You can view your renewal date(s), cancel, or manage subscriptions by contacting plusplus@dev.to . Fees and Changes. We may change our fees at any time in accordance with these Terms and requirements under applicable law. This means that we may change our fees going forward or remove or update features or functionality that were previously included in the fees. If you don’t agree with the changes, you must cancel your Paid Service. Refunds. There are no refunds and all payments are final. European Users: You have the right to withdraw from the transaction within fourteen (14) days from the date of the purchase without giving any reason as long as your purchase was not of downloadable content or of a customized nature, and (i) the service has not been fully performed, or (ii) subject to other limitations as permitted by law. If you cancel this contract, we will reimburse you all payments we have received from you, without undue delay and no later than within fourteen days from the day on which we received the notification of your cancellation of this contract. For this repayment, we will use the same means of payment that you used for the original transaction, unless expressly agreed otherwise with you; you will not be charged for this repayment. You may exercise your right to withdrawal by sending a clear, email request to plusplus@dev.to with the following information: List of services you wish to withdraw from List the date that you purchased the goods or services. If this is a recurring subscription, please list the most recent renewal date List your full legal name and the email associated with your account List the address in which you legally reside Today's Date 13. Governing Law Any claim relating to DEV Community's web site shall be governed by the laws of the State of New York without regard to its conflict of law provisions. General Terms and Conditions applicable to Use of a Web Site. 💎 DEV Diamond Sponsors Thank you to our Diamond Sponsors for supporting the DEV Community Google AI is the official AI Model and Platform Partner of DEV Neon is the official database partner of DEV Algolia is the official search partner of DEV Crypto Forem — A collaborative community for all things Crypto—from Bitcoin to protocol development and DeFi to NFTs and market analysis. Home About Contact Code of Conduct Privacy Policy Terms of Use Built on Forem — the open source software that powers DEV and other inclusive communities. Made with love and Ruby on Rails . Crypto Forem © 2016 - 2026. Uniting blockchain builders and thinkers. Log in Create account | 2026-01-13T08:47:52 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.