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://popcorn.forem.com/wajihaseo | wajihaseo - Popcorn Movies and TV 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 Popcorn Movies and TV Close Follow User actions wajihaseo i am a student of internet marketing Joined Joined on Dec 28, 2025 More info about @wajihaseo 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 1 post published Comment 0 comments written Tag 0 tags followed Shoujo: A Celebration of Emotion, Growth, and Storytelling in Japanese Manga and Anime wajihaseo wajihaseo wajihaseo Follow Dec 28 '25 Shoujo: A Celebration of Emotion, Growth, and Storytelling in Japanese Manga and Anime # genrestudies # filmhistory # animation # analysis Comments Add Comment 4 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 Popcorn Movies and TV — Movie and TV enthusiasm, criticism and everything in-between. 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 . Popcorn Movies and TV © 2016 - 2026. Let's watch something great! Log in Create account | 2026-01-13T08:49:33 |
https://www.fine.dev/blog/o1-vs-sonnet-es#october-claude-update | OpenAI o1 vs. Claude Sonnet 3.5: ¿Cuál modelo de IA es mejor para programar? Home Docs Changelog Pricing Sign in Get started -> Menu Home Docs Changelog Pricing <- Go Back OpenAI o1 vs. Claude Sonnet 3.5: ¿Cuál modelo de IA es mejor para programar? Introducción A medida que la IA continúa evolucionando, dos modelos destacan: o1 de OpenAI y Claude Sonnet 3.5 de Anthropic. Ambos ofrecen capacidades impresionantes para los desarrolladores de software, pero sus fortalezas varían, especialmente cuando se trata de programación. Este blog compara estos dos modelos de IA, centrándose en tareas de programación y rendimiento general. Fine incluye acceso ilimitado a ambos modelos, lo que lo convierte en una excelente manera de probar y comparar cómo o1 y Sonnet se desempeñan con tareas de programación. Diferencias Principales o1 está diseñado para razonamiento complejo y resolución de problemas . Sus respuestas son profundas y reflexivas, lo que lo hace ideal para desarrolladores que trabajan en problemas intrincados o que necesitan explicaciones detalladas. Por otro lado, Claude Sonnet 3.5 se centra en eficiencia y velocidad , destacando en tiempos de respuesta rápidos mientras es más rentable. Si buscas generar código rápidamente o manejar tareas de alto volumen, Claude Sonnet 3.5 puede ser la mejor opción. Ambos modelos utilizan arquitecturas basadas en transformadores, pero o1 es más adecuado para desarrolladores que buscan razonamiento detallado, mientras que Claude Sonnet 3.5 es la opción preferida para aquellos que priorizan la velocidad. Ventana de Contexto y Rendimiento La ventana de contexto juega un papel crucial en cómo estos modelos manejan entradas grandes o conversaciones extendidas. ChatGPT o1 admite 128,000 tokens, mientras que Claude Sonnet 3.5 maneja un mayor 200,000 tokens , dándole una ventaja para tareas que requieren una retención significativa de contexto, como revisar grandes bases de código. Ambos modelos ofrecen un rendimiento sólido en una variedad de tareas, pero sus habilidades brillan en diferentes áreas. ChatGPT o1 sobresale en razonamiento multietapa , explicando la lógica de código compleja en detalle, mientras que Claude Sonnet 3.5 se centra en correcciones de errores rápidas y generación eficiente de código . Versión Mejorada de Claude 3.5 Sonnet - Octubre 2024 - ¿Es Claude ahora mejor que GPT para programar? En octubre de 2024, Anthropic anunció una versión mejorada de Claude 3.5 Sonnet. Las recientes actualizaciones a Claude 3.5 Sonnet han mejorado significativamente sus capacidades de ingeniería de software. Notablemente, el rendimiento del modelo en el benchmark SWE-bench Verified ha mejorado del 33.4% al 49.0%, superando a todos los modelos disponibles públicamente, incluido el o1-preview de OpenAI. Este avance refleja la mayor precisión de Claude 3.5 Sonnet en la generación de funciones y verificación de errores, particularmente en la depuración y refactorización de código que involucra funciones anidadas o segmentos interdependientes. Además, la capacidad de tokens ampliada del modelo le permite retener y utilizar un contexto más extenso, lo que lo hace ideal para revisar grandes bases de código o gestionar proyectos intrincados con múltiples dependencias. Las pruebas iniciales indican que Claude 3.5 Sonnet sobresale en tareas de programación especializadas, como identificar vulnerabilidades de seguridad en aplicaciones web y optimizar algoritmos para velocidad y eficiencia. GitLab, por ejemplo, informó hasta un 10% de mejora en las capacidades de razonamiento para tareas de DevSecOps con el modelo actualizado, sin ningún aumento en la latencia. Casos de uso de IA para programación con o1 y Claude Sonnet 3.5 ChatGPT o1: Depuración de gestión de estado compleja en React: Usa o1 para analizar profundamente por qué ciertos estados no se actualizan correctamente o entran en conflicto entre componentes. Refactorización de código heredado: Emplea el razonamiento exhaustivo de o1 para reestructurar un script antiguo de Python para mejorar su legibilidad y mantenibilidad. Creación de algoritmos: Ideal para escribir y explicar algoritmos como ordenamiento, recorrido de árboles o programación dinámica en detalle. Claude Sonnet 3.5: Generación de código boilerplate: Crea rápidamente archivos de configuración para nuevos proyectos como APIs de Flask o estructura de front-end en Next.js. Autocompletar funciones: Úsalo para completar una función de JavaScript a medio escribir con manejo de errores adecuado y casos extremos. Generación masiva de código: Sonnet 3.5 sobresale en producir estructuras de código repetitivas pero ligeramente variadas como endpoints de API similares o casos de prueba unitarios. ¿Qué modelos de IA utilizan las diferentes herramientas de programación con IA? Hoy en día hay muchas herramientas de desarrollo disponibles para ayudarte con tu programación con IA, desde asistentes avanzados de programación con IA como Fine hasta generadores de código como GitHub Copilot. Algunas usan múltiples LLMs, algunas te dan la opción y otras se basan en un solo modelo. ¿Qué modelo de IA (LLM) utiliza Fine? Fine es una de las pocas herramientas de programación con IA que ofrece a los usuarios la opción entre diferentes LLMs para diversas tareas. Al usar Fine a través del navegador web, los usuarios pueden elegir entre o1-preview, 4o y Claude 3.5 Sonnet. Sin embargo, necesitarás una suscripción pro para aprovechar esto, que cuesta $13-15 por mes. Si eres un usuario gratuito, podrás usar Fine con 4o. Haz clic aquí para probarlo. ¿Qué modelo de IA (LLM) utiliza GitHub Copilot? GitHub Copilot está fuertemente integrado con OpenAI. GitHub es propiedad de Microsoft, que tiene una profunda asociación con OpenAI. La mayoría de los usuarios tienen acceso a 4o, mientras que los suscriptores de Azure AI pueden usar GitHub Copilot con o1-mini y o1-preview. ACTUALIZACIÓN: En GitHub Universe 2024, se anunció que esta asociación exclusiva ya no era tan exclusiva y que la opción de usar Claude se implementaría para todos los usuarios de GitHub Copilot en breve. Algunos usuarios ya han podido acceder a Claude. Está disponible en el Copilot Chat en Visual Studio Code y en Immersive Copilot en el navegador web solamente. ¿Qué modelo de IA (LLM) utiliza Cursor? Cursor utiliza Claude 3.5 Sonnet por defecto y recurre a OpenAI 4o durante interrupciones de Anthropic. ¿Qué modelo de IA (LLM) utiliza Bolt? Bolt, la herramienta de programación con IA que se especializa exclusivamente en front-end, se basa en Claude 3.5 Sonnet. ¿Qué modelo de IA (LLM) utiliza Replit? Aunque Replit lanzó previamente su propio modelo de IA en 2023, cuando anunciaron Replit Agent, su principal herramienta de programación con IA, en 2024, parece que tomaron la decisión de usar Claude 3.5 Sonnet. ¿Cómo comparar diferentes herramientas de programación con IA y LLMs? Si estás buscando comparar cuáles son las mejores herramientas de programación con IA o LLMs, hay algunas cosas a tener en cuenta. Primero, es importante evaluar el LLM y la herramienta por separado. Usa una herramienta como Fine que te permita dar la misma tarea a múltiples LLMs para comparar cuál te da el mejor resultado. Aquí hay una comparación que hicimos de los tres modelos ofrecidos por Fine, planteados con la misma pregunta: ¿Qué hace este repositorio? (Es una pregunta que algunos están llamando el Hola Mundo de la programación con IA). Segundo, compara cómo las herramientas se desempeñan con tu LLM elegido, específico para tu caso de uso. Fine ofrece una variedad de integraciones para aumentar tu productividad, como la capacidad de hacer revisiones dentro de GitHub PR, que están ahorrando horas a los desarrolladores cada semana. ¿Cuál modelo es mejor para programar? Para tareas de programación, tu elección depende de tus necesidades: ChatGPT o1 es la mejor opción cuando trabajas en problemas complejos y multietapa donde necesitas un razonamiento profundo y explicaciones detalladas. Por ejemplo, sobresale en explicar código intrincado o ayudar con la depuración de una manera más reflexiva. Claude Sonnet 3.5 es el modelo preferido para generación de código rápida y eficiente y prototipado iterativo. Es rentable para tareas de alto volumen como generar múltiples fragmentos de código o automatizar correcciones de errores. Ambos modelos apoyan a los desarrolladores en la programación, pero Claude Sonnet 3.5 puede ahorrar tiempo y dinero para tareas de programación cotidianas, mientras que ChatGPT o1 podría ser tu aliado para problemas de programación más difíciles y detallados. Conclusión Al decidir entre ChatGPT o1 y Claude Sonnet 3.5 , considera la complejidad de tus tareas de programación y las restricciones de presupuesto. ChatGPT o1 ofrece una mejor resolución de problemas para tareas intrincadas, mientras que Claude Sonnet 3.5 proporciona una generación de código más rápida y asequible para las necesidades de desarrollo diarias. Ambos modelos son herramientas de IA poderosas que pueden mejorar significativamente tu productividad como desarrollador de software. Regístrate en una plataforma como Fine , que incluye acceso ilimitado a ambos, para lo mejor de ambos mundos sin pagar de más. ¿Por qué suscribirse a Fine? Fine es una plataforma que ofrece acceso ilimitado tanto a o1 como a Claude Sonnet 3.5 , permitiendo a los desarrolladores cambiar entre estos poderosos LLMs según las necesidades de su tarea. Esta flexibilidad es perfecta para aquellos que requieren explicaciones detalladas de ChatGPT o generación de código rápida y eficiente de Claude. Con Fine, no hay necesidad de gestionar tus propias claves API o preocuparte por los límites de uso: todo está incluido. Suscribirse a Fine simplifica el proceso, ofreciendo acceso ilimitado y rentable a ambos modelos para todas tus tareas de programación y desarrollo. Fuentes McNulty, Niall. "ChatGPT o1 vs Claude Sonnet 3.5." Medium , hace 5 días. Enlace . "GPT o1 vs Claude 3.5 Sonnet: ¿Cuál modelo es mejor para programar?" Bind AI Blog , 17 Sep 2024. Enlace . "Comparar o1 Preview vs. Claude 3.5 Sonnet." Context.ai . Enlace . Harisec. "o1 vs Claude." GitHub . Enlace . Tabla de Contenidos Introducción Diferencias Principales Ventana de Contexto y Rendimiento Versión Mejorada de Claude 3.5 Sonnet - Octubre 2024 - ¿Es Claude ahora mejor que GPT para programar? Casos de uso de IA para programación con o1 y Claude 3.5 Sonnet ¿Qué modelos de IA utilizan las diferentes herramientas de programación con IA? Fine GitHub Copilot Cursor Bolt Replit ¿Cómo comparar diferentes herramientas de programación con IA y LLMs? ¿Cuál modelo es mejor para programar? Conclusión ¿Por qué suscribirse a Fine? Start building today Try out the smoothest way to build, launch and manage an app Try for Free -> © Fine.dev - All rights reserved. Product Overview AI Workflows Pricing & Plans Changelog Blog Docs Company Press Terms & Conditions Privacy policy | 2026-01-13T08:49:33 |
https://popcorn.forem.com/popcorn_movies/ringer-movies-the-robert-redford-hall-of-fame-4k88 | Ringer Movies: The Robert Redford Hall of Fame - Popcorn Movies and TV 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 Popcorn Movies and TV Close Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Movie News Posted on Nov 28, 2025 Ringer Movies: The Robert Redford Hall of Fame # movies # streaming # recommendations The Robert Redford Hall of Fame Sean Fennessey and Amanda Dobbins invite actor-playwright Tracy Letts to celebrate Robert Redford’s illustrious career. Together they riff on his standout roles, share personal anecdotes about the star’s impact, and literally build their own Redford Hall of Fame. From Sundance Kid stardom to directorial triumphs like Ordinary People, this lively chat maps Redford’s biggest milestones and enduring appeal. If you’re streaming on Prime or just love classic Hollywood legends, it’s a fun, affectionate deep dive into one of cinema’s all-time greats. Watch on YouTube Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Movie News Follow Joined Jun 22, 2025 More from Movie News Ringer Movies: The 2026 Golden Globes: ‘One Battle After Another’ vs. ‘Hamnet’ Begins # movies # reviews # analysis # streaming CinemaSins: Everything Wrong With Austin Powers in Goldmember in 19 Minutes Or Less # movies # reviews # analysis # marketing Ringer Movies: Five Burning Questions About Awards Season & Our Golden Globes Predictions # movies # analysis # reviews # recommendations 💎 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 Popcorn Movies and TV — Movie and TV enthusiasm, criticism and everything in-between. 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 . Popcorn Movies and TV © 2016 - 2026. Let's watch something great! Log in Create account | 2026-01-13T08:49:33 |
https://popcorn.forem.com/popcorn_tv/ramy-youssef-exits-will-ferrells-netflix-golf-comedy-over-creative-differences-molly-shannon-5ak8#comments | Ramy Youssef Exits Will Ferrell's Netflix Golf Comedy Over Creative Differences; Molly Shannon Joins Cast - Popcorn Movies and TV 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 Popcorn Movies and TV Close Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse TV News Posted on Aug 12, 2025 Ramy Youssef Exits Will Ferrell's Netflix Golf Comedy Over Creative Differences; Molly Shannon Joins Cast # marketing # offtopic # filmindustry # studios Ramy Youssef Exits Will Ferrell Netflix Comedy; Molly Shannon JoinsRamy Youssef Exits Will Ferrell Netflix Comedy; Molly Shannon Joins Ramy Youssef and Josh Rabinowitz exited Will Ferrell's upcoming Netflix comedy over creative differences. Separately, Molly Shannon has been cast. variety.com Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse TV News Follow Joined Jun 22, 2025 More from TV News Gina Carano, Disney Settle Legal Dispute Over ‘Mandalorian' Firing # filmindustry # marketing # agencies # offtopic ‘South Park' Doubles Down on Kristi Noem With Paramount+ End Credits Scene Featuring Her on Shooting Spree at a Pet Store # marketing # analysis # filmindustry # offtopic Stephen Colbert To Guest Star As a Late-Night Host In An Upcoming Episode of ‘Elsbeth' # accessibilitymedia # marketing # filmindustry # distribution 💎 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 Popcorn Movies and TV — Movie and TV enthusiasm, criticism and everything in-between. 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 . Popcorn Movies and TV © 2016 - 2026. Let's watch something great! Log in Create account | 2026-01-13T08:49:33 |
https://opensource.org/board-member/josh-berkus | Josh Berkus – Open Source Initiative Skip to content Get involved About Licenses Open Source Definition Open Source AI Programs Blog Get involved About Licenses Open Source Definition Open Source AI Programs Blog Open Main Menu Josh Berkus Josh Berkus he/him Chair of the License Committee Board Member Candidacy Period: April 1, 2022 – March 31, 2026 Type of Seat: Individual Josh Berkus has been involved with open source for 25 years, including participating in Linux, PostgreSQL, Perl, OpenOffice, Django, MySQL, CouchDB, Docker, Kubernetes, and multiple other communities. He is currently an Individual Board Member of the OSI, and has been on the board for one term. He chairs the License Consistency Working Group. He has also been a contributing member of License Review since 2003, regularly contributing a developer perspective to reviews of submitted licenses. Josh works for the Red Hat Open Source Program Office, where he supports and administers multiple open source projects and interfaces with many OSS-supporting companies and foundations, including guiding teams and partners in launching open source efforts. Additionally, Josh has accumulated a significant amount of nonprofit experience. He has been a fundraiser for the San Francisco Opera, during which time he was a member of Development Executives Rountable and other professional fundraising organizations. He is the co-chair of the Contributor Strategy TAG in the Cloud Native Computing foundation, and has a history of collaboration with the Linux Foundation and the Open Infra Foundation. Josh is also a former board member and treasurer of Software In The Public Interest, where he helped with the final transfer of ownership of the Opensource.org domain to the OSI. Josh sits on the program committee for several software conferences, is a well-known public speaker at many tech events, and wants to know “why is it always database companies messing with licenses?” How will you contribute to the board: I plan to complete my work on the License Consistency Working Group, and significantly rationalize our license list. This work is coordinated with the other working group in seeing that licenses are marked in ways that make them clear to adopters. I will continue my efforts to improve the election rules and processes for the OSI in order to prevent issues and increase election participation. I also plan to continue collaborate with staff in the following areas as OSI’s staffing grows and the staff are able to take on new initiatives: Improving membership participation, recruitment, and fundraising Launching an Ambassador program Working on new license review tools Building awareness of the OSI, its mission and programs Why you should be elected: My main goal as a board member is to help the OSI improve continuously as a non-profit organization. In order for OSI to promote real open source, develop new standards for open source AI, educate developers and lawyers, and advocate for open source projects and contributors in legislatures and with regulatory bodies, it needs to have a stable and growing foundation. OSI needs a high profile and it needs to be trusted and respected, not just by its members, but by world leaders. Maintaining OSI’s status and effectiveness requires continuous work, and as a board member I will be there to help the staff do that work. Get involved Mastodon Twitter LinkedIn Reddit About About Our team Board of directors Sponsors Programs Blog Press mentions Trademark Bylaws Licenses Open Source Definition Licenses License Review Process Open Standards Requirement for Software Open Source AI Open Source AI OSAI Definition Process Timeline Open Weights FAQ Checklist Forum Community Become an Individual Member Become an OSI Affiliate Affiliate Organizations Maintainers Events Forum OpenSource.net The content on this website, of which Opensource.org is the author, is licensed under a Creative Commons Attribution 4.0 International License . Opensource.org is not the author of any of the licenses reproduced on this site. Questions about the copyright in a license should be directed to the license steward. Read our Privacy Policy Proudly powered by WordPress. Hosted by Pressable. Manage Cookie Consent To provide the best experiences, we use technologies like cookies to store and/or access device information. Consenting to these technologies will allow us to process data such as browsing behavior or unique IDs on this site. Not consenting or withdrawing consent, may adversely affect certain features and functions. Functional Functional Always active The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network. Preferences Preferences The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user. Statistics Statistics The technical storage or access that is used exclusively for statistical purposes. The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you. Marketing Marketing The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes. Manage options Manage services Manage {vendor_count} vendors Read more about these purposes Accept Deny View preferences Save preferences View preferences {title} {title} {title} Manage consent | 2026-01-13T08:49:33 |
https://www.fine.dev/blog/o1-vs-sonnet-es#cursor-ai-coding-llm | OpenAI o1 vs. Claude Sonnet 3.5: ¿Cuál modelo de IA es mejor para programar? Home Docs Changelog Pricing Sign in Get started -> Menu Home Docs Changelog Pricing <- Go Back OpenAI o1 vs. Claude Sonnet 3.5: ¿Cuál modelo de IA es mejor para programar? Introducción A medida que la IA continúa evolucionando, dos modelos destacan: o1 de OpenAI y Claude Sonnet 3.5 de Anthropic. Ambos ofrecen capacidades impresionantes para los desarrolladores de software, pero sus fortalezas varían, especialmente cuando se trata de programación. Este blog compara estos dos modelos de IA, centrándose en tareas de programación y rendimiento general. Fine incluye acceso ilimitado a ambos modelos, lo que lo convierte en una excelente manera de probar y comparar cómo o1 y Sonnet se desempeñan con tareas de programación. Diferencias Principales o1 está diseñado para razonamiento complejo y resolución de problemas . Sus respuestas son profundas y reflexivas, lo que lo hace ideal para desarrolladores que trabajan en problemas intrincados o que necesitan explicaciones detalladas. Por otro lado, Claude Sonnet 3.5 se centra en eficiencia y velocidad , destacando en tiempos de respuesta rápidos mientras es más rentable. Si buscas generar código rápidamente o manejar tareas de alto volumen, Claude Sonnet 3.5 puede ser la mejor opción. Ambos modelos utilizan arquitecturas basadas en transformadores, pero o1 es más adecuado para desarrolladores que buscan razonamiento detallado, mientras que Claude Sonnet 3.5 es la opción preferida para aquellos que priorizan la velocidad. Ventana de Contexto y Rendimiento La ventana de contexto juega un papel crucial en cómo estos modelos manejan entradas grandes o conversaciones extendidas. ChatGPT o1 admite 128,000 tokens, mientras que Claude Sonnet 3.5 maneja un mayor 200,000 tokens , dándole una ventaja para tareas que requieren una retención significativa de contexto, como revisar grandes bases de código. Ambos modelos ofrecen un rendimiento sólido en una variedad de tareas, pero sus habilidades brillan en diferentes áreas. ChatGPT o1 sobresale en razonamiento multietapa , explicando la lógica de código compleja en detalle, mientras que Claude Sonnet 3.5 se centra en correcciones de errores rápidas y generación eficiente de código . Versión Mejorada de Claude 3.5 Sonnet - Octubre 2024 - ¿Es Claude ahora mejor que GPT para programar? En octubre de 2024, Anthropic anunció una versión mejorada de Claude 3.5 Sonnet. Las recientes actualizaciones a Claude 3.5 Sonnet han mejorado significativamente sus capacidades de ingeniería de software. Notablemente, el rendimiento del modelo en el benchmark SWE-bench Verified ha mejorado del 33.4% al 49.0%, superando a todos los modelos disponibles públicamente, incluido el o1-preview de OpenAI. Este avance refleja la mayor precisión de Claude 3.5 Sonnet en la generación de funciones y verificación de errores, particularmente en la depuración y refactorización de código que involucra funciones anidadas o segmentos interdependientes. Además, la capacidad de tokens ampliada del modelo le permite retener y utilizar un contexto más extenso, lo que lo hace ideal para revisar grandes bases de código o gestionar proyectos intrincados con múltiples dependencias. Las pruebas iniciales indican que Claude 3.5 Sonnet sobresale en tareas de programación especializadas, como identificar vulnerabilidades de seguridad en aplicaciones web y optimizar algoritmos para velocidad y eficiencia. GitLab, por ejemplo, informó hasta un 10% de mejora en las capacidades de razonamiento para tareas de DevSecOps con el modelo actualizado, sin ningún aumento en la latencia. Casos de uso de IA para programación con o1 y Claude Sonnet 3.5 ChatGPT o1: Depuración de gestión de estado compleja en React: Usa o1 para analizar profundamente por qué ciertos estados no se actualizan correctamente o entran en conflicto entre componentes. Refactorización de código heredado: Emplea el razonamiento exhaustivo de o1 para reestructurar un script antiguo de Python para mejorar su legibilidad y mantenibilidad. Creación de algoritmos: Ideal para escribir y explicar algoritmos como ordenamiento, recorrido de árboles o programación dinámica en detalle. Claude Sonnet 3.5: Generación de código boilerplate: Crea rápidamente archivos de configuración para nuevos proyectos como APIs de Flask o estructura de front-end en Next.js. Autocompletar funciones: Úsalo para completar una función de JavaScript a medio escribir con manejo de errores adecuado y casos extremos. Generación masiva de código: Sonnet 3.5 sobresale en producir estructuras de código repetitivas pero ligeramente variadas como endpoints de API similares o casos de prueba unitarios. ¿Qué modelos de IA utilizan las diferentes herramientas de programación con IA? Hoy en día hay muchas herramientas de desarrollo disponibles para ayudarte con tu programación con IA, desde asistentes avanzados de programación con IA como Fine hasta generadores de código como GitHub Copilot. Algunas usan múltiples LLMs, algunas te dan la opción y otras se basan en un solo modelo. ¿Qué modelo de IA (LLM) utiliza Fine? Fine es una de las pocas herramientas de programación con IA que ofrece a los usuarios la opción entre diferentes LLMs para diversas tareas. Al usar Fine a través del navegador web, los usuarios pueden elegir entre o1-preview, 4o y Claude 3.5 Sonnet. Sin embargo, necesitarás una suscripción pro para aprovechar esto, que cuesta $13-15 por mes. Si eres un usuario gratuito, podrás usar Fine con 4o. Haz clic aquí para probarlo. ¿Qué modelo de IA (LLM) utiliza GitHub Copilot? GitHub Copilot está fuertemente integrado con OpenAI. GitHub es propiedad de Microsoft, que tiene una profunda asociación con OpenAI. La mayoría de los usuarios tienen acceso a 4o, mientras que los suscriptores de Azure AI pueden usar GitHub Copilot con o1-mini y o1-preview. ACTUALIZACIÓN: En GitHub Universe 2024, se anunció que esta asociación exclusiva ya no era tan exclusiva y que la opción de usar Claude se implementaría para todos los usuarios de GitHub Copilot en breve. Algunos usuarios ya han podido acceder a Claude. Está disponible en el Copilot Chat en Visual Studio Code y en Immersive Copilot en el navegador web solamente. ¿Qué modelo de IA (LLM) utiliza Cursor? Cursor utiliza Claude 3.5 Sonnet por defecto y recurre a OpenAI 4o durante interrupciones de Anthropic. ¿Qué modelo de IA (LLM) utiliza Bolt? Bolt, la herramienta de programación con IA que se especializa exclusivamente en front-end, se basa en Claude 3.5 Sonnet. ¿Qué modelo de IA (LLM) utiliza Replit? Aunque Replit lanzó previamente su propio modelo de IA en 2023, cuando anunciaron Replit Agent, su principal herramienta de programación con IA, en 2024, parece que tomaron la decisión de usar Claude 3.5 Sonnet. ¿Cómo comparar diferentes herramientas de programación con IA y LLMs? Si estás buscando comparar cuáles son las mejores herramientas de programación con IA o LLMs, hay algunas cosas a tener en cuenta. Primero, es importante evaluar el LLM y la herramienta por separado. Usa una herramienta como Fine que te permita dar la misma tarea a múltiples LLMs para comparar cuál te da el mejor resultado. Aquí hay una comparación que hicimos de los tres modelos ofrecidos por Fine, planteados con la misma pregunta: ¿Qué hace este repositorio? (Es una pregunta que algunos están llamando el Hola Mundo de la programación con IA). Segundo, compara cómo las herramientas se desempeñan con tu LLM elegido, específico para tu caso de uso. Fine ofrece una variedad de integraciones para aumentar tu productividad, como la capacidad de hacer revisiones dentro de GitHub PR, que están ahorrando horas a los desarrolladores cada semana. ¿Cuál modelo es mejor para programar? Para tareas de programación, tu elección depende de tus necesidades: ChatGPT o1 es la mejor opción cuando trabajas en problemas complejos y multietapa donde necesitas un razonamiento profundo y explicaciones detalladas. Por ejemplo, sobresale en explicar código intrincado o ayudar con la depuración de una manera más reflexiva. Claude Sonnet 3.5 es el modelo preferido para generación de código rápida y eficiente y prototipado iterativo. Es rentable para tareas de alto volumen como generar múltiples fragmentos de código o automatizar correcciones de errores. Ambos modelos apoyan a los desarrolladores en la programación, pero Claude Sonnet 3.5 puede ahorrar tiempo y dinero para tareas de programación cotidianas, mientras que ChatGPT o1 podría ser tu aliado para problemas de programación más difíciles y detallados. Conclusión Al decidir entre ChatGPT o1 y Claude Sonnet 3.5 , considera la complejidad de tus tareas de programación y las restricciones de presupuesto. ChatGPT o1 ofrece una mejor resolución de problemas para tareas intrincadas, mientras que Claude Sonnet 3.5 proporciona una generación de código más rápida y asequible para las necesidades de desarrollo diarias. Ambos modelos son herramientas de IA poderosas que pueden mejorar significativamente tu productividad como desarrollador de software. Regístrate en una plataforma como Fine , que incluye acceso ilimitado a ambos, para lo mejor de ambos mundos sin pagar de más. ¿Por qué suscribirse a Fine? Fine es una plataforma que ofrece acceso ilimitado tanto a o1 como a Claude Sonnet 3.5 , permitiendo a los desarrolladores cambiar entre estos poderosos LLMs según las necesidades de su tarea. Esta flexibilidad es perfecta para aquellos que requieren explicaciones detalladas de ChatGPT o generación de código rápida y eficiente de Claude. Con Fine, no hay necesidad de gestionar tus propias claves API o preocuparte por los límites de uso: todo está incluido. Suscribirse a Fine simplifica el proceso, ofreciendo acceso ilimitado y rentable a ambos modelos para todas tus tareas de programación y desarrollo. Fuentes McNulty, Niall. "ChatGPT o1 vs Claude Sonnet 3.5." Medium , hace 5 días. Enlace . "GPT o1 vs Claude 3.5 Sonnet: ¿Cuál modelo es mejor para programar?" Bind AI Blog , 17 Sep 2024. Enlace . "Comparar o1 Preview vs. Claude 3.5 Sonnet." Context.ai . Enlace . Harisec. "o1 vs Claude." GitHub . Enlace . Tabla de Contenidos Introducción Diferencias Principales Ventana de Contexto y Rendimiento Versión Mejorada de Claude 3.5 Sonnet - Octubre 2024 - ¿Es Claude ahora mejor que GPT para programar? Casos de uso de IA para programación con o1 y Claude 3.5 Sonnet ¿Qué modelos de IA utilizan las diferentes herramientas de programación con IA? Fine GitHub Copilot Cursor Bolt Replit ¿Cómo comparar diferentes herramientas de programación con IA y LLMs? ¿Cuál modelo es mejor para programar? Conclusión ¿Por qué suscribirse a Fine? Start building today Try out the smoothest way to build, launch and manage an app Try for Free -> © Fine.dev - All rights reserved. Product Overview AI Workflows Pricing & Plans Changelog Blog Docs Company Press Terms & Conditions Privacy policy | 2026-01-13T08:49:33 |
https://future.forem.com/code-of-conduct#enforcement | Code of Conduct - 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 Code of Conduct Last updated July 31, 2023 All participants of DEV Community are expected to abide by our Code of Conduct and Terms of Service , both online and during in-person events that are hosted and/or associated with DEV Community. Our Pledge In the interest of fostering an open and welcoming environment, we as moderators of DEV Community pledge to make participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, gender identity and expression, level of experience, nationality, personal appearance, race, religion, or sexual identity and orientation. Our Standards Examples of behavior that contributes to creating a positive environment include: Using welcoming and inclusive language Being respectful of differing viewpoints and experiences Referring to people by their pronouns and using gender-neutral pronouns when uncertain Gracefully accepting constructive criticism Focusing on what is best for the community Showing empathy towards other community members Citing sources if used to create content (for guidance see DEV Community: How to Avoid Plagiarism ) Following our AI Guidelines and disclosing AI assistance if used to create content Examples of unacceptable behavior by participants include: The use of sexualized language or imagery and unwelcome sexual attention or advances The use of hate speech or communication that is racist, homophobic, transphobic, ableist, sexist, or otherwise prejudiced/discriminatory (i.e. misusing or disrespecting pronouns) Trolling, insulting/derogatory comments, and personal or political attacks Public or private harassment Publishing others' private information, such as a physical or electronic address, without explicit permission Plagiarizing content or misappropriating works Other conduct which could reasonably be considered inappropriate in a professional setting Dismissing or attacking inclusion-oriented requests We pledge to prioritize marginalized people's safety over privileged people's comfort. We will not act on complaints regarding: 'Reverse' -isms, including 'reverse racism,' 'reverse sexism,' and 'cisphobia' Reasonable communication of boundaries, such as 'leave me alone,' 'go away,' or 'I'm not discussing this with you.' Someone's refusal to explain or debate social justice concepts Criticisms of racist, sexist, cissexist, or otherwise oppressive behavior or assumptions Enforcement Violations of the Code of Conduct may be reported by contacting the team via the abuse report form or by sending an email to support@dev.to . All reports will be reviewed and investigated and will result in a response that is deemed necessary and appropriate to the circumstances. Further details of specific enforcement policies may be posted separately. Moderators have the right and responsibility to remove comments or other contributions that are not aligned to this Code of Conduct or to suspend temporarily or permanently any members for other behaviors that they deem inappropriate, threatening, offensive, or harmful. If you agree with our values and would like to help us enforce the Code of Conduct, you might consider volunteering as a DEV moderator. Please check out the DEV Community Moderation page for information about our moderator roles and how to become a mod. Attribution This Code of Conduct is adapted from: Contributor Covenant, version 1.4 Write/Speak/Code Geek Feminism 💎 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 | 2026-01-13T08:49:33 |
https://www.fine.dev/blog/build-scalable-tech-infrastructure-for-startups#scalable-data | How to Build a Scalable Tech Infrastructure on a Startup Budget: A Step-by-Step Guide for CTOs Home Docs Changelog Pricing Sign in Get started -> Menu Home Docs Changelog Pricing <- Go Back How to Build a Scalable Tech Infrastructure on a Startup Budget: A Step-by-Step Guide for CTOs Building a scalable tech infrastructure on a startup budget requires creativity and prioritization. As a CTO, you need to grow infrastructure without exhausting resources. This guide outlines steps to help your tech stack expand with your user base, without financial strain. Table of Contents Start with Open-Source Solutions Use Cloud Services Wisely Modular Architecture Automate Early Think Lean—Build for Your Current Needs Monitoring and Alerts Outsource Non-Critical Components Leverage Community and Startup Programs Scalable Data Management Prepare for Growth with a Flexible Mindset Look for Integrations Ready to Scale with Ease? 1. Start with Open-Source Solutions When budget is tight, opting for open-source software can be a game-changer. Open-source solutions often provide the flexibility you need to get started without the licensing fees associated with proprietary systems. Tools like PostgreSQL for databases, Kubernetes for orchestration, and Apache Kafka for data streaming can all be incredibly effective without incurring high costs. can all be incredibly effective without incurring high costs. The initial learning curve might be steep, but the savings are well worth it. There's also a whole community out there to help you. 2. Use Cloud Services Wisely The allure of cloud services like AWS , Google Cloud , or Azure is real—scalability, reliability, and global availability. However, these services can become expensive if not optimized. Start small by utilizing free tiers and cost calculators. Identify the essential cloud resources you need, and always keep an eye on your billing dashboard. Consider using cloud credits, which are often available for startups through accelerator programs.. 3. Modular Architecture Adopting a modular architecture allows you to build components that can be independently scaled or replaced. By separating services (e.g., microservices or serverless functions), you gain the flexibility to scale certain parts of your infrastructure as needed, instead of the entire system. This approach can help you save on unnecessary costs and avoid a complete overhaul when scaling. 4. Automate Early Automation saves both time and money. Implement CI/CD pipelines to automate testing, deployment, and code integration. This not only reduces manual effort but also helps you ship faster without additional costs. Tools like Jenkins , GitLab CI , or GitHub Actions are great options that won't break the bank, and they help maintain quality control as your team expands. that won't break the bank, and they help maintain quality control as your team expands. They can also work together with Fine, to ensure that you not only have a robust set of tests that constantly run, but any failures are turned into fixes at maximum speed. 5. Think Lean—Build for Your Current Needs Avoid the temptation to over-engineer your infrastructure based on hypothetical future requirements. Focus on building for your current needs, but keep scalability in mind. You want something that’s "scale-ready" without being bloated. An MVP-style infrastructure should focus on the most crucial features that will support immediate growth and customer acquisition. 6. Monitoring and Alerts Establishing a simple monitoring system will help you identify issues before they impact users. Open-source tools like Prometheus and Grafana allow you to keep an eye on system performance and resource usage. on system performance and resource usage. Effective monitoring helps you make informed decisions on scaling—such as when it's truly necessary to increase server capacity. 7. Outsource Non-Critical Components To keep your internal team focused on core competencies, consider outsourcing non-critical functions, like hosting static assets or even customer support. Managed services can help reduce overhead. For example, Firebase can handle authentication and real-time data syncing, allowing your developers to focus on core product features instead of worrying about server maintenance. 8. Leverage Community and Startup Programs Many tech giants offer generous startup programs, including cloud credits, free tools, and discounted software licenses. Amazon Activate , Microsoft for Startups , and Google for Startups are programs that can provide significant cost savings in the early stages. that can provide significant cost savings in the early stages. Engage with tech communities like Stack Overflow and GitHub as well, where you can access free resources and advice. 9. Scalable Data Management Data is at the core of most tech businesses, but managing it can quickly become expensive if not done wisely. Start with cost-effective databases like PostgreSQL or NoSQL options like MongoDB, depending on your needs. As your data needs grow, consider partitioning, archiving older data, and using data warehouses only when it makes sense. 10. Prepare for Growth with a Flexible Mindset Scalability is about more than technology; it's about mindset. Regularly evaluate whether your tech stack is meeting your current needs and where you might face constraints as you grow. Flexibility in choosing tools, hiring, and decision-making will allow you to scale smoothly when your startup hits growth phases. 11. Look for integrations Where platforms offer similar features, integrations with your existing tech stack can often be the deciding factor. The more your platforms can talk to each other and automate tasks, the better for your growth. Fine works with a variety of platforms to build a knowledge graph and complement your natural workflows, making it the premier AI choice for many scaling startups. Ready to Scale with Ease? Consider using Fine to make your infrastructure scalable and efficient. Fine offers advanced AI capabilities that help automate testing, code integration, and debugging, allowing your team to focus on core development without getting bogged down in manual tasks. Start building today Try out the smoothest way to build, launch and manage an app Try for Free -> © Fine.dev - All rights reserved. Product Overview AI Workflows Pricing & Plans Changelog Blog Docs Company Press Terms & Conditions Privacy policy | 2026-01-13T08:49:33 |
https://opensource.org/board-member/anne-marie-scott | Anne-Marie Scott – Open Source Initiative Skip to content Get involved About Licenses Open Source Definition Open Source AI Programs Blog Get involved About Licenses Open Source Definition Open Source AI Programs Blog Open Main Menu Anne-Marie Scott Anne-Marie Scott she/her Chair of the finance committee Board Member Proposed by: Apereo Software Foundation Candidacy Period: April 15, 2023 – March 31, 2026 Type of Seat: Affiliate Anne-Marie has been a member of the Apereo (and formerly Ja-sig) community since the mid-2000s, active in the implementation of open source technologies in higher education in the UK and Canada. She has been a member of the Apereo Board of Directors since 2018, and has held the role of Board Chair since 2020. She is currently Deputy Provost of Athabasca University, Canada’s largest open university, and works as an external advisor to the government of British Columbia’s Ministry of Advanced Education and Skills. In this context she has been successful in introducing the idea of a sector-wide OSPO pilot as part of the Ministry’s Digital Learning Strategy. This project explicitly aims to build community and capacity in open source, supporting wider access to education and reduced costs for the sector. It is expected to be funded in 2023/24. She has also been a core member of the OpenETC ( opened.ca ) in British Columbia since 2018, providing a sector-wide set of shared open technologies including WordPress, Mattermost, and Sandstorm. She co-authored and teaches the Open Educational Technologies module of Kwantlen Polytechnic University’s Open Education programme, and as a passionate advocate for open education, she believes that open education is not truly possible without open platforms to support it. As she cycles off the Apereo Board after her second term of service, she is keen to continue to play an active role in advocating for and supporting open source globally. How the candidate will contribute to the boar d Anne-Marie brings existing Board level experience. As Chair of the Apereo Board over the last 3 years she has led the replacement of our Executive Director, a full operational and financial review, and is currently working on a revision of our strategy, due to complete as her Board term ends. She also has significant Board experience from other domains having sat for over a decade on the Board of a building preservation charity in the UK. She has experience dealing with government representatives through her work in Canada and with Apereo. Through her work in Scotland leading Girl Geek Scotland (a women in IT advocacy group) for 3 years she has experience working with the private tech sector. Through her senior leadership roles in higher education she brings financial, organisation, communication, and change management skills to the OSI, along with her education domain experience. She brings a wide global network of contacts within the open education movement along with strong community building skills. Why the candidate should be elected Having worked in higher education technology for over 20 years, Anne-Marie brings experience of the realities of implementing open source successfully in a domain that has been rapidly moving towards adoption of commercial and proprietary tech in many countries. As awareness of surveillance cultures and the predatory nature of educational technology companies become more visible post-COVID she believes there is a real moment appearing for strong advocacy for change and wider adoption of open source. She has been writing and advocating for changes to public sector procurement practices for over a decade to make the adoption of open source more possible, seeing this area as a systemic barrier at present. She believes that education is a particularly important domain for open source communities to engage with, as it is a crucial opportunity to build the awareness and talent that can support the wider global open source movement. Get involved Mastodon Twitter LinkedIn Reddit About About Our team Board of directors Sponsors Programs Blog Press mentions Trademark Bylaws Licenses Open Source Definition Licenses License Review Process Open Standards Requirement for Software Open Source AI Open Source AI OSAI Definition Process Timeline Open Weights FAQ Checklist Forum Community Become an Individual Member Become an OSI Affiliate Affiliate Organizations Maintainers Events Forum OpenSource.net The content on this website, of which Opensource.org is the author, is licensed under a Creative Commons Attribution 4.0 International License . Opensource.org is not the author of any of the licenses reproduced on this site. Questions about the copyright in a license should be directed to the license steward. Read our Privacy Policy Proudly powered by WordPress. Hosted by Pressable. Manage Cookie Consent To provide the best experiences, we use technologies like cookies to store and/or access device information. Consenting to these technologies will allow us to process data such as browsing behavior or unique IDs on this site. Not consenting or withdrawing consent, may adversely affect certain features and functions. Functional Functional Always active The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network. Preferences Preferences The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user. Statistics Statistics The technical storage or access that is used exclusively for statistical purposes. The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you. Marketing Marketing The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes. Manage options Manage services Manage {vendor_count} vendors Read more about these purposes Accept Deny View preferences Save preferences View preferences {title} {title} {title} Manage consent | 2026-01-13T08:49:33 |
https://docs.github.com/en/get-started/git-basics/managing-remote-repositories | Managing remote repositories - GitHub Docs Skip to main content GitHub Docs Version: Free, Pro, & Team Search or ask Copilot Search or ask Copilot Select language: current language is English Search or ask Copilot Search or ask Copilot Open menu Open Sidebar Get started / Git basics / Manage remote repositories Home Get started Start your journey About GitHub and Git Create an account Hello World Set up your profile Find inspiration Download files Upload a project Learning resources Onboarding Getting started with your GitHub account Getting started with GitHub Team Getting started with the GitHub Enterprise Cloud trial Getting started with GitHub Enterprise Cloud Using GitHub GitHub flow Connecting to GitHub Communicating on GitHub Feature preview Supported browsers GitHub Mobile Allow network access Connectivity problems Learning about GitHub GitHub’s plans GitHub language support Types of GitHub accounts Access permissions GitHub Advanced Security Changes to GitHub plans GitHub glossary Learn to code Get started with Git Finding example code Reuse people's code Set up Copilot for learning Local development Debug with Copilot Storing secrets safely Getting feedback on your code Secure your code Secure your dependencies Accessibility Manage theme settings Keyboard shortcuts GitHub Command Palette Writing on GitHub Start writing on GitHub Quickstart About writing & formatting Basic formatting syntax Work with advanced formatting Organized data with tables Collapsed sections Create code blocks Create diagrams Mathematical expressions Auto linked references Attaching files About tasklists Permanent links to code Using keywords in issues and pull requests Work with saved replies About saved replies Creating a saved reply Editing a saved reply Deleting a saved reply Using saved replies Share content with gists Creating gists Forking and cloning gists Saving gists with stars Moderating gist comments Explore projects Finding open source projects Contribute to open source Use Copilot to explore projects Contribute to a project Save repositories with stars Following people Following organizations Git basics Set up Git Set your username Caching credentials Repeated credential prompts macOS Keychain credentials Git workflows About remote repositories Manage remote repositories Associate text editors Handle line endings Ignoring files Git cheatsheet Using Git About Git Push commits to a remote Get changes from a remote Non-fast-forward error Splitting a subfolder About Git subtree merges About Git rebase Git rebase Resolve conflicts after rebase Special characters in names Maximum push limit Archive account and public repos Request account archive GitHub Archive program Using GitHub Docs Docs versions Hover cards GitHub Certifications About GitHub Certifications Registering for an exam Get started / Git basics / Manage remote repositories Managing remote repositories Learn to work with your local repositories on your computer and remote repositories hosted on GitHub. Platform navigation Mac Windows Linux View page as Markdown In this article Adding a remote repository Changing a remote repository's URL Renaming a remote repository Removing a remote repository Further reading Adding a remote repository To add a new remote, use the git remote add command on the terminal, in the directory your repository is stored at. The git remote add command takes two arguments: A remote name, for example, origin A remote URL, for example, https://github.com/OWNER/REPOSITORY.git For example: $ git remote add origin https://github.com/OWNER/REPOSITORY.git # Set a new remote $ git remote -v # Verify new remote > origin https://github.com/OWNER/REPOSITORY.git (fetch) > origin https://github.com/OWNER/REPOSITORY.git (push) For more information on which URL to use, see About remote repositories . Troubleshooting: Remote origin already exists This error means you've tried to add a remote with a name that already exists in your local repository. $ git remote add origin https://github.com/octocat/Spoon-Knife.git > fatal: remote origin already exists. To fix this, you can: Use a different name for the new remote. Rename the existing remote repository before you add the new remote. For more information, see Renaming a remote repository below. Delete the existing remote repository before you add the new remote. For more information, see Removing a remote repository below. Changing a remote repository's URL The git remote set-url command changes an existing remote repository URL. Tip For information on the difference between HTTPS and SSH URLs, see About remote repositories . The git remote set-url command takes two arguments: An existing remote name. For example, origin or upstream are two common choices. A new URL for the remote. For example: If you're updating to use HTTPS, your URL might look like: https://github.com/OWNER/REPOSITORY.git If you're updating to use SSH, your URL might look like: git@github.com:OWNER/REPOSITORY.git Switching remote URLs from SSH to HTTPS Open Terminal Terminal Git Bash . Change the current working directory to your local project. List your existing remotes in order to get the name of the remote you want to change. $ git remote -v > origin git@github.com:OWNER/REPOSITORY.git (fetch) > origin git@github.com:OWNER/REPOSITORY.git (push) Change your remote's URL from SSH to HTTPS with the git remote set-url command. git remote set-url origin https://github.com/OWNER/REPOSITORY.git Verify that the remote URL has changed. $ git remote -v # Verify new remote URL > origin https://github.com/OWNER/REPOSITORY.git (fetch) > origin https://github.com/OWNER/REPOSITORY.git (push) The next time you git fetch , git pull , or git push to the remote repository, you'll be asked for your GitHub username and password. When Git prompts you for your password, enter your personal access token. Alternatively, you can use a credential helper like Git Credential Manager . Password-based authentication for Git has been removed in favor of more secure authentication methods. For more information, see Managing your personal access tokens . You can use a credential helper so Git will remember your GitHub username and personal access token every time it talks to GitHub. Switching remote URLs from HTTPS to SSH Open Terminal Terminal Git Bash . Change the current working directory to your local project. List your existing remotes in order to get the name of the remote you want to change. $ git remote -v > origin https://github.com/OWNER/REPOSITORY.git (fetch) > origin https://github.com/OWNER/REPOSITORY.git (push) Change your remote's URL from HTTPS to SSH with the git remote set-url command. git remote set-url origin git@github.com:OWNER/REPOSITORY.git Verify that the remote URL has changed. $ git remote -v # Verify new remote URL > origin git@github.com:OWNER/REPOSITORY.git (fetch) > origin git@github.com:OWNER/REPOSITORY.git (push) Troubleshooting: No such remote '[name]' This error means that the remote you tried to change doesn't exist: $ git remote set-url sofake https://github.com/octocat/Spoon-Knife > fatal: No such remote 'sofake' Check that you've correctly typed the remote name. Renaming a remote repository Use the git remote rename command to rename an existing remote. The git remote rename command takes two arguments: An existing remote name, for example, origin A new name for the remote, for example, destination Example of renaming a remote repository These examples assume you're cloning using HTTPS , which is recommended. $ git remote -v # View existing remotes > origin https://github.com/OWNER/REPOSITORY.git (fetch) > origin https://github.com/OWNER/REPOSITORY.git (push) $ git remote rename origin destination # Change remote name from 'origin' to 'destination' $ git remote -v # Verify remote 's new name > destination https://github.com/OWNER/REPOSITORY.git (fetch) > destination https://github.com/OWNER/REPOSITORY.git (push) Troubleshooting: Could not rename config section 'remote.[old name]' to 'remote.[new name]' This error means that the old remote name you typed doesn't exist. You can check which remotes currently exist with the git remote -v command: $ git remote -v # View existing remotes > origin https://github.com/OWNER/REPOSITORY.git (fetch) > origin https://github.com/OWNER/REPOSITORY.git (push) Troubleshooting: Remote [new name] already exists This error means that the remote name you want to use already exists. To solve this, either use a different remote name, or rename the original remote. Removing a remote repository Use the git remote rm command to remove a remote URL from your repository. The git remote rm command takes one argument: A remote name, for example, destination Removing the remote URL from your repository only unlinks the local and remote repositories. It does not delete the remote repository. Example of removing a remote repository These examples assume you're cloning using HTTPS , which is recommended. $ git remote -v # View current remotes > origin https://github.com/OWNER/REPOSITORY.git (fetch) > origin https://github.com/OWNER/REPOSITORY.git (push) > destination https://github.com/FORKER/REPOSITORY.git (fetch) > destination https://github.com/FORKER/REPOSITORY.git (push) $ git remote rm destination # Remove remote $ git remote -v # Verify it 's gone > origin https://github.com/OWNER/REPOSITORY.git (fetch) > origin https://github.com/OWNER/REPOSITORY.git (push) Note git remote rm does not delete the remote repository from the server. It simply removes the remote and its references from your local repository. Troubleshooting: Could not remove config section 'remote.[name]' This error means that the remote you tried to delete doesn't exist: $ git remote rm sofake > error: Could not remove config section 'remote.sofake' Check that you've correctly typed the remote name. Further reading "Working with Remotes" from the Pro Git book Help and support Did you find what you needed? Yes No Privacy policy Help us make these docs great! All GitHub docs are open source. See something that's wrong or unclear? Submit a pull request. Make a contribution Learn how to contribute Still need help? Ask the GitHub community Contact support Legal © 2026 GitHub, Inc. Terms Privacy Status Pricing Expert services Blog | 2026-01-13T08:49:33 |
https://www.fine.dev/blog/captive-portal#pricing | Creating a Custom Captive Portal for Home WiFi with Raspberry Pi and AI Magic Home Docs Changelog Pricing Sign in Get started -> Menu Home Docs Changelog Pricing <- Go Back Creating a Custom Captive Portal for Home WiFi with Raspberry Pi and AI Magic Table of Contents What is a Captive Portal? Capabilities of a Captive Portal You Will Need Why Raspberry Pi? RaspAP: Simplifying WiFi Management Why Do We Need RaspAP for a Captive Portal? Why Is an Ethernet Cable Needed? Introduction to Nodogsplash Customizing the Splash Page Generating a Stunning Splash Page Image Customizing HTML & CSS with Fine’s AI Agents Test Your Customized Page Final Words Ever wondered about the magic behind those WiFi login pages that greet you at places like Starbucks? You know the drill – you sip your coffee, pull out your laptop or smartphone, connect to the WiFi, and voilà! Suddenly, you're redirected to a page where you need to log in or accept terms before diving into the digital realm. It's a seamless experience we've all grown accustomed to, but have you ever thought about creating one yourself? Well, probably not. But I did! And there’s a good reason why. I live on Ruppin Street, and as a joke, I call my apartment the “Royal Ruppin Relax” as if it was some kind of boutique hotel. I wanted to create my own customized WiFi login portal so that guests at my home would get a surprise when they log in. That's what we're diving into today: In this tutorial, I’ll show you how to build and customize your own captive portal – a digital gateway that not only controls access but also acts as a canvas for your creativity and a great conversation starter! With a Raspberry Pi and a bit of AI magic, you can transform your mundane WiFi login into an engaging, personalized experience. But First, What is a Captive Portal? The term might sound technical, but in essence, it's the official name for those login pages you encounter when connecting to a public WiFi network. Most captive portals are like virtual gatekeepers, ensuring that only authorized users gain access to a WiFi network. But this interface can be a powerful tool, not just for authentication, but also for conveying information and engaging users creatively. Capabilities of a Captive Portal: Authentication : Captive portals authenticate users by prompting them to enter login credentials or accept terms and conditions. This process ensures that the network is used responsibly and securely. Customization : One of the features of a captive portal is its customization potential. Businesses often use captive portals to showcase their branding, display advertisements, or provide essential information. Access Control : Captive portals enable administrators to control the type of access users have to the internet. For instance, they can restrict certain websites, limit bandwidth, or provide different levels of access based on user roles. So technically, you can configure it such that your devices are prioritized bandwidth-wise on your WiFi network, but that’s up to you. 😉 Now, let's move forward and create our own captivating captive portal. The creative journey begins! You Will Need: Before we dive into creating your personalized captive portal, let's gather the essentials: Raspberry Pi : The heart of your project, this versatile microcomputer will serve as the central hub for your captive portal setup. MicroSD Card : You'll need a microSD card (at least 16GB) to store the operating system and other necessary files. Power Supply : Ensure you have a compatible power supply for your Raspberry Pi to keep it running smoothly. Ethernet Cable : You'll require an Ethernet cable to establish a wired connection between your Raspberry Pi and your internet router. Why Raspberry Pi? In the landscape of network devices, not all routers are created equal. Many standard routers lack native support for captive portals, making it challenging to implement this feature seamlessly. When faced with this limitation, we turn to Raspberry Pi as a solution. This credit-card-sized, affordable computer will allow you to run complementary network-related software and overcome the constraints of your existing router. If you've never used your Raspberry Pi before, set it up according to the [simple instructions on the official website]( https://www.raspberrypi.com/documentation/computers/getting-started.html ). Our next step would be installing RaspAP. RaspAP: Simplifying WiFi Management Now that you have your Raspberry Pi ready, it's time to introduce RaspAP. RaspAP is an open-source software that simplifies the process of setting up a WiFi access point on your Raspberry Pi. Think of it as the bridge between your Raspberry Pi and the devices that will connect to your WiFi. [To install RaspAP, simply follow the instructions on the official website]( https://raspap.com/#quick ). Why Do We Need RaspAP for a Captive Portal? To create a captive portal, we need a WiFi network that's entirely under our control. RaspAP allows you to do just that: while Raspberry Pi provides the hardware backbone, RaspAP adds the user-friendly interface, making it incredibly easy to configure your WiFi network settings. You can customize the network name (SSID), set up passwords, and manage the connection preferences. RaspAP handles the complexities of access points, security protocols, and IP addresses, ensuring that the WiFi network your guests connect to operates smoothly and securely. Why Is an Ethernet Cable Needed? You might be wondering about the necessity of an Ethernet cable in a wireless setup. When you connect your Raspberry Pi to your router using an Ethernet cable, you establish a stable, wired connection. This wired connection serves as the foundation upon which you'll build your customized WiFi network. Introduction to Nodogsplash Now that you've set up your WiFi access point with RaspAP, it's time to introduce Nodogsplash into the mix. Nodogsplash is a high-performance Captive Portal and the key player in bringing our idea to life. Nodogsplash offers by default a simple splash page that we will customize later. Install and configure Nodogsplash by following the easy tutorial on RaspAP’s official documentation. If you are successful, you will see this page: Nodogsplash Customizing the Splash Page Here comes the exciting part! Now we will customize the captive portal page to our liking. Customizing the splash page might seem like a challenging task for two reasons: Nodogsplash Rules : Nodogsplash has specific rules that the splash page must adhere to, ensuring functionality. Deviating from these rules might result in our captive portal not working, making it crucial to comply with them. CDCs Force Us to Work with HTML and CSS Only, No JS : A CDC (Captive Detection Client) is a component in operating systems or devices that helps in detecting whether a network has a captive portal. When a device connects to a WiFi network, the CDC functionality checks if the network connection is restricted by a captive portal. If it detects a captive portal, the device redirects the user to the portal's login or authentication page. Most of the CDCs don’t allow JS or even href s, so we will have to work with HTML and CSS only to make a beautiful captive portal. Manipulating HTML & CSS requires a good understanding of their syntax, making customization challenging for many users. To overcome these challenges, we will use some ✨ AI magic ✨. Generating a Stunning Splash Page Image First, we will obtain a stunning boutique hotel picture with Leonardo AI: an innovative tool that generates realistic and visually appealing images from prompts. Here’s how you can use it: [Visit Leonardo AI : Go to the Leonardo AI website and click on “AI Image Generation”]( https://leonardo.ai/ ). Generate Your Image : Using Leonardo AI's intuitive interface, generate an image that resonates with your captive portal's ambiance. You can tweak various settings until you find the perfect image. My prompt was: “A beautiful boutique hotel next to the sea, palms and luxurious atmosphere, beautiful day”. Download Your Image : Once satisfied with the generated image, download it to your computer. This stunning visual will serve as the backdrop for your customized splash page. Customizing HTML & CSS with Fine’s AI Agents Now that we have the image, we can customize the default HTML and CSS. To do that we will use Fine’s AI agents, which can quickly get us to the point: Deploy an HTML Agent to Your Workspace : Open Fine and click “Deploy Agent”. Upload the YAML file of the HTML Agent, found [here]( https://github.com/finehq/fine/blob/main/html-agent/html-agent.yml ). This agent specializes in HTML and CSS tasks. Create a Project : Place the default Nodogsplash files in a folder, together with your generated image. Run git init inside the folder and then add it as a new project to Fine. Create a Notebook and Specify the Changes You Want to Make : The agents work according to a plan specified in a notebook. I wrote a short description of my wanted task and connected the notebook to the project. Run the Agent and Make Some Final Tweaks : The agent will start changing the HTML and CSS pages according to the specifications in your notebook. If it isn’t exactly to your liking, make the final changes and that’s it! With Fine’s AI agents, the process of customizing your splash page becomes intuitive and efficient. You don’t need to deal with HTML and CSS, and you don’t need to learn the rules of Nodogsplash. You easily transform a basic login interface into a visually appealing and engaging portal that captivates users, providing a memorable WiFi experience. Test Your Customized Page After Fine generates the code, test your customized splash page. To do that, upload your files to the Raspberry Pi and replace the default splash page files in /etc/Nodogsplash/htdocs/ . Ensure that it complies with Nodogsplash rules and provides a seamless user experience. Make any necessary adjustments until you achieve the desired result. Final Words By integrating Raspberry Pi, RaspAP, Nodogsplash, Fine, and Leonardo AI, you've not only created a functional captive portal but also unleashed your creativity without the headache of coding intricacies. This project not only enhances your technical skills but also transforms your WiFi experience at home. Feel free to experiment further and explore the endless possibilities of customization, all thanks to the power of innovative AI technology. Now it's your turn to improve your home WiFi experience! Get creative, get connected, and let your imagination run wild – AI will take care of the rest! Start building today Try out the smoothest way to build, launch and manage an app Try for Free -> © Fine.dev - All rights reserved. Product Overview AI Workflows Pricing & Plans Changelog Blog Docs Company Press Terms & Conditions Privacy policy | 2026-01-13T08:49:33 |
https://dev.to/beau-to/bun-ify-your-project-544i | Bun-ify Your Project - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Anna for Beau Posted on Mar 6, 2024 Bun-ify Your Project # javascript # bunjs # vue # nuxt In the realm of front-end development, maximizing efficiency and performance is paramount. Bun is a JavaScript runtime that offers faster development, testing, running, and bundling for your project. Moreover, it is also known because of its memory efficiency. Bun claims to offer significant improvements in their benchmarks. Bundle benchmark: Package installation: It’s also worth paying attention to Bun’s bundler abilities: support for tree shaking, source maps, and minification. Bun was known for some time even though the v1.0 was released only on September 8, 2023, and caused much fuss among the front-end community. So, after some preparation and research, we decided to use it in our project, and that’s what happened. Initial data At Beau, we have several front-end projects with the same architecture. Those projects were built using Nuxt.js, Vue2, and JavaScript. The Yarn was used as a package manager. Also, our projects have a bunch of tests: unit, e2e, and regression. Those tests use Puppeteer, jest, playwright, and other handy vue libraries for testing. Why did we decide to use Bun? Who, as a developer, has never faced the issue of waiting for a project to build or tests to run? This obstacle is relatable to any developer. Moreover, for business, it means money. Our project isn’t an exception. The slower parts of our processes are package installation and running tests. We think that Bun might help us to speed up such processes. Replacing yarn First of all, we need to deal with package management. The first step was installing the Bun itself. We can find all the necessary commands in Bun documentation. curl -fsSL https://bun.sh/install|bash #for macOS, Linux and WSL Enter fullscreen mode Exit fullscreen mode Bun also provides a Docker image if it’s necessary. Let’s check our local speed of package installation with yarn. To be precise about this, we need to clean the yarn cache by using the following command: yarn cache clean Enter fullscreen mode Exit fullscreen mode After this, the pure installation speed will be almost a minute. Done in 57.33s Enter fullscreen mode Exit fullscreen mode So, let’s try installing the packages with bun. bun install Enter fullscreen mode Exit fullscreen mode We can already see a significant difference. With yarn using a cache, this difference isn’t that impressive. Done in 23.71s Enter fullscreen mode Exit fullscreen mode After installing the packages, Bun will also add the bun.lockb file as an analog of yarn.lock or package.lock. Bun will install dependencies, devDependencies, optionalDependencies, and peerDependecies by default, but because of security reasons, it will skip lifecycle scripts of installed dependencies. And this might be a problem. These scripts, such as postinstall-scripts or node-gyp, might be an essential part of the package you use. Using Bun, you can see some errors like this: error: could not determine executable to run for package Enter fullscreen mode Exit fullscreen mode Bun has a solution for it. First of all, it already has a list of trusted dependencies. For them, Bun will execute all necessary scripts by default. Otherwise, you can add it to trustedDependecies in your package.json file. In Bun community usage of trustedDependencies is a hot topic . There are several suggestions on how to improve it. Tests with Bun After dealing with packages, we need to look at our tests. The first obstacle we faced here was the puppeteer. Puppeteer is a Node.js library that provides a high-level API to control Chrome/Chromium over the DevTools Protocol. It’s usually used for e2e testing or screenshot testing. This library has a script that installs Chromium by default, but we must find a solution as Bun skips it. As was discussed before, it’s about trustedDependencies. Although Bun already added Puppeteer to the list of trusted dependencies, it still skips the part with chromium installation. Adding this library to trustedDependecies in package.json file doesn’t help. During the test run, no browser was installed. We found an open bug in the Bun repo with similar problems. It ended up with a separate script that installed the necessary browser for Puppeteer. Not a big deal. The other thing was the collision of webpack package versions, so we had to fix one specific version via the overrides option in the package.json file. So far, we used Bun for e2e end regression testing. But what about unit tests? Bun has the opportunity to get rid of any test runner because it has all the necessary instruments for it, similar to jest abilities. Unfortunately, it seems not to work with vue-test-utils, which is essential for our project, so we decided to keep it as it was, at least for now. After running this test, we found that something was wrong with the installed testing libraries and bumped into the following messages: - Test suite failed to run Cannot find module '../build/Release/canvas.node' Enter fullscreen mode Exit fullscreen mode This time, the solution with trusted dependencies helps us. GitHub actions Besides library installation and test running, running projects in dev and production mode didn’t cause any problems, so it is time to look at GitHub actions. First, we needed to use the official setup-bun GitHub action to use Bun. Second, we needed to rewrite all commands with bun usage instead of npm or npx. After that, there was a last question. Usually, we need to use some cache mechanism in GitHub actions for package installation. We dived into the documentation and GitHub issues, and according to this fantastic comment, there is no need for that. Conclusion Using Bun helped us reach our main goal with minimum effort from our team. We successfully implemented Bun in 2 of our projects, speeding up our pipeline time by 30%. For me, as a developer, it means the ability to deliver some changes faster without much time for waiting. It allows business to see actual changes more quickly, ultimately saving time and cost. Imagine how Bun might speed up processes on larger projects! We faced some problems, but all of them had solutions. It’s also worth mentioning that Bun creators and the community are aware of those problems and continue working on solutions. The next steps for our project will be improvements in tests and their adaptations for our team to use Bun entirely. It is also worth mentioning a few problems with Bun: Windows support is still experimental It came out AFTER ChatGPT:) So, no help from AI. Bun still cannot completely replace node.js Top comments (1) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Collapse Expand Daria Moreno-Gogoleva Daria Moreno-Gogoleva Daria Moreno-Gogoleva Follow front end developer Joined Nov 28, 2019 • Mar 6 '24 Dropdown menu Copy link Hide Thank you a lot! Like comment: Like comment: 2 likes Like Comment button Reply Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Beau Follow YC S21 Trending on DEV Community Hot Prompt Engineering Won’t Fix Your Architecture # discuss # career # ai # programming 🧗♂️Beginner-Friendly Guide 'Max Dot Product of Two Subsequences' – LeetCode 1458 (C++, Python, JavaScript) # programming # cpp # python # javascript What was your win this week??? # weeklyretro # discuss 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/devteam/congrats-to-the-winners-of-postmark-challenge-inbox-innovators-56f2 | Congrats to the Winners of Postmark Challenge: Inbox Innovators! - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse dev.to staff for The DEV Team Posted on Jun 24, 2025 Congrats to the Winners of Postmark Challenge: Inbox Innovators! # devchallenge # postmarkchallenge # webdev # api The wait is over! We are excited to announce the winners of Postmark Challenge: Inbox Innovators . This challenge truly showcased the incredible creativity that emerges when developers are given the freedom to innovate. From AI-powered contract analysis and interactive workplace comedies to daily briefings and IRC-style chats, our participants demonstrated that email is far from a legacy technology. We hope you enjoyed pushing the boundaries of what's possible with email and are proud of your submissions, regardless of whether or not you take home the cash prize. Without further ado, our winners. Congratulations To… PostmarkGBA: Gaming Through Your Inbox @rensieeee created a working GameBoy Advanced emulator that you control entirely through email. PostmarkGBA: A working GBA emulator running through Postmark Rens Wolters ・ May 26 #devchallenge #postmarkchallenge #webdev #api This project transforms your inbox into a collaborative gaming experience, much like "Twitch Chat Plays" but accessible through the most universal communication platform. MailCast.ai: Your Personal Podcast Producer @tom_canfarotta_775a68254f developed a service that converts any email into a podcast episode. 🎙️ MailCast.ai: Email-to-Podcast-RSS-Feed Tom Canfarotta ・ Jun 9 #webdev #devchallenge #postmarkchallenge #api Forward any newsletter or article and you'll receive an MP3 download and personal RSS feed in return! Email PR Bot: Email-to-Code Generation @async_dime built an AI-powered development workflow that turns email requests into working code. EPB: Turn Emails into Code - AI-Powered Pull Requests from Your Inbox B G Adam ・ Jun 9 #devchallenge #postmarkchallenge #webdev #api Simply send coding requirements to the service, and EPB analyzes your repository context, generates appropriate code using Mistral AI, and creates a GitHub pull request—all from a single email. Our three winners will each receive: $1,000 USD DEV++ Membership Exclusive DEV badge All participants with valid submissions will receive a completion badge. Special Thanks to Postmark We want to shout out Postmark for sponsoring this challenge. Postmark's developer-focused API and reliable inbound email parsing made these innovative projects possible, allowing the community to focus on creativity rather than email handling complexity. If you're inspired by these projects and want to build your own email-driven applications, we hope you choose Postmark. What's next? Keep your DEV Challenges streak going!! Here are three more challenges live right now for you to check out: Join the Storyblok Headless CMS Challenge: $3,000 in Prizes! dev.to staff for The DEV Team ・ Jun 11 #devchallenge #webdev #api #storyblokchallenge Join the Runner H "AI Agent Prompting" Challenge: $10,000 in Prizes for 20 Winners!!! dev.to staff for The DEV Team ・ Jun 5 #devchallenge #runnerhchallenge #ai #machinelearning Join our latest Frontend Challenge: June Celebrations dev.to staff for The DEV Team ・ Jun 4 #devchallenge #frontendchallenge #javascript #css Thank you again to everyone who participated! We hope you had fun, felt challenged, and maybe added a thing or two to your professional profile. Interested in being a volunteer judge for future challenges? Learn more here ! Top comments (22) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Collapse Expand Peter Kim Frank The DEV Team Peter Kim Frank The DEV Team Peter Kim Frank Follow Doing a bit of everything at DEV / Forem Email peter@dev.to Education Wesleyan University Pronouns He/Him Work Co-Founder Joined Jan 3, 2017 • Jun 24 '25 Dropdown menu Copy link Hide Congrats @rensieeee , @tom_canfarotta_775a68254f , @async_dime ! Like comment: Like comment: 7 likes Like Comment button Reply Collapse Expand Adam Adam Adam Follow A curious being Location ~/ Pronouns He/ Him Joined Feb 18, 2019 • Jun 25 '25 Dropdown menu Copy link Hide Thanks @peter ! I'm incredibly honored to be chosen as a winner of the hackathon! Huge thanks to the dev.to team and everyone who participated. The creativity and talent in this community continues to inspire me to keep shipping. All the best. Like comment: Like comment: 3 likes Like Comment button Reply Collapse Expand Tom Canfarotta Tom Canfarotta Tom Canfarotta Follow Joined May 22, 2025 • Jun 24 '25 Dropdown menu Copy link Hide Thanks @peter ! This was a lot of fun! I’m looking forward to being an active member of the community! Like comment: Like comment: 3 likes Like Comment button Reply Collapse Expand Pravesh Sudha Pravesh Sudha Pravesh Sudha Follow AWS Community Builder Bridging critical thinking and innovation, from philosophy to DevOps. Email programmerpravesh@gmail.com Location India Education Hindu College, Delhi University, India Pronouns he/him Work Freelance DevOps Engineer At Fiverr Joined Jul 19, 2024 • Jun 24 '25 Dropdown menu Copy link Hide Congrats to all winner! Like comment: Like comment: 4 likes Like Comment button Reply Collapse Expand Matt Stavola Matt Stavola Matt Stavola Follow Joined Jun 5, 2025 • Jun 24 '25 Dropdown menu Copy link Hide Congrats to the winners-- when I saw PostmarkGBA I just knew it was going to get one of those spots. Incredible idea and absolutely brilliant execution. Like comment: Like comment: 4 likes Like Comment button Reply Collapse Expand Jess Lee The DEV Team Jess Lee The DEV Team Jess Lee Follow Building DEV and Forem with everyone here. Interested in the future. Email jess@forem.com Location USA / TAIWAN Pronouns she/they Work Co-Founder & COO at Forem Joined Jul 29, 2016 • Jun 24 '25 Dropdown menu Copy link Hide @mbstavola I thoroughly enjoyed Bolton's Vermont Distilling Company drama. Like comment: Like comment: 4 likes Like Comment button Reply Collapse Expand Bridget Amana Bridget Amana Bridget Amana Follow Just a curious frontend developer learning in public Location Lagos, Nigeria Pronouns She/Her Joined Jun 27, 2024 • Jun 24 '25 Dropdown menu Copy link Hide Congratulations to all winners Like comment: Like comment: 3 likes Like Comment button Reply Collapse Expand Nikoloz Turazashvili (@axrisi) Nikoloz Turazashvili (@axrisi) Nikoloz Turazashvili (@axrisi) Follow Founder & CTO at NikoLabs LLC, building Axrisi—an AI-powered browser extension for seamless on-page text processing and productivity. Opened Chicos restaurant in Tbilisi, Georgia. Email turazashvili@gmail.com Location Tbilisi, Georgia Education EXCELIA La Rochelle Pronouns He/Him Work Founder & CTO at NikoLabs LLC and Axrisi Joined May 30, 2025 • Jun 24 '25 Dropdown menu Copy link Hide congrats everyone! but I'm sad it's not mine :( tbh, I saw that my project received just 1 email from judges. for full test needed at least 3 to go through full customer journey, but well, i guess will do better next time :) Like comment: Like comment: 5 likes Like Comment button Reply Collapse Expand Robert Willson Robert Willson Robert Willson Follow Joined May 24, 2025 • Jun 25 '25 Dropdown menu Copy link Hide They didn't even test mine Like comment: Like comment: 7 likes Like Comment button Reply Collapse Expand Jack Qasim Jack Qasim Jack Qasim Follow Joined Jun 29, 2025 • Jun 29 '25 Dropdown menu Copy link Hide Congrats to all the Postmark Challenge: Inbox Innovators winners Like comment: Like comment: 1 like Like Comment button Reply Collapse Expand Nizzad Nizzad Nizzad Follow Data Scientist / AWS Certified (2X) ML Specialist | AWS ABW Grant Recipient '24 | 2 (Masters + Bachelors) | Researcher - NLP (Bias & Fairness) | Attorney-at-Law | Supervised 100+ Location Abu Dhabi, United Arab Emirates Education BIT (UOM), MSc in IT (SLIIT), MBA (SEUSL), LL.B (OUSL), Attorney-at-Law Pronouns He/Him Work Data Scientist, AI Engineer, Machine Learning Engineer, Research Supervisor Joined Jan 9, 2025 • Jun 25 '25 Dropdown menu Copy link Hide Congratulations for the winners and my appreciation for all the participants in the competition. Like comment: Like comment: 2 likes Like Comment button Reply Collapse Expand Fayaz Fayaz Fayaz Follow Software Engineer 𑁍 Thinker 𑁍 Problem Solver. Interests: AI, Software Development, Web Security, Privacy, Nature, Philosophy, History, Spirituality, Politics, Conversation. Location Bangladesh Education BSc. in Computer Science & Engineering Work Building a new SaaS Joined Nov 12, 2017 • Jun 24 '25 Dropdown menu Copy link Hide Congrats to all the winners! All cool projects! ❤️ Like comment: Like comment: 2 likes Like Comment button Reply Collapse Expand Dotallio Dotallio Dotallio Follow Joined Apr 7, 2025 • Jun 24 '25 Dropdown menu Copy link Hide Incredible ideas - turning email into a GBA gaming platform and a podcast feed is next level creativity! Has anyone here actually tried playing a game through their inbox? Like comment: Like comment: 3 likes Like Comment button Reply Collapse Expand Veríssimo Cassange Veríssimo Cassange Veríssimo Cassange Follow Developer passionate about technology, continuous learning, and building solutions that impact people and businesses. Sharing projects, ideas, and development experiences. Location Angola, Luanda Education ISTM - Computer Engineering Pronouns He/Him Work programmer at Vec corporation Joined Sep 24, 2020 • Jun 29 '25 Dropdown menu Copy link Hide Hi! Congrats to all the winners, amazing projects! 🎉 I just wanted to ask if all the submissions were reviewed. I submitted my project ( Postmark RAG Email Assistant 2.0 ) for the challenge, but I’m not sure if it was evaluated. I’d really appreciate any feedback, and thanks again for the opportunity! Like comment: Like comment: 1 like Like Comment button Reply Collapse Expand Rens Wolters Rens Wolters Rens Wolters Follow Enthousiastic and Entrepreneurial. I'm a back-end developer all the way, but enjoy building all kinds of stuff. Joined May 23, 2025 • Jun 24 '25 Dropdown menu Copy link Hide Thanks, and congratulations to the other winners as well! I had a lot of fun making this, and seeing people play and engage during this past month was awesome. Cheers to you! 🎉 Like comment: Like comment: 1 like Like Comment button Reply View full discussion (22 comments) Some comments may only be visible to logged-in visitors. Sign in to view all comments. Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse The DEV Team Follow The hardworking team behind DEV ❤️ Want to contribute to open source and help make the DEV community stronger? The code that powers DEV is called Forem and is freely available on GitHub. You're welcome to jump in! Contribute to Forem More from The DEV Team Congrats to the AI Agents Intensive Course Writing Challenge Winners! # googleaichallenge # devchallenge # ai # agents Join the Algolia Agent Studio Challenge: $3,000 in Prizes! # algoliachallenge # devchallenge # agents # webdev Congrats to the Xano AI-Powered Backend Challenge Winners! # xanochallenge # backend # api # ai 💎 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 | 2026-01-13T08:49:33 |
https://kafka.apache.org/ | Apache Kafka Get Started Introduction Quickstart Use Cases Books and Papers Videos Podcasts Docs Key Concepts APIs Configuration Design Implementation Operations Security Clients Kafka Connect Kafka Streams Powered By Community Blog Kafka Summit Project Info Trademark Ecosystem Events Contact Us Apache Apache.org License Donate Sponsors Security Privacy Releases 4.1 4.0 3.9 3.8 3.7 3.6 3.5 3.4 3.3 3.2 3.1 3.0 2.8 2.7 2.6 2.5 2.4 2.3 2.2 2.1 2.0 1.1 1.0 0.11.0 0.10.2 0.10.1 0.10.0 0.9.0 0.8.2 0.8.1 0.8.0 0.7 DOWNLOAD KAFKA Learn More Download More than 80% of all Fortune 100 companies trust, and use Apache Kafka. Apache Kafka Apache Kafka is an open-source distributed event streaming platform used by thousands of companies for high-performance data pipelines, streaming analytics, data integration, and mission-critical applications. Manufacturing 10 OUT OF 10 Banks 7 OUT OF 10 Insurance 10 OUT OF 10 Telecom 8 OUT OF 10 Transportation 8 OUT OF 10 Energy and Utilities 10 OUT OF 10 Above is a snapshot of the number of top-ten largest companies using Kafka, per-industry. See full list Core capabilities Kafka boasts core capabilities that are battle tested and ready to power businesses in the digital world. High Throughput Deliver messages at network limited throughput using a cluster of machines with latencies as low as 2ms. Scalable Scale production clusters up to a thousand brokers, trillions of messages per day, petabytes of data, hundreds of thousands of partitions. Elastically expand and contract storage and processing. Permanent Storage Store streams of data safely in a distributed, durable, fault-tolerant cluster. High Availability Stretch clusters efficiently over availability zones or connect separate clusters across geographic regions. Built-in Stream Processing Process streams of events with joins, aggregations, filters, transformations, and more, using event-time and exactly-once processing. Connect to almost anything Kafka’s out-of-the-box Connect interface integrates with hundreds of event sources and event sinks including Postgres, JMS, Elasticsearch, AWS S3, and more. Trust and Ease of Use Kafka is simple to use and is trusted by thousands of organizations around the world. Mission Critical Support mission-critical use cases with guaranteed ordering, zero message loss, and efficient exactly-once processing. Trusted By Thousands of Orgs Thousands of organizations use Kafka, from internet giants to car manufacturers to stock exchanges. More than 5 million unique lifetime downloads. Vast User Community Kafka is one of the five most active projects of the Apache Software Foundation, with hundreds of meetups around the world. Client Libraries Read, write and process streams of events in a vast array of programming languages. Rich Online Resources Rich documentation, online training, guided tutorials, videos, sample projects, Stack overflow, etc. Large Ecosystem Open Source Tools Large ecosystem of open source tools: Leverage a vast array of community-driven tooling. The contents of this website are © 2026 Apache Software Foundation under the terms of the Apache License v2 . Apache Kafka, Kafka, and the Kafka logo are either registered trademarks or trademarks of The Apache Software Foundation in the United States and other countries. Security | Donate | Thanks | Events | License | Privacy | 2026-01-13T08:49:33 |
https://www.fine.dev/blog/captive-portal#why-do-we-need-raspap-for-a-captive-portal | Creating a Custom Captive Portal for Home WiFi with Raspberry Pi and AI Magic Home Docs Changelog Pricing Sign in Get started -> Menu Home Docs Changelog Pricing <- Go Back Creating a Custom Captive Portal for Home WiFi with Raspberry Pi and AI Magic Table of Contents What is a Captive Portal? Capabilities of a Captive Portal You Will Need Why Raspberry Pi? RaspAP: Simplifying WiFi Management Why Do We Need RaspAP for a Captive Portal? Why Is an Ethernet Cable Needed? Introduction to Nodogsplash Customizing the Splash Page Generating a Stunning Splash Page Image Customizing HTML & CSS with Fine’s AI Agents Test Your Customized Page Final Words Ever wondered about the magic behind those WiFi login pages that greet you at places like Starbucks? You know the drill – you sip your coffee, pull out your laptop or smartphone, connect to the WiFi, and voilà! Suddenly, you're redirected to a page where you need to log in or accept terms before diving into the digital realm. It's a seamless experience we've all grown accustomed to, but have you ever thought about creating one yourself? Well, probably not. But I did! And there’s a good reason why. I live on Ruppin Street, and as a joke, I call my apartment the “Royal Ruppin Relax” as if it was some kind of boutique hotel. I wanted to create my own customized WiFi login portal so that guests at my home would get a surprise when they log in. That's what we're diving into today: In this tutorial, I’ll show you how to build and customize your own captive portal – a digital gateway that not only controls access but also acts as a canvas for your creativity and a great conversation starter! With a Raspberry Pi and a bit of AI magic, you can transform your mundane WiFi login into an engaging, personalized experience. But First, What is a Captive Portal? The term might sound technical, but in essence, it's the official name for those login pages you encounter when connecting to a public WiFi network. Most captive portals are like virtual gatekeepers, ensuring that only authorized users gain access to a WiFi network. But this interface can be a powerful tool, not just for authentication, but also for conveying information and engaging users creatively. Capabilities of a Captive Portal: Authentication : Captive portals authenticate users by prompting them to enter login credentials or accept terms and conditions. This process ensures that the network is used responsibly and securely. Customization : One of the features of a captive portal is its customization potential. Businesses often use captive portals to showcase their branding, display advertisements, or provide essential information. Access Control : Captive portals enable administrators to control the type of access users have to the internet. For instance, they can restrict certain websites, limit bandwidth, or provide different levels of access based on user roles. So technically, you can configure it such that your devices are prioritized bandwidth-wise on your WiFi network, but that’s up to you. 😉 Now, let's move forward and create our own captivating captive portal. The creative journey begins! You Will Need: Before we dive into creating your personalized captive portal, let's gather the essentials: Raspberry Pi : The heart of your project, this versatile microcomputer will serve as the central hub for your captive portal setup. MicroSD Card : You'll need a microSD card (at least 16GB) to store the operating system and other necessary files. Power Supply : Ensure you have a compatible power supply for your Raspberry Pi to keep it running smoothly. Ethernet Cable : You'll require an Ethernet cable to establish a wired connection between your Raspberry Pi and your internet router. Why Raspberry Pi? In the landscape of network devices, not all routers are created equal. Many standard routers lack native support for captive portals, making it challenging to implement this feature seamlessly. When faced with this limitation, we turn to Raspberry Pi as a solution. This credit-card-sized, affordable computer will allow you to run complementary network-related software and overcome the constraints of your existing router. If you've never used your Raspberry Pi before, set it up according to the [simple instructions on the official website]( https://www.raspberrypi.com/documentation/computers/getting-started.html ). Our next step would be installing RaspAP. RaspAP: Simplifying WiFi Management Now that you have your Raspberry Pi ready, it's time to introduce RaspAP. RaspAP is an open-source software that simplifies the process of setting up a WiFi access point on your Raspberry Pi. Think of it as the bridge between your Raspberry Pi and the devices that will connect to your WiFi. [To install RaspAP, simply follow the instructions on the official website]( https://raspap.com/#quick ). Why Do We Need RaspAP for a Captive Portal? To create a captive portal, we need a WiFi network that's entirely under our control. RaspAP allows you to do just that: while Raspberry Pi provides the hardware backbone, RaspAP adds the user-friendly interface, making it incredibly easy to configure your WiFi network settings. You can customize the network name (SSID), set up passwords, and manage the connection preferences. RaspAP handles the complexities of access points, security protocols, and IP addresses, ensuring that the WiFi network your guests connect to operates smoothly and securely. Why Is an Ethernet Cable Needed? You might be wondering about the necessity of an Ethernet cable in a wireless setup. When you connect your Raspberry Pi to your router using an Ethernet cable, you establish a stable, wired connection. This wired connection serves as the foundation upon which you'll build your customized WiFi network. Introduction to Nodogsplash Now that you've set up your WiFi access point with RaspAP, it's time to introduce Nodogsplash into the mix. Nodogsplash is a high-performance Captive Portal and the key player in bringing our idea to life. Nodogsplash offers by default a simple splash page that we will customize later. Install and configure Nodogsplash by following the easy tutorial on RaspAP’s official documentation. If you are successful, you will see this page: Nodogsplash Customizing the Splash Page Here comes the exciting part! Now we will customize the captive portal page to our liking. Customizing the splash page might seem like a challenging task for two reasons: Nodogsplash Rules : Nodogsplash has specific rules that the splash page must adhere to, ensuring functionality. Deviating from these rules might result in our captive portal not working, making it crucial to comply with them. CDCs Force Us to Work with HTML and CSS Only, No JS : A CDC (Captive Detection Client) is a component in operating systems or devices that helps in detecting whether a network has a captive portal. When a device connects to a WiFi network, the CDC functionality checks if the network connection is restricted by a captive portal. If it detects a captive portal, the device redirects the user to the portal's login or authentication page. Most of the CDCs don’t allow JS or even href s, so we will have to work with HTML and CSS only to make a beautiful captive portal. Manipulating HTML & CSS requires a good understanding of their syntax, making customization challenging for many users. To overcome these challenges, we will use some ✨ AI magic ✨. Generating a Stunning Splash Page Image First, we will obtain a stunning boutique hotel picture with Leonardo AI: an innovative tool that generates realistic and visually appealing images from prompts. Here’s how you can use it: [Visit Leonardo AI : Go to the Leonardo AI website and click on “AI Image Generation”]( https://leonardo.ai/ ). Generate Your Image : Using Leonardo AI's intuitive interface, generate an image that resonates with your captive portal's ambiance. You can tweak various settings until you find the perfect image. My prompt was: “A beautiful boutique hotel next to the sea, palms and luxurious atmosphere, beautiful day”. Download Your Image : Once satisfied with the generated image, download it to your computer. This stunning visual will serve as the backdrop for your customized splash page. Customizing HTML & CSS with Fine’s AI Agents Now that we have the image, we can customize the default HTML and CSS. To do that we will use Fine’s AI agents, which can quickly get us to the point: Deploy an HTML Agent to Your Workspace : Open Fine and click “Deploy Agent”. Upload the YAML file of the HTML Agent, found [here]( https://github.com/finehq/fine/blob/main/html-agent/html-agent.yml ). This agent specializes in HTML and CSS tasks. Create a Project : Place the default Nodogsplash files in a folder, together with your generated image. Run git init inside the folder and then add it as a new project to Fine. Create a Notebook and Specify the Changes You Want to Make : The agents work according to a plan specified in a notebook. I wrote a short description of my wanted task and connected the notebook to the project. Run the Agent and Make Some Final Tweaks : The agent will start changing the HTML and CSS pages according to the specifications in your notebook. If it isn’t exactly to your liking, make the final changes and that’s it! With Fine’s AI agents, the process of customizing your splash page becomes intuitive and efficient. You don’t need to deal with HTML and CSS, and you don’t need to learn the rules of Nodogsplash. You easily transform a basic login interface into a visually appealing and engaging portal that captivates users, providing a memorable WiFi experience. Test Your Customized Page After Fine generates the code, test your customized splash page. To do that, upload your files to the Raspberry Pi and replace the default splash page files in /etc/Nodogsplash/htdocs/ . Ensure that it complies with Nodogsplash rules and provides a seamless user experience. Make any necessary adjustments until you achieve the desired result. Final Words By integrating Raspberry Pi, RaspAP, Nodogsplash, Fine, and Leonardo AI, you've not only created a functional captive portal but also unleashed your creativity without the headache of coding intricacies. This project not only enhances your technical skills but also transforms your WiFi experience at home. Feel free to experiment further and explore the endless possibilities of customization, all thanks to the power of innovative AI technology. Now it's your turn to improve your home WiFi experience! Get creative, get connected, and let your imagination run wild – AI will take care of the rest! Start building today Try out the smoothest way to build, launch and manage an app Try for Free -> © Fine.dev - All rights reserved. Product Overview AI Workflows Pricing & Plans Changelog Blog Docs Company Press Terms & Conditions Privacy policy | 2026-01-13T08:49:33 |
https://docs.devcycle.com/platform/feature-flags/status-and-lifecycle#managing-statuses | Status and Lifecycle | DevCycle Docs Skip to main content Home SDKs APIs Management API Bucketing API Integrations CLI / MCP Best Practices Community Blog Discord Search Sign Up Home Getting Started Essentials DevCycle Overview Key Features System Architecture Feature Hierarchy Feature Types Platform Feature Flags Features Variables and Variations Targeting Status and Lifecycle Stale Feature Notifications Experimentation Account Management Security and Guardrails Testing and QA Extras Examples Platform Feature Flags Status and Lifecycle On this page Feature Status and Lifecycle Management In DevCycle, Features have Statuses that indicate their current position in the feature lifecycle. Statuses provide a clear, at-a-glance understanding of where a Feature is in its development, release, and cleanup process. Each Status belongs to a Status Category , which defines how the Feature behaves, what actions are allowed, and how it is displayed across the dashboard. Statuses Every Feature in DevCycle always has one Status , which determines its lifecycle stage. By default, DevCycle provides a set of predefined Statuses aligned to core lifecycle categories. The default Statuses are: Development Live Completed Archived In addition to the default Statuses, teams can define custom Statuses within their Project settings. This allows teams to better align Feature lifecycle tracking with their internal development and release processes while preserving DevCycle's lifecycle guarantees. Each custom Status inherits the behavior of their Category. Status changes are not automatic and are always managed explicitly by the user. Status Categories Statuses are grouped into Categories , which define shared lifecycle behavior. Development This Category represents Features that are actively being built, tested, or prepared for release. By default, new Features are created with the Development Status. While a Feature is in Development, all Targeting rules and Variations remain editable. This stage is typically used while work is ongoing and before a Feature is considered ready for a broader release. Below are some examples of different Statuses that would make sense in the Development Category: In Development Pending Design QA Internal Testing Live The Live Category represents Features that are actively running in production or being exposed to users. While a Feature is Live, all Targeting rules and Variations remain editable. Below are some examples of different Statuses that would make sense in the Live Category: Beta Ramping In Production Live Experiment Completed The Completed Category represents Features that have reached the end of active development and rollout. A Feature may be considered Completed once it has been tested, approved, and is fully released, or when no further targeting changes are expected. When a Feature is moved into a Status within the Completed Category, it enters a semi-read-only state : A single final (release) Variation must be selected All Environments will serve this Variation to all users Targeting rules are replaced with an "All users" rule New targeting rules and Variations cannot be added Variable values may still be edited Environments can still be toggled on or off When using the CLI to generate TypeScript types, Variables belonging to a Feature in the Completed Category will be marked as deprecated . Below are some examples of different Statuses that would make sense in the Completed Category: Ready for Cleanup All Users Enabled Stable Release Cleanup Checklist Upon entering a Completed Status, a cleanup checklist is shown for each Variable associated with the Feature. This checklist helps teams determine when it is safe to remove Variables from their codebase or archive them. If a Variable is still referenced in code or evaluated in production, removing it may result in default values being served. If Code References are enabled, additional context will be provided to assist with cleanup. Archived The Archived Category represents the terminal lifecycle state for Features. This Category and Status cannot be edited or changed. A Feature should be archived once it has been fully cleaned up and its Variables have been removed from the codebase. When a Feature is Archived: It becomes fully read-only It is hidden from standard dashboard views Audit Logs remain accessible for historical reference Metrics & Reach data will not be visible on the dashboard for Archived features Archiving Features helps keep both your dashboard and codebase clean while preserving valuable lifecycle history. Note: Feature deletion still exists, but should only be used for mistakes. Deleting a Feature permanently removes it and its Audit Log. Archived Features retain historical data that may be used for future reporting and analysis. Changing Status Moving a Feature to Completed When a Feature is moved into the Completed Category: A final Variation must be selected All Environments serve that Variation to all users Existing Environment statuses are preserved Targeting rules are replaced with a single "All users" rule Additional Variations and targeting rules are locked Reverting to Development or Live Features in the Completed Category can be reverted back to an earlier Status. When reverting: Previous Variations become available again Changes made to Variable values while Completed are retained Prior targeting rules are not restored and must be reconfigured Viewing Features by Status (Kanban View) On the Feature list page, users can switch between a List view and a Kanban-style view that displays Features grouped by their current Status, allowing teams to quickly visualize progress across the Feature lifecycle. In this view: Each column represents a Feature Status Each column header includes a total count of Features in each Status Features appear as cards within the column matching their current Status, and can be sorted differently by selected criteria Columns are ordered based on the Status order defined in Project Settings Status colors are reflected in the column headers for quick visual scanning This view is intended for high-level lifecycle tracking and workflow management. Selecting a Feature card opens the Feature detail view for configuration, targeting, and Variable management. Managing Statuses Statuses are managed at the Project level and apply to all Features within that Project. Each Project starts with a default set of Statuses aligned to DevCycle's lifecycle categories. Teams may customize these Statuses to better reflect their internal workflows. Project Settings Statuses can be viewed and managed from the Project Settings page under the Feature Statuses section. From this page, users can: View all Statuses grouped by Category Create new custom Statuses within supported Categories Edit existing Status names (Note: each Status must have a unique key) Reorder Statuses within a Category Assign colors to Statuses for quick visual identification Add a description to provide context behind what a Status represents Select the default Status applied when a new Feature is created Changes made in Project Settings take effect immediately and apply across the Project. Status Categories and Rules Statuses must belong to one of DevCycle's predefined Categories. The following rules apply: New Categories cannot be created Each Category must contain at least one Status The last remaining Status in a Category cannot be deleted Status labels and ordering within a Category can be modified Permissions for Status Changes Permission Rules When permissions are enabled: Statuses in the Development and Live Categories can be applied by any user with access to the Project Statuses in the Completed and Archived Categories can only be applied by users with the Publisher permission Only Publishers can create, and modify Feature Statuses in the Project Settings Edit this page Last updated on Jan 9, 2026 Previous EdgeDB (Stored Custom Properties) Next Stale Feature Notifications Statuses Status Categories Development Live Completed Archived Changing Status Moving a Feature to Completed Reverting to Development or Live Viewing Features by Status (Kanban View) Managing Statuses Project Settings Permissions for Status Changes DevCycle Dashboard Blog Privacy Policy Twitter Discord GitHub Copyright © 2026 DevCycle. All rights reserved. | 2026-01-13T08:49:33 |
https://dev.to/t/rust/videos#main-content | Videos - 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 All videos # rust on Video 00:23 windows-contextmenu-manager 阿豪 07:05 Chain Abstraction - Etherspot Pulse Demo Alexandra 00:55 I made a tool in Rust to play mechanical keyboard sounds on every key press Kunal Bagaria 45:43 Database Architecture - TerminusDB Discussion #14 Cheuk Ting Ho 🐍 38:47 The Rise of Functional Programming - TerminusDB Discussion #7 Cheuk Ting Ho 🐍 29:52 Terminators on Tech - TerminusDB Internals Cheuk Ting Ho 🐍 26:24 Livestream - Dev.to Challenge Vowel Count in Rust Corey Alexander 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 | 2026-01-13T08:49:33 |
https://docs.devcycle.com/platform/feature-flags/status-and-lifecycle#theme-svg-external-link | Status and Lifecycle | DevCycle Docs Skip to main content Home SDKs APIs Management API Bucketing API Integrations CLI / MCP Best Practices Community Blog Discord Search Sign Up Home Getting Started Essentials DevCycle Overview Key Features System Architecture Feature Hierarchy Feature Types Platform Feature Flags Features Variables and Variations Targeting Status and Lifecycle Stale Feature Notifications Experimentation Account Management Security and Guardrails Testing and QA Extras Examples Platform Feature Flags Status and Lifecycle On this page Feature Status and Lifecycle Management In DevCycle, Features have Statuses that indicate their current position in the feature lifecycle. Statuses provide a clear, at-a-glance understanding of where a Feature is in its development, release, and cleanup process. Each Status belongs to a Status Category , which defines how the Feature behaves, what actions are allowed, and how it is displayed across the dashboard. Statuses Every Feature in DevCycle always has one Status , which determines its lifecycle stage. By default, DevCycle provides a set of predefined Statuses aligned to core lifecycle categories. The default Statuses are: Development Live Completed Archived In addition to the default Statuses, teams can define custom Statuses within their Project settings. This allows teams to better align Feature lifecycle tracking with their internal development and release processes while preserving DevCycle's lifecycle guarantees. Each custom Status inherits the behavior of their Category. Status changes are not automatic and are always managed explicitly by the user. Status Categories Statuses are grouped into Categories , which define shared lifecycle behavior. Development This Category represents Features that are actively being built, tested, or prepared for release. By default, new Features are created with the Development Status. While a Feature is in Development, all Targeting rules and Variations remain editable. This stage is typically used while work is ongoing and before a Feature is considered ready for a broader release. Below are some examples of different Statuses that would make sense in the Development Category: In Development Pending Design QA Internal Testing Live The Live Category represents Features that are actively running in production or being exposed to users. While a Feature is Live, all Targeting rules and Variations remain editable. Below are some examples of different Statuses that would make sense in the Live Category: Beta Ramping In Production Live Experiment Completed The Completed Category represents Features that have reached the end of active development and rollout. A Feature may be considered Completed once it has been tested, approved, and is fully released, or when no further targeting changes are expected. When a Feature is moved into a Status within the Completed Category, it enters a semi-read-only state : A single final (release) Variation must be selected All Environments will serve this Variation to all users Targeting rules are replaced with an "All users" rule New targeting rules and Variations cannot be added Variable values may still be edited Environments can still be toggled on or off When using the CLI to generate TypeScript types, Variables belonging to a Feature in the Completed Category will be marked as deprecated . Below are some examples of different Statuses that would make sense in the Completed Category: Ready for Cleanup All Users Enabled Stable Release Cleanup Checklist Upon entering a Completed Status, a cleanup checklist is shown for each Variable associated with the Feature. This checklist helps teams determine when it is safe to remove Variables from their codebase or archive them. If a Variable is still referenced in code or evaluated in production, removing it may result in default values being served. If Code References are enabled, additional context will be provided to assist with cleanup. Archived The Archived Category represents the terminal lifecycle state for Features. This Category and Status cannot be edited or changed. A Feature should be archived once it has been fully cleaned up and its Variables have been removed from the codebase. When a Feature is Archived: It becomes fully read-only It is hidden from standard dashboard views Audit Logs remain accessible for historical reference Metrics & Reach data will not be visible on the dashboard for Archived features Archiving Features helps keep both your dashboard and codebase clean while preserving valuable lifecycle history. Note: Feature deletion still exists, but should only be used for mistakes. Deleting a Feature permanently removes it and its Audit Log. Archived Features retain historical data that may be used for future reporting and analysis. Changing Status Moving a Feature to Completed When a Feature is moved into the Completed Category: A final Variation must be selected All Environments serve that Variation to all users Existing Environment statuses are preserved Targeting rules are replaced with a single "All users" rule Additional Variations and targeting rules are locked Reverting to Development or Live Features in the Completed Category can be reverted back to an earlier Status. When reverting: Previous Variations become available again Changes made to Variable values while Completed are retained Prior targeting rules are not restored and must be reconfigured Viewing Features by Status (Kanban View) On the Feature list page, users can switch between a List view and a Kanban-style view that displays Features grouped by their current Status, allowing teams to quickly visualize progress across the Feature lifecycle. In this view: Each column represents a Feature Status Each column header includes a total count of Features in each Status Features appear as cards within the column matching their current Status, and can be sorted differently by selected criteria Columns are ordered based on the Status order defined in Project Settings Status colors are reflected in the column headers for quick visual scanning This view is intended for high-level lifecycle tracking and workflow management. Selecting a Feature card opens the Feature detail view for configuration, targeting, and Variable management. Managing Statuses Statuses are managed at the Project level and apply to all Features within that Project. Each Project starts with a default set of Statuses aligned to DevCycle's lifecycle categories. Teams may customize these Statuses to better reflect their internal workflows. Project Settings Statuses can be viewed and managed from the Project Settings page under the Feature Statuses section. From this page, users can: View all Statuses grouped by Category Create new custom Statuses within supported Categories Edit existing Status names (Note: each Status must have a unique key) Reorder Statuses within a Category Assign colors to Statuses for quick visual identification Add a description to provide context behind what a Status represents Select the default Status applied when a new Feature is created Changes made in Project Settings take effect immediately and apply across the Project. Status Categories and Rules Statuses must belong to one of DevCycle's predefined Categories. The following rules apply: New Categories cannot be created Each Category must contain at least one Status The last remaining Status in a Category cannot be deleted Status labels and ordering within a Category can be modified Permissions for Status Changes Permission Rules When permissions are enabled: Statuses in the Development and Live Categories can be applied by any user with access to the Project Statuses in the Completed and Archived Categories can only be applied by users with the Publisher permission Only Publishers can create, and modify Feature Statuses in the Project Settings Edit this page Last updated on Jan 9, 2026 Previous EdgeDB (Stored Custom Properties) Next Stale Feature Notifications Statuses Status Categories Development Live Completed Archived Changing Status Moving a Feature to Completed Reverting to Development or Live Viewing Features by Status (Kanban View) Managing Statuses Project Settings Permissions for Status Changes DevCycle Dashboard Blog Privacy Policy Twitter Discord GitHub Copyright © 2026 DevCycle. All rights reserved. | 2026-01-13T08:49:33 |
https://www.fine.dev/blog/build-scalable-tech-infrastructure-for-startups#automate-early | How to Build a Scalable Tech Infrastructure on a Startup Budget: A Step-by-Step Guide for CTOs Home Docs Changelog Pricing Sign in Get started -> Menu Home Docs Changelog Pricing <- Go Back How to Build a Scalable Tech Infrastructure on a Startup Budget: A Step-by-Step Guide for CTOs Building a scalable tech infrastructure on a startup budget requires creativity and prioritization. As a CTO, you need to grow infrastructure without exhausting resources. This guide outlines steps to help your tech stack expand with your user base, without financial strain. Table of Contents Start with Open-Source Solutions Use Cloud Services Wisely Modular Architecture Automate Early Think Lean—Build for Your Current Needs Monitoring and Alerts Outsource Non-Critical Components Leverage Community and Startup Programs Scalable Data Management Prepare for Growth with a Flexible Mindset Look for Integrations Ready to Scale with Ease? 1. Start with Open-Source Solutions When budget is tight, opting for open-source software can be a game-changer. Open-source solutions often provide the flexibility you need to get started without the licensing fees associated with proprietary systems. Tools like PostgreSQL for databases, Kubernetes for orchestration, and Apache Kafka for data streaming can all be incredibly effective without incurring high costs. can all be incredibly effective without incurring high costs. The initial learning curve might be steep, but the savings are well worth it. There's also a whole community out there to help you. 2. Use Cloud Services Wisely The allure of cloud services like AWS , Google Cloud , or Azure is real—scalability, reliability, and global availability. However, these services can become expensive if not optimized. Start small by utilizing free tiers and cost calculators. Identify the essential cloud resources you need, and always keep an eye on your billing dashboard. Consider using cloud credits, which are often available for startups through accelerator programs.. 3. Modular Architecture Adopting a modular architecture allows you to build components that can be independently scaled or replaced. By separating services (e.g., microservices or serverless functions), you gain the flexibility to scale certain parts of your infrastructure as needed, instead of the entire system. This approach can help you save on unnecessary costs and avoid a complete overhaul when scaling. 4. Automate Early Automation saves both time and money. Implement CI/CD pipelines to automate testing, deployment, and code integration. This not only reduces manual effort but also helps you ship faster without additional costs. Tools like Jenkins , GitLab CI , or GitHub Actions are great options that won't break the bank, and they help maintain quality control as your team expands. that won't break the bank, and they help maintain quality control as your team expands. They can also work together with Fine, to ensure that you not only have a robust set of tests that constantly run, but any failures are turned into fixes at maximum speed. 5. Think Lean—Build for Your Current Needs Avoid the temptation to over-engineer your infrastructure based on hypothetical future requirements. Focus on building for your current needs, but keep scalability in mind. You want something that’s "scale-ready" without being bloated. An MVP-style infrastructure should focus on the most crucial features that will support immediate growth and customer acquisition. 6. Monitoring and Alerts Establishing a simple monitoring system will help you identify issues before they impact users. Open-source tools like Prometheus and Grafana allow you to keep an eye on system performance and resource usage. on system performance and resource usage. Effective monitoring helps you make informed decisions on scaling—such as when it's truly necessary to increase server capacity. 7. Outsource Non-Critical Components To keep your internal team focused on core competencies, consider outsourcing non-critical functions, like hosting static assets or even customer support. Managed services can help reduce overhead. For example, Firebase can handle authentication and real-time data syncing, allowing your developers to focus on core product features instead of worrying about server maintenance. 8. Leverage Community and Startup Programs Many tech giants offer generous startup programs, including cloud credits, free tools, and discounted software licenses. Amazon Activate , Microsoft for Startups , and Google for Startups are programs that can provide significant cost savings in the early stages. that can provide significant cost savings in the early stages. Engage with tech communities like Stack Overflow and GitHub as well, where you can access free resources and advice. 9. Scalable Data Management Data is at the core of most tech businesses, but managing it can quickly become expensive if not done wisely. Start with cost-effective databases like PostgreSQL or NoSQL options like MongoDB, depending on your needs. As your data needs grow, consider partitioning, archiving older data, and using data warehouses only when it makes sense. 10. Prepare for Growth with a Flexible Mindset Scalability is about more than technology; it's about mindset. Regularly evaluate whether your tech stack is meeting your current needs and where you might face constraints as you grow. Flexibility in choosing tools, hiring, and decision-making will allow you to scale smoothly when your startup hits growth phases. 11. Look for integrations Where platforms offer similar features, integrations with your existing tech stack can often be the deciding factor. The more your platforms can talk to each other and automate tasks, the better for your growth. Fine works with a variety of platforms to build a knowledge graph and complement your natural workflows, making it the premier AI choice for many scaling startups. Ready to Scale with Ease? Consider using Fine to make your infrastructure scalable and efficient. Fine offers advanced AI capabilities that help automate testing, code integration, and debugging, allowing your team to focus on core development without getting bogged down in manual tasks. Start building today Try out the smoothest way to build, launch and manage an app Try for Free -> © Fine.dev - All rights reserved. Product Overview AI Workflows Pricing & Plans Changelog Blog Docs Company Press Terms & Conditions Privacy policy | 2026-01-13T08:49:33 |
https://docs.devcycle.com/platform/experimentation/feature-experimentation/ | Feature Experimentation | DevCycle Docs Skip to main content Home SDKs APIs Management API Bucketing API Integrations CLI / MCP Best Practices Community Blog Discord Search Sign Up Home Getting Started Essentials DevCycle Overview Key Features System Architecture Feature Hierarchy Feature Types Platform Feature Flags Experimentation Feature Experimentation Creating and Managing Metrics How Metrics are Calculated Video Tutorial: Experiment Setup Tutorial: Funnel Experiment Account Management Security and Guardrails Testing and QA Extras Examples Platform Experimentation Feature Experimentation On this page Feature Experimentation Overview At DevCycle we believe that Experimentation should be a part of the natural lifecycle of all Features. So no matter the Feature type selected, can be experimented on. Experiments can be as simple as comparing any target audiences against a Metric, or can be fully randomized A/B tests using statistical methodologies. This article outlines why and how to run and analyze Experiments on your Features within DevCycle. Why Experiment Experimentation is crucial for testing modifications to your product. You may investigate which changes would result in the best outcomes. It's also known as split testing or A/B testing, or comparative analysis depending on who you ask. Experimentation can be used to test new Features, design changes, marketing campaigns, or anything that could potentially impact how a product or service is used. You may want to experiment on any of these things and more: Validate to make sure application performance remains the same or improves. Validate in a controlled way whether code changes increase or decrease error rates. Confirm that a new Feature is driving more conversions or revenue. Measure real impacts of Features on SLAs and SLOs. You've likely been doing "Experimentation" without knowing it. Whenever you release a new feature or service, compare the before and after (and during). When combined with Features, DevCycle can give direct Metrics on a feature's performance during a release, allowing you to react and make changes accordingly. Of course, with this in mind, your team isn't restricted to a simple on or off approach. Using DevCycle, a team can have numerous Variations which are released and tested at the same time, giving an even deeper view with more flexibility. Using Experimentation To run an Experiment on any Feature, all you need is two things: At least two Variations served to your users At least one Metric defined and attached to your Feature Comparing Multiple Variations The primary concept of an Experiment is the need to have at least two different experiences to compare performances. There are several ways in DevCycle to run multiple experiences for users. We go into depth on this in our Targeting documentation . To get started with your first Feature Experiment, it is best to keep it simple and run a basic A/B test comparing two Variations, one control and one treatment Variation, delivered randomly to all your users. To set this up, create a targeting rule in Production that delivers to All Users and serves Variations randomly with percentages set equally at 50% against your first Variation, and 50% against your second Variation. Adding Metrics to Your Feature info Experimentation relies on Custom Events . Experimentation is available to all customers on any plan. However, to perform Experiments, events must be sent to DevCycle to calculate Metrics. These events are added to your existing plan. To learn more, read about our pricing , or contact us. Now that you have two segments receiving different experiences, the only other thing you need to run an Experiment is a Metric to evaluate the comparative performance of those experiences. To add a Metric to your Feature, click “Experiment Results” under the “Data & Results” section on the sidebar of the Feature editing page. Click the “Choose a Metric” dropdown. This will bring up the option to add a Metric that has already been created in the Project or to create a new one. For the creation of new Metrics check out our documentation here . Once you have Metrics in your Project, all you need to do is: Select a Metric you want to use to judge the performance of your Experiment Set the Variation that you want to use as your control Variation Now that you have a Metric added and a control Variation selected, the performance of the Experiment will be tracked over time. The performance of the treatment Variation compared to the control Variation will be tracked by the Difference and Statistical Significance indicator in real-time as the Experiment progresses. Any number of Metrics can be added to a Feature for analysis, keep clicking “Choose a Metric” and add pre-existing or create new Metrics as needed. Determining a Winner The most important part of an Experiment is determining a winner. The length of time an Experiment needs to run to determine a winner varies depending on the overall traffic, the observed conversion rate, and the size of the difference in conversion or values between the Variations. Typically Experiments should be run for a minimum of 1-2 weeks to achieve valid statistical significance with a good amount of time to get a proper cross-section of your user base. Given the time it takes, your team should generally avoid early analysis and create a process by which an Experiment runs with no review of results until a pre-determined amount of time has passed. Once this time has passed, the charts and graphs for any added Metrics can be reviewed to determine which Variation performed best. When Metrics are created, you define if a decrease or an increase is the targeted improvement. Our results graphs take this into account and show clearly if the Metrics have driven either positive or negative results. The charts also provide guidance on if statistical significance has been achieved by displaying the following indicators. Statistical Significance Definition ✅ Positive Significant Result ❌ Negative Significant Result ... Non-Significant Result Positive Results Negative Results Experimentation using a Custom Property for Randomization info For documentation on this functionality outside of the context of experimentation you can check out our documentation dedicated to this topic here . DevCycle typically uses the User ID as the primary key for Feature rollouts and randomization. However, in certain scenarios, Features you release are intended to be rolled out to a cohort of users vs an individual user. For example, a new feature in a B2B platform might impact an entire Organization rather than a single user within that Organization. In such cases, you can randomize and rollout by using a Custom Property. What are Experiments that Randomize Using a Custom Property? When running an Experiment where you randomize using a Custom Property, the Experiment is applied to a set of users (those who possess a Custom Property) rather than individual users. This means that every user who has that Custom Property will experience the same Feature Variation, such as being part of the control or the test variant. This approach allows you to assess the impact of changes on the group as a whole. Groups in DevCycle are defined using Custom Properties. These groups could be companies, tenants, geographic locations, or any set of users sharing common characteristics. How to Randomize Using a Custom Property in Experiments To set this up, create a Targeting Rule that serves a Random Distribution of the Variations. When you select Random Distribution , Randomize Using field will appear at the bottom of the Targeting Rule under the Schedule section. The dropdown will populate with all existing Custom Properties. Select the Custom Property you wish to use for your random distribution. If you are both randomizing distribution and using a gradual rollout of some form, the Custom Property will be used for both forms of randomization, keeping distribution sticky based off of that property. Risks to Experimentation There are several risks to be aware of when randomizing your Experiments in this way: Less Statistical Power: In Experiments with randomization using a Custom Property, each group is treated as a single data point, reducing the overall statistical power of the Experiment. For example, a platform might have millions of users but only a few thousand companies using it. This typically requires running these types of Experiments for a longer period to achieve statistically significant results. Higher Randomization Risk: There's a greater risk of improper randomization when assigning Custom Properties to control or test variants. With fewer data points, any imbalance can significantly skew the results. For example, if a new pricing model is tested across different companies, an imbalance in the distribution of company sizes could lead to inaccurate conclusions about the model’s effectiveness. Fewer User-Level Insights: Custom Property-targeted Experiments provide insights at an aggregate level, potentially obscuring user-level behaviors and preferences. For example, a new feature might increase overall usage within a company, but it might not reveal which specific roles or user types are most engaged with the feature. Randomization Collisions: Our random distribution system works on a murmurhash, where we purposely limit User IDs to less than 200 characters to reduce the risk of collisions. If you randomize off of a Custom Property where the values are over 200 characters there is a potential for collisions that could impact randomization. Regardless of the type of risk, if you are worried about the statistical validity of your Experiment you should make sure that there is both a significant number of groups as well as good balanced stratification across the groups that you're testing against. These two factors protect you against the most substantial risks. Edit this page Last updated on Jan 9, 2026 Previous Stale Feature Notifications Next Creating and Managing Metrics Overview Why Experiment Using Experimentation Comparing Multiple Variations Adding Metrics to Your Feature Determining a Winner Experimentation using a Custom Property for Randomization What are Experiments that Randomize Using a Custom Property? How to Randomize Using a Custom Property in Experiments Risks to Experimentation DevCycle Dashboard Blog Privacy Policy Twitter Discord GitHub Copyright © 2026 DevCycle. All rights reserved. | 2026-01-13T08:49:33 |
https://www.fine.dev/blog/chatgpt-canvas#pricing | Coding with ChatGPT Canvas: Elevate Your Workflow with Fine Home Docs Changelog Pricing Sign in Get started -> Menu Home Docs Changelog Pricing <- Go Back Coding with ChatGPT Canvas: Elevate Your Workflow with Fine Table of Contents What Is ChatGPT Canvas? How Can Canvas Help You? Who Is Canvas Useful For? Comparing Canvas to ChatGPT-3.5 and ChatGPT-4 ChatGPT Canvas vs. GitHub Copilot ChatGPT Canvas vs. Cursor The Ultimate Workflow: Combining Canvas with Fine Why Fine Is the Superior Choice How Fine Outperforms the Rest Fine: More Than Just a Tool Conclusion: Transform Your Coding Experience with Fine What Is ChatGPT Canvas? ChatGPT Canvas is an interactive, visual platform that transforms the way developers interact with AI. Unlike traditional text-based AI models, Canvas provides a visual workspace where you can collaboratively write, edit, and debug code alongside an AI assistant. It's like having a smart whiteboard where both you and the AI can jot down ideas, spot errors, and iterate code in real-time. How Can Canvas Help You? Visual Collaboration : Work alongside an AI in a shared visual space, making it easier to understand complex code structures. Efficient Debugging : Identify and fix issues faster with AI-guided insights directly on your code. Revision Tracking : Keep a clear history of changes, making it simpler to revert to previous versions if needed. Who Is Canvas Useful For? Individual Developers looking to enhance their coding efficiency. Development Teams aiming for a collaborative environment with AI assistance. Educators and Students who benefit from visual learning tools. Comparing Canvas to ChatGPT-3.5 and ChatGPT-4 While ChatGPT-3.5 and ChatGPT-4 are powerful language models capable of generating and understanding code, they operate primarily through text-based interactions. ChatGPT-3.5 : Great for generating code snippets and answering straightforward questions. ChatGPT-4 : Offers improved context understanding and can handle more complex queries. Limitations: Lack of a visual interface makes it harder to manage large codebases. Iterative revisions are cumbersome due to the linear text format. Canvas Advantage : Provides an interactive visual workspace. Enhances collaboration by allowing both AI and developers to interact with code visually. ChatGPT Canvas vs. GitHub Copilot GitHub Copilot is an AI pair programmer that integrates into your IDE, offering real-time code suggestions. Strengths: Seamless IDE integration. Excellent for autocompleting code and generating boilerplate code. Limitations: Lacks a collaborative visual interface. Limited in managing code revisions and providing in-depth debugging assistance. Known for hallucinations. Limited to generating code live as you type. Canvas Advantage : Offers a shared visual space for collaboration. Better suited for debugging and iterative development. ChatGPT Canvas vs. Cursor Cursor provides live coding assistance with features like real-time collaboration and multi-language support. Strengths: Supports multiple languages. Allows for real-time collaboration. Limitations: Less focused on revision tracking. Limited debugging capabilities compared to Canvas. Canvas Advantage : Superior in revision management. Offers structured debugging tools within a visual interface. The Ultimate Workflow: Combining Canvas with Fine While ChatGPT Canvas significantly enhances your coding experience, integrating it with Fine takes your workflow to an entirely new level. Why Fine Is the Superior Choice Holistic Development Platform : Fine isn't just an AI assistant; it's a comprehensive platform that streamlines coding, project management, and workflow automation. Advanced AI Capabilities : Fine leverages state-of-the-art AI to assist in code generation, optimization, and error detection. Seamless Integration : Works effortlessly with tools like GitHub, Linear, and leading LLMs. Enhanced Collaboration : Fine's collaborative features are designed for both individual developers and teams. How Fine Outperforms the Rest Cloud-based, asynchronous coding : Delegate a task and get a notification when it’s complete. Customization : Tailor AI assistance to fit your project's specific needs. Scalability : Whether you're a solo developer or part of a large team, Fine adapts to your workflow. Fine: More Than Just a Tool Fine doesn't just complement your existing tools—it amplifies them. By combining Fine with ChatGPT Canvas: Boost Productivity : Achieve more in less time with AI-assisted coding and debugging. Improve Code Quality : Leverage Fine's advanced AI to write cleaner, more efficient code. Streamline Collaboration : Keep everyone on the same page with shared workspaces and real-time updates. Conclusion: Transform Your Coding Experience with Fine While ChatGPT Canvas, GitHub Copilot, and Cursor each offer unique benefits, Fine stands out as the most comprehensive solution for modern developers. It brings together the best features of these tools and adds its own powerful capabilities to deliver an unmatched coding experience. Don't settle for just improving your workflow—revolutionize it. Ready to elevate your development process? Sign up for Fine today and unlock the full potential of AI-assisted coding! Start building today Try out the smoothest way to build, launch and manage an app Try for Free -> © Fine.dev - All rights reserved. Product Overview AI Workflows Pricing & Plans Changelog Blog Docs Company Press Terms & Conditions Privacy policy | 2026-01-13T08:49:33 |
https://popcorn.forem.com/gg_news/ign-the-pout-pout-fish-official-trailer-2026-nick-offerman-jordin-sparks-amy-sedaris-2chm | IGN: The Pout-Pout Fish - Official Trailer (2026) Nick Offerman, Jordin Sparks, Amy Sedaris - Popcorn Movies and TV 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 Popcorn Movies and TV Close Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Gaming News Posted on Oct 16, 2025 IGN: The Pout-Pout Fish - Official Trailer (2026) Nick Offerman, Jordin Sparks, Amy Sedaris # celebrities # adventure # animation # movies The Pout-Pout Fish is an animated family adventure set to splash into theaters on March 20, 2026. Introverted Mr. Fish (Nick Offerman) and his hyperactive sidekick Pip (Nina Oyama) dive into a quest for a legendary wish-granting fish—because only that mythical finned friend can save their homes. With a stellar voice cast including Jordin Sparks, Amy Sedaris, Miranda Otto and Remy Hii, this heartwarming romp is directed by Ricard Cussó and Rio Harrington and penned by Elise Allen, Elie Choufany and Dominic Morris. Expect plenty of giggles, a few heartfelt moments, and an undersea world you won’t forget. Watch on YouTube Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Gaming News Follow Joined Apr 30, 2025 More from Gaming News IGN: Baahubali: The Epic - Official Trailer #2 (2025) # adventure # action # directorscut # movies IGN: Baahubali: The Epic - Official Trailer #2 (2025) # adventure # action # marketing # movies IGN: Baahubali: The Epic - Official Trailer #2 (2025) # action # directorscut # movies 💎 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 Popcorn Movies and TV — Movie and TV enthusiasm, criticism and everything in-between. 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 . Popcorn Movies and TV © 2016 - 2026. Let's watch something great! Log in Create account | 2026-01-13T08:49:33 |
https://hmpljs.forem.com/code-of-conduct#attribution | Code of Conduct - HMPL.js 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 HMPL.js Forem Close Code of Conduct Last updated July 31, 2023 All participants of DEV Community are expected to abide by our Code of Conduct and Terms of Service , both online and during in-person events that are hosted and/or associated with DEV Community. Our Pledge In the interest of fostering an open and welcoming environment, we as moderators of DEV Community pledge to make participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, gender identity and expression, level of experience, nationality, personal appearance, race, religion, or sexual identity and orientation. Our Standards Examples of behavior that contributes to creating a positive environment include: Using welcoming and inclusive language Being respectful of differing viewpoints and experiences Referring to people by their pronouns and using gender-neutral pronouns when uncertain Gracefully accepting constructive criticism Focusing on what is best for the community Showing empathy towards other community members Citing sources if used to create content (for guidance see DEV Community: How to Avoid Plagiarism ) Following our AI Guidelines and disclosing AI assistance if used to create content Examples of unacceptable behavior by participants include: The use of sexualized language or imagery and unwelcome sexual attention or advances The use of hate speech or communication that is racist, homophobic, transphobic, ableist, sexist, or otherwise prejudiced/discriminatory (i.e. misusing or disrespecting pronouns) Trolling, insulting/derogatory comments, and personal or political attacks Public or private harassment Publishing others' private information, such as a physical or electronic address, without explicit permission Plagiarizing content or misappropriating works Other conduct which could reasonably be considered inappropriate in a professional setting Dismissing or attacking inclusion-oriented requests We pledge to prioritize marginalized people's safety over privileged people's comfort. We will not act on complaints regarding: 'Reverse' -isms, including 'reverse racism,' 'reverse sexism,' and 'cisphobia' Reasonable communication of boundaries, such as 'leave me alone,' 'go away,' or 'I'm not discussing this with you.' Someone's refusal to explain or debate social justice concepts Criticisms of racist, sexist, cissexist, or otherwise oppressive behavior or assumptions Enforcement Violations of the Code of Conduct may be reported by contacting the team via the abuse report form or by sending an email to support@dev.to . All reports will be reviewed and investigated and will result in a response that is deemed necessary and appropriate to the circumstances. Further details of specific enforcement policies may be posted separately. Moderators have the right and responsibility to remove comments or other contributions that are not aligned to this Code of Conduct or to suspend temporarily or permanently any members for other behaviors that they deem inappropriate, threatening, offensive, or harmful. If you agree with our values and would like to help us enforce the Code of Conduct, you might consider volunteering as a DEV moderator. Please check out the DEV Community Moderation page for information about our moderator roles and how to become a mod. Attribution This Code of Conduct is adapted from: Contributor Covenant, version 1.4 Write/Speak/Code Geek Feminism 💎 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 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 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 . HMPL.js Forem © 2016 - 2026. Powerful templates, minimal JS Log in Create account | 2026-01-13T08:49:33 |
https://dev.to/gayatrisachdev1/building-a-rag-based-agent-using-dronahq-59n7 | Building a RAG based agent using DronaHQ - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Gayatri Sachdeva Posted on Dec 22, 2025 Building a RAG based agent using DronaHQ # rag # agents # ai # nocode RAG and agentic RAG are often discussed at a high level, which makes them sound either overly academic or unrealistically autonomous. In practice, most useful systems sit somewhere in between. This post breaks the topic down clearly. What RAG actually is, what agentic RAG adds on top, what agentic RAG looks like in real business operations, and how I built a RAG-based agent for internal ops without writing any code. This RAG agent is based on an actual implementation by me for our marketing-sales enablement function. If you'd like to exchange ideas, lets connect ! What is retrieval augmented generation (RAG) Retrieval augmented generation is a pattern where a language model generates responses using external data retrieved at runtime, instead of relying only on its training knowledge. At a minimum, a RAG system has three parts: A corpus of source material that represents ground truth. A retriever that selects relevant pieces of that corpus based on a user query. And a generator that produces an answer using only the retrieved context. The key property of RAG is grounding. The model is constrained by what it retrieves. If the information does not exist in the corpus, the system should either say it does not know or ask for clarification. In business settings, RAG is most valuable when accuracy matters more than creativity . Internal documentation, customer stories, policies, analytics, and transcripts are all natural fits because they are bounded and auditable. What agentic RAG adds on top of RAG Agentic RAG builds on the same retrieval foundation, but adds decision-making and iteration. Instead of a single retrieve and generate step, an agentic RAG system can plan its work , adapt retrieval based on intermediate results, verify outputs, and take actions across tools. Retrieval still grounds the system, but the agent decides how and when retrieval happens. Important distinction . Agentic RAG does not require full autonomy or open ended reasoning. In most enterprise use cases, agentic behavior is narrow, intentional, and bounded. Planning, verification, and clarification loops matter more than long reasoning chains. A useful way to think about it is this. RAG answers questions. Agentic RAG completes tasks. What agentic RAG realistically looks like in business operations In practice (so far), agentic RAG systems do not behave like general assistants. They behave like focused workers with a clear job. Think about a vendor renewal in a finance or operations team. The information needed to make a decision lives in many places. Contracts in shared drives. Usage data in dashboards. Email threads where exceptions were discussed. A basic RAG system can answer a question like “What does the contract say about renewal?” by retrieving and summarizing a clause. An agentic RAG system does more. When asked to prepare a renewal summary, it first figures out what evidence is required. It retrieves renewal terms from the contract, pulls recent usage metrics, and searches for past exception notes. If any piece is missing or contradictory, it flags that instead of guessing. Only then does it generate a structured summary that can be reviewed or shared. The key difference is not the output format. It is the planning, targeted retrieval, and verification before writing. That pattern is what agentic RAG looks like in real business operations. Building a RAG-based agent for business ops - Real life use case Problem statement Customer stories were valuable, but hard to use. Information about a single customer lived across many places. A published blog might capture the high level narrative. Internal documents added implementation detail. Transcripts from customer story videos contained the strongest proof points and quotes. Slides and notes added yet another layer. Any time someone needed a short customer bite, a few bullets for a deck, or a quote focused on a specific theme like integrations, the work was manual. Someone had to search across sources, reconcile overlaps, decide what was current, and rewrite everything for the new context. The cost was not just time. It was inconsistency, outdated facts, and repeated rework. Alternatives considered and why they failed The first and default option was manual curation. Ad hoc requests to create custom one pagers, a bite for an email, or a slide for a deck. ChatGPT and NotebookLM produced fluent answers, but accuracy was unreliable. They mixed customers, invented quotes, and blurred timelines. For customer stories, that risk was unacceptable. Each alternative either did not scale or compromised trust. The solution built The solution was a RAG based agent scoped specifically to customer stories. Instead of trying to know everything, the agent retrieves only verified, customer specific material at runtime and generates outputs strictly from that context. It does not rely on general model knowledge for facts or quotes. Over time, this evolved into an agentic RAG system by adding planning, verification, and multi step behavior. How the solution works conceptually At a high level, the agent treats customer stories as evidence, not prompts. When a request comes in, it first identifies which customer the request refers to and what outputs are required. It then decides which sources are appropriate for each output. Narrative summaries come from blogs or internal docs. Quotes come from transcripts. Metrics come from outcome summaries. The agent retrieves these pieces separately, assembles them into a working context, and only then generates the final output. Nothing is written before retrieval. Nothing is generated without grounding. How I built a RAG-based agent without coding I used DronaHQ’s Agentic Platform to build this agent. Resources: The first step was defining what the agent is allowed to know. I added only approved, existing resources that already reflect how we work. This included documents, transcripts, long form pages, and links. These sources live in different formats, but together they represent the full context the agent needs. Tip: Do not dump all resources into the system. Multiple sources of truth can confuse the agent. The goal is to give it the right data and nothing else. Instructions: Instructions were the most important part of the build. I wrote instructions that explained what the agent is responsible for, how it should interpret vague requests, and what it must never do. I was explicit about avoiding overlap between sources and about asking follow up questions when the request is underspecified. Most of the iteration happened here. Small changes in instruction quality had a much bigger impact than changing tools or models. LLM model: I selected the GPT 5 model and tuned it for lower creativity. The agent’s job is not to be clever. It is to be accurate and consistent. In this case, model choice mattered less than expected. Once the constraints and instructions were solid, the behavior became predictable regardless of model tweaks. AI tools: I connected only the tools needed to produce outputs in formats people already use. This included document generation and Google Slides so the agent’s responses could immediately fit into existing tasks. Testing: Testing happened continuously. I used the playground within DronaHQ to run real, messy prompts. I deliberately tested vague requests, edge cases, and scenarios where multiple sources could apply. Whenever the output drifted or overlapped, I refined the instructions instead of adding complexity. This tight feedback loop made it easy to improve behavior without rewriting anything. Steps involved in a real request Prompt: “Give me a 100 to 150 word bite on customer XYZ, add three to four bullet points, and include two quote options where the customer talks about integrations.” The agent limits its search to artifacts tagged to customer XYZ. It identifies three output sections and maps each to a source type. Blogs or docs for the bite and bullets. Transcripts for quotes about integrations. It pulls the most relevant story sections and transcript segments that mention integrations. Retrieved content is grouped by purpose so summaries and quotes do not bleed into each other. The agent writes the bite and bullets using only retrieved story material and generates quote options derived from transcript language. If the retrieved material is insufficient or contradictory, the agent does not guess. It either asks for clarification or limits the output. This sequence is what turns a scattered knowledge base into reliable, reusable customer storytelling. Mapping RAG concepts to the agent accurately The corpus is the full set of customer story artifacts. Blogs, internal write ups, outcome summaries, transcripts, and tagged notes form the grounding data. The agent is not allowed to answer beyond this material. Ingestion brings these artifacts into the system in a retrievable form. Stories are split into logical sections such as problem, solution, integrations, scale, and outcomes. Transcripts are chunked into conversational segments. Retrieval happens at runtime. When a user mentions a specific customer, the agent scopes retrieval to that customer only. When the user asks for integration related quotes, the retriever pulls transcript segments that semantically match integration discussions. Context assembly separates sources by purpose. Blog and document content is used to generate narrative bites and bullets. Transcript content is used to generate quote options. Generation is constrained. The model is instructed to rely only on retrieved context. If the context is insufficient, the agent asks a clarifying question or declines to invent. Where agentic behavior comes in The first agentic layer is planning. Before retrieving, the agent decomposes the task into outputs and evidence needs. This determines which sources to query and how deeply. The second layer is multi pass retrieval. The agent retrieves broadly first, then runs targeted retrieval for gaps such as integrations, metrics, or quotes. The third layer is verification. The agent builds an internal evidence table mapping each claim to a source. Conflicts across sources are flagged or resolved using predefined rules. Quote handling is agentic as well. The agent first extracts verbatim transcript lines related to the requested theme, then selects the strongest candidates. Cleaned versions are generated only after selection. Slides introduce additional decision making. The agent chooses a narrative structure, retrieves proof points per slide, generates titles and speaker notes, and adapts the deck to the intended audience. A final quality check loop evaluates grounding, completeness, and format compliance. If the output falls short, the agent revises using additional retrieval. Closing thoughts If you are exploring RAG , start with a workflow where the cost of being wrong is obvious. Customer stories, policies, support runbooks, vendor renewals, and internal SOPs are all good candidates because the source material already exists and the outputs are used by real teams. A basic RAG system will get you faster answers . The moment you need consistent outputs that hold up under review, you will start adding agentic layers. Planning so the system knows what to fetch. Multi pass retrieval so it can fill gaps. Verification so it can flag contradictions. Clarifying questions so it stops guessing. Those upgrades are what move the system from “helpful” to dependable. In my case, the shift was practical. The goal was not an autonomous agent. The goal was to stop redoing the same customer story work every week, and to make sure the outputs stayed grounded in what the customer actually said and what we actually shipped. If you are building something similar, the biggest unlock is a combination of your stack, how you structure your resources, and the guardrails you add for the agent to overcome what other AI chatbots could not. If you want to see the agent in action, the video above shows a real request end-to-end. If you are building your own RAG or agentic RAG workflow, I would love to hear what corpus you are grounding it on and where it breaks today. Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Gayatri Sachdeva Follow I'm a b2b saas marketer, love exploring saas tools, no code enthusiast Location Mumbai, India Work Product Marketer at DronaHQ Joined Jan 31, 2020 More from Gayatri Sachdeva Trying out top AI app builders | Review and first impressions # ai # lowcode # appdev # agentic Build your first AI agent | Top 9 low-code agent builders # ai # lowcode # mcp # automation How to build a loan application using MySQL in DronaHQ # webdev # ai # vibecoding # tutorial 💎 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 | 2026-01-13T08:49:33 |
https://x.com/IndianTechGuide/status/2009256327596355938?s=20 | 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. | 2026-01-13T08:49:33 |
https://dev.to/chefgs/automate-kubernetes-deployment-using-terraform-and-github-actions-3m5c#comments | Automate Kubernetes Deployment using Terraform and GitHub Actions - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Saravanan Gnanaguru Posted on May 22, 2023 • Edited on Dec 13, 2023 Automate Kubernetes Deployment using Terraform and GitHub Actions # githubhack23 # terraform # kubernetes # githubactions Terraform Tutorials (8 Part Series) 1 Developing Terraform Custom Provider for Terraform v0.12 2 Create Apache Web Server in AWS Using Terraform ... 4 more parts... 3 Create and Configure Google Cloud Instance using Terraform and Chef 4 How to Develop a Custom Provider in Terraform v0.13+ 5 Create AWS Infrastructure using CDK for Terraform 6 Deploy Kubernetes Resources in Minikube cluster using Terraform 7 Create Amazon EKS Cluster using Terraform Module 8 Automate Kubernetes Deployment using Terraform and GitHub Actions Automate Kubernetes Deployment using Terraform and GitHub Actions What I built I've created Terraform code that will create a namespace and deploys the Nginx server in the minikube cluster and TF code verification and deployment has been automated using GitHub actions How I built Created a GitHub Actions workflow using the Marketplace Github actions plugins, actions/checkout@v2.5.0 -> to Checkout the code medyagh/setup-minikube@v0.0.13 -> to setup minikube Azure/setup-kubectl@v3 -> to setup kubectl hashicorp/setup-terraform@v2.0.2 -> to setup terraform This workflow can be used in development environments, in which an Infra developer can create the Terraform code to deploy kubernetes workload. Once after creating the tf code, the developer can trigger the Terraform workflow, that will do the CI for Terraform code, and deploy the infra in minikube . The kube config context has been created as a variable in Terraform, so it can be overridden with other Kubernetes Cluster config and contexts from Cloud providers like Amazon EKS or Azure AKS or GCP GKE Clusters. Category Submission DIY Deployments App Link Source code for the Repo is available here Github Action Workflow Yaml Screenshots Description Triggering the Workflow This workflow can be triggered from the actions tab, by providing the Terraform code directory as an input (Refer the screenshot above). So it will run the below steps in the directory provided as input, Workflow installs, minikube , kubectl and terraform CLI executables needed to be used by the rest of workflow It runs terraform init command to download the kubernetes provider Then runs terraform validate command to check the tf code is valid or not After that it runs, terraform plan and terraform apply commands and performs the Kubernetes namespace creation and deploys the nginx server. Workflow also has terraform destroy command, that deletes the kubernetes infra created in the workflow Workflow Dispatch This workflow uses, workflow_displatch Github feature - It is the sub block inside the on event triggering block, in which we can specify what are the inputs needed to trigger the workflow. In the on event block workflow_dispatch section, we will be adding the inputs directory path, on which we are going to run our Terraform code validation It is defaulted to the 'kubernetes' directory present in the repo for the ease of demo purpose. Link to Source Code Source code for the Repo is available here Github Action Workflow Log Github Action Workflow Yaml Permissive License MIT License Background As mentioned earlier, This workflow (or pipeline) can be configured for testing the terraform code pushed by DevOps engineers/SREs/Developers, and can be triggered whenever there is new tf code is pushed into a specific branch for Kubernetes workload management Additional Resources/Info Terraform Kubernetes Provider Workflow Dispatch Inputs Jobs Terraform Market place Action Terraform Tutorials (8 Part Series) 1 Developing Terraform Custom Provider for Terraform v0.12 2 Create Apache Web Server in AWS Using Terraform ... 4 more parts... 3 Create and Configure Google Cloud Instance using Terraform and Chef 4 How to Develop a Custom Provider in Terraform v0.13+ 5 Create AWS Infrastructure using CDK for Terraform 6 Deploy Kubernetes Resources in Minikube cluster using Terraform 7 Create Amazon EKS Cluster using Terraform Module 8 Automate Kubernetes Deployment using Terraform and GitHub Actions Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Saravanan Gnanaguru Follow Cloud DevOps and Infra as Code Location India Pronouns he/him Work Architect Joined Dec 29, 2019 More from Saravanan Gnanaguru My new blog on Docker and Kubernetes deployment in UpCloud # docker # kubernetes # cloud # devops Practicing Kubernetes Control Plane environment in Killercoda Interactive Terminal # kubernetes # beginners # kcdchennai # blogathon Create Amazon EKS Cluster using Terraform Module # aws # kubernetes # awseks # tutorial 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/codeideal/dlman-the-download-manager-i-always-wanted-5bi2 | DLMan :: the download manager I always wanted - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Shayan Posted on Jan 8 DLMan :: the download manager I always wanted # programming # opensource # rust # tauri As a Mac user, I always felt this gap. Windows users have IDM and a bunch of other solid download managers, but most of them are ancient, paid, or both. Meanwhile on Mac? Not much to choose from. So I did what any frustrated developer would do; I built my own. Introducing DLMan DLMan is a modern, open source download manager , built with Rust (Tauri) and React . It’s fast, lightweight, and actually works the same on: Windows macOS Linux Why is it great? Multi-segment downloads with stable pause / resume Queues, schedules, and post actions (yes, including shut down my computer when finished ) Batch import + drag & drop (single or multiple links) Super lightweight (~5MB) Modern architecture, fully cross-platform Browser extensions 100% open source Download You can grab it from GitHub: 👉 GitHub Repo 👉 Latest Release Final words from the creator I genuinely love what I’m doing. I love building open source tools and sharing them with the world. But yeah — making a living this way isn’t easy. Open source survives because of the community behind it ❤️ How you can support DLMan Use it and report issues ( right here ) Share it with friends Star the repo ⭐ Feeling generous? ☕ Buy me a coffee || sponsor the project I really want to put more time into DLMan and make it even better. I do read issues, and I do try to fix them. Thanks for being part of this... Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Shayan Follow Indie maker. Building tools at the intersection of design, code, and creativity. TypeScript, UX, and open source enthusiast. Joined Jun 12, 2025 More from Shayan I Fixed Blender's Render Output Paths ( Because it SUCKS! ) # blender # opensource # showdev I Built OpenFields ( Free Alternative to ACF for WP ) # wordpress # tooling # showdev # opensource I Built LexKit: A Modern, Type-Safe Rich Text Editor for React # react # showdev # opensource # typescript 💎 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 | 2026-01-13T08:49:33 |
https://docs.devcycle.com/platform/experimentation/creating-and-managing-metrics/ | Creating and Managing Metrics | DevCycle Docs Skip to main content Home SDKs APIs Management API Bucketing API Integrations CLI / MCP Best Practices Community Blog Discord Search Sign Up Home Getting Started Essentials DevCycle Overview Key Features System Architecture Feature Hierarchy Feature Types Platform Feature Flags Experimentation Feature Experimentation Creating and Managing Metrics How Metrics are Calculated Video Tutorial: Experiment Setup Tutorial: Funnel Experiment Account Management Security and Guardrails Testing and QA Extras Examples Platform Experimentation Creating and Managing Metrics On this page Creating and Managing Metrics info Metrics are available to all customers on any plan and rely on Custom Events that must be sent to DevCycle. All plans come with an included amount of free events. When exceeded, additional costs will be incurred. To learn more, read about our pricing , or contact us . This article explains how to create, define, and manage all of the Metrics in a Project. Metrics provide a broad overview of your system. They may be used to quickly assess the health of your Features across environments, visualize how quickly people are visiting your applications, or how much memory is being used by your servers as a Feature rolls out. Metrics may be known as "Goals" on other platforms. Within DevCycle, Metrics are their own items outside of a Feature and thus can be defined once and applied to as many Features as desired. This gives the opportunity to attach and test Metrics with seemingly unrelated Features and find unintended or hidden impacts. Metrics Section To view and create Metrics, first navigate to the Metrics section of the Dashboard This section will contain a list of all of the Metrics on the current Project, all of which are re-usable across any number of Features at any time. This list contains some simple base info. Below is a brief description of each column, with deeper explanations later in this document Name - The name of the Metric. This name is the human-readable format of the Metric for easily discussing the Metrics. As explained later, the key is what will be used within the Management API. Type - The "Type" of Metric which represents the dimension or calculation used for the Metric. It may be a simple count, or a rate, or an average. These type definitions are described below in "Creating a Metric". Event Type - This is the name of the event sent by the SDKs or APIs which is being used for this Metric. Date Modified - Simple date explaining the last time someone made any modifications to a Metric which may have changed anything significant to the calculated results. Creating a Metric Follow the video below from our DevCycle Experiment Setup series or read-along to find out how to create a Metric on DevCycle. To create a Metric, navigate to the Metrics page as noted above, and click "Create a Metric". Metrics can also be created directly within any Feature from the Experimentation panel. Upon clicking create, the following modal will show: To set up a Metric, the following items are needed: Name - This is the name of the Metric. It should be descriptive enough that any team member viewing it understands it and can both get the information necessary, and also decide if they would like to re-use the Metric for other Features. Key - Like other DevCycle keys, this is how this Metric will be referenced in the Management API and all other non-dashboard interactions with this Metric. Event Type - This is the EXACT event name that is sent by the DevCycle Track methods of the SDKs or via the DevCycle APIs. This event will be used in all calculations of the Metric. How it is used specifically is described below in How do Metrics get calculated? Optimize For - DevCycle represents Metrics as a positive or negative depending on the desired optimization. Often times, tools will always assume that an increase is beneficial. However, in most engineering applications, the opposite is true! Things such as latency, load times, server load, and processing times are Metrics that should be decreased. DevCycle will make obvious whether a Metric is improving in the desired direction, and will soon notify you if a significant impact in either direction has been made. Description (optional) - A meaningful description explaining what this Metric is for and why it is being tracked. In conjunction with DevCycle's Jira Integration, this can be useful for managers to get a greater depth of information when understanding Metrics. Type - The type of a Metric defines how and what it is calculating and represented to the user. This "Type" is currently a set of the items defined below and available in the dropdown. Types When making a Metric, the types of Metrics will contain a small definition Count per Unique User - This Metric type calculates the total number of times a unique user (or service) has sent this event. This can be something such as total number of clicks on a new feature, total number of API calls for a new service, total number of of views for a new advertisement, etc. This is also useful for error tracking -- A total count of specific errors is a great Metric to count when monitoring the rollout of a new release of a Feature. Count per Variable Evaluation - This type counts the total number of times this event has been seen ONLY when the actual related Variable has been evaluated. This is a very useful case, as there may be events which already exist within your system which could potentially also be impacted by this Variable. In this case, this type of Metric represents the exact number of times that event has been sent ONLY after the related Variable has since been evaluated for use. Sum per User (numerical) - Each event can carry a numerical value with it, and this Metric will sum up the total number sent with the events per unique user. This type of Metric is great for tracking things such as Revenue, or number of total items purchased or interacted with. From an engineering view, things such as a total number of api calls per unique user may be something intended to decrease (for optimizations) or increase (for increased interaction). Average per User (numerical) - Similar to the sum per user, the average for user also uses the numerical value on each event. This type of Metric is extremely useful for tracking things such as the average latency per API call, or average size of an API call, hoping for a decrease. Load times, server load, api latency, or even your own internal build time can be candidates for a Metric which is re-used across every single Feature for viewing the impact and reacting accordingly. Future Types - If there are any types of Metric you'd like to see, or if your team would like a more flexible view into all of your data, do not hesitate to reach out to [email protected] . We will be increasing the number of types, as well as providing direct calculation control in the future. If such things are desired now, contact us to discuss direct data access, which will provide full access to all events and data for each of your Projects. Metric Details Page After creating a Metric, or by clicking on one from the Metric list, you will be navigated to the Metric Details page. This page has the following sections. Metric Definition The Metric definition allows for modifying the Metric Name, Type, Definition, and Optimization. Metric Testing This section provides the ability to test a Metric against any Feature in any environment and ensure it is working as intended. It is also useful to use this testing section to quickly check a Metric against any given Feature to potentially find any unintended impacts if the Metric is not associated with a specific Feature. When testing a Metric, navigate to the Testing section. To run a test, the following fields must be set: Feature - This is the specific Feature this Metric should be applied to. Any event that has been sent since the creation of this Metric from a user receiving any Variation of this Feature will be part of this Metric. In the event that an error is shown, this means the event has not been seen from this Feature yet. Control - After selecting a Feature, a "control" Variation must be selected. This is what will be used to show a comparative analysis against all other Variations in a Feature. Typically, an "off" or "Baseline" Variation would act as the control. For more information on this, please refer to the Feature Experimentation documentation . Date Range - Select a date range of up to the last 30 days to display results for. This range will default to the last 30 days or to the Feature creation date if the Feature was created within 30 days. Environment - This will calculate the Metric using events from the specified environments. Once these fields are set, the test can be ran by clicking the test button, resulting in a test result. (For these documents, our own internal Metrics testing at this time were used!) The results of this test will show the actual result which would be within a Feature if this Metric was associated with it! Attaching Metrics to Features Tracking Metrics within a Feature is an important aspect of data analysis, as it can provide valuable insights into the performance and behaviour of different Features. Once a Metric has been created, it can be attached to any Feature for use and analysis. Follow the video below from our DevCycle Experiment Setup series or read-along to find out how to add a Metric to a Feature and view Experiment results. Here are the steps you can follow to track Metrics within a Feature: Select the Feature you want to track : Within that Feature, navigate to the Data & Results tab on the Feature Form of the page and click on Experiment Results . Choose the Metric(s) associated with the Feature : Create new Metrics or attach existing ones to the Feature by navigating to the Choose a Metric dropdown. Attach the Metric(s) : Attach the Metric from the dropdown menu by selecting it. For our example, let's use the Metric Metric Testing , which has already been setup within our Project. While the setup has some default values, the Metric requires the following fields to be filled: Control - This is what will be used to show a comparative analysis against all other Variations in a Feature. Typically, an "off" or "Baseline" Variation would act as the control. For more information on this, please refer to the Feature Experimentation documentation . Date Range - Select a date range of up to the last 30 days to display results for. This range will default to the last 30 days or to the Feature creation date if the Feature was created within 30 days. Environment - This will calculate the Metric using events from the specified environments. Calculate results : Once one or more Metrics have been selected, we can then run the Metric calculation to generate insight into how the Feature is doing. View your results : Once calculated, if there is available data for the Feature, the results data will populate within the dashboard. From here, useful information such as trends and patterns in the data can be used to make informed decisions about how to optimize the Feature for performance improvements. How do Metrics get calculated? To calculate Metrics, DevCycle uses the custom events sent via its API or SDKs . Each Event has the information of which user sent it and which Feature and Variation they were in at that time. For optimal Experiments, use Features with Variations randomly distributed across users . To read more on the queries behind the Metrics, see How Metrics Are Calculated Running Experiments With Metrics on a Feature, Experimentation can be easily executed on any Feature. At DevCycle we believe that Experimentation should be a part of the natural lifecycle of all Features. So no matter the Feature type selected, Experimentation will always be available for use. To learn more on how to run Experiments with DevCycle, read Feature Experimentation Edit this page Last updated on Jan 9, 2026 Previous Feature Experimentation Next How Metrics are Calculated Metrics Section Creating a Metric Types Metric Details Page Attaching Metrics to Features How do Metrics get calculated? Running Experiments DevCycle Dashboard Blog Privacy Policy Twitter Discord GitHub Copyright © 2026 DevCycle. All rights reserved. | 2026-01-13T08:49:33 |
https://dev.to/challenges/postmark#main-content | Postmark Challenge: Inbox Innovators - DEV Challenge - 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 Challenges > Postmark Challenge: Inbox Innovators CHALLENGE RESULTS 🏆 Winners Announced! 🎊 Congrats to the Winners of Postmark Challenge: Inbox Innovators! Read Announcement Challenge ends soon! Submit your entry now DAYS : HOURS : MINUTES : SECONDS See prompts Postmark Challenge: Inbox Innovators View Entries Please sign in to follow this challenge The email delivery service that people actually like! Challenge Status: Ended Ended Join our next Challenge Running through June 8 , the Postmark Challenge: Inbox invites you to play with data by leveraging Postmark's inbound email parsing capabilities. Email remains one of the most universal and powerful communication tools, and Postmark's developer-focused API makes it easier than ever to incorporate sophisticated email functionality into your applications. This challenge is your opportunity to demonstrate how creative you can get with email-based features while adding an impressive project to your portfolio! We will selected three talented winners. Each will receive: $1,000 USD DEV++ Membership Exclusive DEV Badge All Participants with a valid submission will receive a completion badge on their DEV profile. Good Luck! Key Dates Contest start: May 21, 2025 Submissions due: June 08, 2025 Winners announced: June 19, 2025 Badge Rewards Postmark Challenge: Inbox Innovators Completion Badge Postmark Challenge: Inbox Innovators Winner Badge Sponsored by Postmark Postmark is a cloud-based email delivery service designed to ensure that transactional emails—such as password resets, order confirmations, and notifications—reach recipients' inboxes quickly and reliably. It offers both an Email API and SMTP service, allowing developers to integrate email functionality into their applications with ease. Learn More → Challenge Prompt Inbox Innovators Your mission is to build an application using Postmark's inbound email parsing feature . Postmark's inbound email parsing allows you to receive and process emails programmatically, opening up countless possibilities for all sorts of applications -- from practical tooling that solves real-world problems to creative and impactful art pieces. Submission Template Judging Criteria: Utilization of Postmark features Use Case (creativity; originality; impact) Accessibility Writing Quality (originality; clarity) Frequently Asked Questions Participation Can I submit to a prompt more than once? Yes, you can submit multiple submissions per prompt but you’ll need to publish a separate post for each submission. Can I work on a team? Yes, you can work on teams of up to four people. If you collaborate with anyone, you’ll need to list their DEV handles in your submission post so we can award a badge to your entire team! Please only publish one submission per team. DEV does not handle prize-splitting, so in the event that your submission wins the shop gift, you will need to split that amongst yourselves. Thank you for understanding! How old do I have to be to participate? Participants need to be 18+ in order to participate. If I live in X, am I eligible to participate? For eligibility rules, see our official challenge rules . Submission Can my submission include open source code? Riffing on open source code and borrowing and improving on previous work/ideas is encouraged but it’s important your changes are significant enough to ensure your submission is valid. When does riffing become plagiarism? It will depend, but transparency is important, license compatibility is important. You can use someone else’s code to give you a jumpstart to demonstrate your ideas on top of someone else’s base, but not just re-package the base. It should be clear to the judges what you added to the project in terms of the code and conceptual inspiration. This means, you should clearly state what you were building on and what elements are original to this new submission. When building on existing code, we expect a significant change that adds something tangible to the output. i.e. a new animation, and new sprite, a new function, a new presentation. Not just changes to the source - i.e. changing colours, changing one sprite, changing one function. What happens if my submission is considered plagiarized or invalid? Anything deemed to be plagiarism will not be eligible for prizes. Incidental plagiarism may simply result in your disqualification from the challenge (regardless of the number of other valid submissions you have published). Egregious plagiarism will result in your suspension from DEV entirely. Any non-generic, non-trivial usage of prior work, including open source code must be credited in your submission. Do submissions have to be in English? Non-english submissions are eligible for a completion badge but not eligible for prizes due to the current limitations of our judges. We will not be judging on mastery of the English language, so please don’t let this deter you from submitting if you are not a native English speaker! We hope to evolve this in the future to be more accommodating. Do I need a license for my code? You are not required to license your code but we strongly recommend that you do. Here are some you may consider: MIT , Apache , BSD-2 , BSD-3 , or Commons Clause . Can I use AI? Use of AI is allowed as long as all other rules are followed. We want to give you a chance to show off your skills in realistic scenarios. If you use AI tools to help you achieve your submission, all the power to you. How do I embed my project directly into my DEV post? Our editor supports many types of embeds, including: Stackbliz, Glitch, Github, etc. You can typically use the {% embed https://... %} syntax directly in the post. Click here for more information on our markdown support. For CodePen, you will need to use this syntax: {% codepen http://... %} For CodeSandbox, you will need to use this syntax: {% codesandbox http://... %} Judging and Prizing Can there be ties? In the event of a tie in scoring between judges, the judges will select the entry that received the highest number of positive reactions on their DEV post to determine the winner. How will I know if I won? Winners will be announced in a DEV post on the winner announcement date noted in our key dates section. When will winners receive their Forem Shop gift? The DEV Team will contact you via the email associated with your DEV profile within, at most, 10 business days of the announcement date to share the details of the shop gift. When will I receive my DEV badge? Both participation and winner badges will be awarded, in most cases, the same day as the winner announcement. When will I receive my prizes? The DEV Team will contact you via the email associated with your DEV profile within, at most, 10 business days of the announcement date to share the details of claiming your prizes. What steps do I need to take to receive my cash prize? The winner (including each member of a team) may be required to sign and return an affidavit of eligibility and publicity/liability release, and provide any additional tax filing information (such as a W-9, social security number or Federal tax ID number) within seven (7) business days following the date of your first email notification. Postmark Challenge: Inbox Innovators Rules NO PURCHASE NECESSARY. Open only to 18+. Contest entry period ends June 1, 2025 at 11:59 PM PDT. Contest is void where prohibited or restricted by law or regulation. All entires must be submitted during the content period. For Official Rules, see Postmark Challenge: Inbox Innovators Contest Rules and General Contest Official Rules . Dismiss 💎 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 | 2026-01-13T08:49:33 |
https://devcycle.com | DevCycle | The First OpenFeature-Native Feature Flag Platform Product Solutions Resources Pricing Docs Book Demo Login Create Account Speed Up Feature Releases The first open standards feature management platform built to help developers ship faster Start Free What's OpenFeature? Trusted by effective engineering teams Open Source Flexibility with SaaS Simplicity Confidence through Open Standard portability The first and only OpenFeature-native feature management platform, built on edge architecture to deliver fast, scalable and low latency performance backed by enterprise-grade security, compliance and dedicated support. Learn more about OpenFeature Faster Feature Releases Move fast and protect production Accelerate your feature releases by shipping code behind feature flags. Teams across your organization can safely test and deploy features in production, avoiding merge conflicts, cross-team bottlenecks and the need for synchronized release schedules. Learn more Total Observability Into Your Feature Flags Flag Understanding at a Glance Gain complete visibility into all the features in your organization. With developer tools and observability integrations, you have full visibility and control over the creation, management and monitoring of your feature flags in code and through our intuitive and user-friendly dashboard. Learn more about our developer tools A True Partner, Not Just a Vendor Sometimes you just need a helping hand Backed by a decade of industry expertise, the DevCycle team has helped many organizations successfully implement feature flagging or A/B testing programs. Want to know the best practices for implementing OpenFeature? Not sure how to migrate from an in-house solution? We've got you! Book some time with us We Don't Charge by Seat Because feature flagging is a team sport We believe teams get the most value out of feature management platforms when everyone has access, which is why we offer usage-based pricing. Every DevCycle plan includes full access to all integrations, so you can focus on building features instead of worrying about seats and add-ons. See pricing Features that make flagging simple and understandable. Feature Flag Visibility Full visibility into which features are running in each of your environments and who they're impacting. Deploy Updates in Realtime Reduce time to recovery by instantly rolling out fixes without rerunning or refreshing applications. QA & Testing Simplify QA and test automation with tools for testing across all environments and platforms. AI & MCP Use your favorite AI agents and natural language to create, manage and monitor feature flags. A/B Testing & Experimentation Run experiments to validate features and make data-driven decisions before release. Gradual Rollouts Reduce the impact of bugs by gradually releasing a feature to a subset of users, and rolling back if needed. Roles & Permissions Granular role-based access control ensures secure, compliant and centralized user management for all flags. Feature Opt-In Customize user experiences and test beta features by allowing customers to self-select their preferred features. Part of the OpenFeature Ecosystem Built on Battle-Tested Industry Standards DevCycle is the top feature flag management platform for developers building with OpenFeature. Open-Source SDKs Fully transparent, up to date, and supported by developers from the open-source community. No Vendor Lock-In Easily export your full project configuration at any time. Built-In Support for OpenFeature SDKs Seamlessly swap providers whenever you'd like. Learn About OpenFeature Check Out the Ecosystem Want to try DevCycle without signing up? Try out feature flags with DevCycle by exploring our no-signup playground. Enter the Playground Fast, Dependable, and Scalable Architected for Scale and Reliability Serve your flags from DevCycle’s scalable, low-latency, and fault-tolerant edge network with automatic fallbacks to safe defaults and local caching. + Years Experience Building Feature Flags Billion Evaluations Daily Million Devices Running DevCycle Get integrated with DevCycle Wide API, SDK, and Integration Coverage Whether you are building for the web, back-end servers, or mobile devices, we've got you covered. 15+ SDKs 15+ Integrations " ...takes the stress out of launches. " " Being able to test out a new feature in production, before it is live for our users, is instrumental in our release process as it takes the stress out of launches. " Jason Barry, Senior Staff Developer @Netlify " ...one of the most intuitive feature flag managers... " " DevCycle is one of the most intuitive feature flag managers we've ever worked with. DevCycle support is top class, with account managers and developers within easy reach. " Michael Wallace, Staff Software Engineer @Bazaarvoice " ...reduced production incidents by 90% " " Through our use of DevCycle, paired with development process improvements, we reduced production incidents by 90%. " Katherine Kurtz, Senior Director @RBC " Devcycle has become an indispensable part of our strategy... " " DevCycle has become an indispensable part of our feature management strategy. The platform enables us to efficiently control the release of features, integrations, and early access functionality…we've successfully used DevCycle to roll out major product enhancements, such as our new SSO and MFA login experience, AI assistant, and AI report builder. " Jon Cain, Software Architect @BigTime " ...Devcycle is an invaluable tool " " With DevCycle, we've significantly improved our development process, reduced risk, and delivered a more customized and impactful experience to our users. It's an invaluable tool for any team looking to take their feature management to the next level. " Erik Heinemark, CPO and Co-Founder @Forza Football " ...significantly improved our agility and responsiveness " " The ability to make controlled, data-driven decisions about feature releases has significantly improved our agility and responsiveness. DevCycle is an essential part of our development and deployment process, and we highly recommend it to teams looking to mitigate risk and integrate CI/CD into their workflows! " Shirley Javier, Director of Product @Just Appraised " ...takes the stress out of launches. " " Being able to test out a new feature in production, before it is live for our users, is instrumental in our release process as it takes the stress out of launches. " Jason Barry, Senior Staff Developer @Netlify " ...one of the most intuitive feature flag managers... " " DevCycle is one of the most intuitive feature flag managers we've ever worked with. DevCycle support is top class, with account managers and developers within easy reach. " Michael Wallace, Staff Software Engineer @Bazaarvoice " ...reduced production incidents by 90% " " Through our use of DevCycle, paired with development process improvements, we reduced production incidents by 90%. " Katherine Kurtz, Senior Director @RBC " Devcycle has become an indispensable part of our strategy... " " DevCycle has become an indispensable part of our feature management strategy. The platform enables us to efficiently control the release of features, integrations, and early access functionality…we've successfully used DevCycle to roll out major product enhancements, such as our new SSO and MFA login experience, AI assistant, and AI report builder. " Jon Cain, Software Architect @BigTime " ...Devcycle is an invaluable tool " " With DevCycle, we've significantly improved our development process, reduced risk, and delivered a more customized and impactful experience to our users. It's an invaluable tool for any team looking to take their feature management to the next level. " Erik Heinemark, CPO and Co-Founder @Forza Football " ...significantly improved our agility and responsiveness " " The ability to make controlled, data-driven decisions about feature releases has significantly improved our agility and responsiveness. DevCycle is an essential part of our development and deployment process, and we highly recommend it to teams looking to mitigate risk and integrate CI/CD into their workflows! " Shirley Javier, Director of Product @Just Appraised < > Free yourself from vendor lock-in. DevCycle + OpenFeature gives you flexibility you never thought you'd have Try DevCycle today, without entering a credit card or speaking to sales. Give DevCycle a Spin See Pricing Footer DevCycle What are Feature Flags? OpenFeature Create a Free Account Request a Demo Pricing Resources Documentation SDKs APIs Integrations Blog Contact Support Company About Us Careers Terms of Service Security & Compliance Privacy Policy Contact Us Discord X GitHub LinkedIn Bluesky © 2026 DevCycle All rights reserved. | 2026-01-13T08:49:33 |
https://realpython.com/python-built-in-functions/ | Python's Built-in Functions: A Complete Exploration – Real Python Start Here Learn Python Python Tutorials → In-depth articles and video courses Learning Paths → Guided study plans for accelerated learning Quizzes & Exercises → Check your learning progress Browse Topics → Focus on a specific area or skill level Community Chat → Learn with other Pythonistas Office Hours → Live Q&A calls with Python experts Podcast → Hear what’s new in the world of Python Books → Round out your knowledge and learn offline Reference → Concise definitions for common Python terms Code Mentor → Beta Personalized code assistance & learning tools Unlock All Content → More Learner Stories Python Newsletter Python Job Board Meet the Team Become a Tutorial Writer Become a Video Instructor Search / Join Sign‑In — FREE Email Series — 🐍 Python Tricks 💌 Get Python Tricks » 🔒 No spam. Unsubscribe any time. Browse Topics Guided Learning Paths Basics Intermediate Advanced ai algorithms api best-practices career community databases data-science data-structures data-viz devops django docker editors flask front-end gamedev gui machine-learning news numpy projects python stdlib testing tools web-dev web-scraping Table of Contents Built-in Functions in Python Using Math-Related Built-in Functions Getting the Absolute Value of a Number: abs() Finding the Quotient and Remainder in Division: divmod() Finding Minimum and Maximum Values: min() and max() Computing Powers: pow() Rounding Numbers: round() Calculating Totals: sum() Creating and Manipulating Basic Data Types Representing Integer Numbers: int(), bin(), oct(), and hex() Manipulating Other Numbers: float() and complex() Building and Representing Strings: str() and repr() Processing Boolean Values: bool() Encoding Strings: ord() and chr() Creating Bytes and Byte Arrays: bytes() and bytearray() Creating Collection Data Types Creating Lists and Tuples: list() and tuple() Constructing Dictionaries: dict() Creating Sets and Frozen Sets: set() and frozenset() Processing Iterables and Iterators Determining the Number of Items in a Container: len() Reversing and Sorting Iterables: reversed() and sorted() Determining the Truth Value of Items in Iterables: all() and any() Creating Ranges of Integer Values: range() Enumerating Items in Loops: enumerate() Extracting Slices or Portions of Sequences: slice() Zipping Iterables for Parallel Iteration: zip() Building and Consuming Iterators: iter() and next() Filtering and Mapping Iterables: filter() and map() Processing Input and Output Accepting Input From the User: input() Opening Files: open() Printing Text to the Screen or Another Output: print() Formatting Strings: format() Working With Classes, Objects, and Attributes Building Properties: property() Creating Class and Static Methods: classmethod() and staticmethod() Managing Attributes: getattr(), setattr(), and delattr() Checking for Attributes: hasattr() Creating and Checking Types: type(), isinstance() and issubclass() Checking for Callable Objects: callable() Accessing the Parent’s Members: super() Building Generic Objects: object() Working With Python Scopes Inspecting and Updating a Local Scope: locals() Inspecting and Updating the Global Scope: globals() Introspecting Objects Knowing an Object’s Identity: id() Checking Names and Attributes: dir() and vars() Running Python Code From Strings Executing Expressions From Strings: eval() Running Code From Strings: exec() and compile() Using Miscellaneous Functions Accessing the Built-in Help System: help() Creating Hash Codes: hash() Importing Objects From String Names: __import__() Manipulating Binary Data Efficiently: memoryview() Conclusion Mark as Completed Share Python's Built-in Functions: A Complete Exploration by Leodanis Pozo Ramos Reading time estimate 2h 20m basics python Mark as Completed Share Table of Contents Built-in Functions in Python Using Math-Related Built-in Functions Getting the Absolute Value of a Number: abs() Finding the Quotient and Remainder in Division: divmod() Finding Minimum and Maximum Values: min() and max() Computing Powers: pow() Rounding Numbers: round() Calculating Totals: sum() Creating and Manipulating Basic Data Types Representing Integer Numbers: int(), bin(), oct(), and hex() Manipulating Other Numbers: float() and complex() Building and Representing Strings: str() and repr() Processing Boolean Values: bool() Encoding Strings: ord() and chr() Creating Bytes and Byte Arrays: bytes() and bytearray() Creating Collection Data Types Creating Lists and Tuples: list() and tuple() Constructing Dictionaries: dict() Creating Sets and Frozen Sets: set() and frozenset() Processing Iterables and Iterators Determining the Number of Items in a Container: len() Reversing and Sorting Iterables: reversed() and sorted() Determining the Truth Value of Items in Iterables: all() and any() Creating Ranges of Integer Values: range() Enumerating Items in Loops: enumerate() Extracting Slices or Portions of Sequences: slice() Zipping Iterables for Parallel Iteration: zip() Building and Consuming Iterators: iter() and next() Filtering and Mapping Iterables: filter() and map() Processing Input and Output Accepting Input From the User: input() Opening Files: open() Printing Text to the Screen or Another Output: print() Formatting Strings: format() Working With Classes, Objects, and Attributes Building Properties: property() Creating Class and Static Methods: classmethod() and staticmethod() Managing Attributes: getattr(), setattr(), and delattr() Checking for Attributes: hasattr() Creating and Checking Types: type(), isinstance() and issubclass() Checking for Callable Objects: callable() Accessing the Parent’s Members: super() Building Generic Objects: object() Working With Python Scopes Inspecting and Updating a Local Scope: locals() Inspecting and Updating the Global Scope: globals() Introspecting Objects Knowing an Object’s Identity: id() Checking Names and Attributes: dir() and vars() Running Python Code From Strings Executing Expressions From Strings: eval() Running Code From Strings: exec() and compile() Using Miscellaneous Functions Accessing the Built-in Help System: help() Creating Hash Codes: hash() Importing Objects From String Names: __import__() Manipulating Binary Data Efficiently: memoryview() Conclusion Remove ads Python has many built-in functions that you can use directly without importing anything. These functions cover a wide variety of common programming tasks that include performing math operations, working with built-in data types, processing iterables of data, handling input and output in your programs, working with scopes, and more. In this tutorial, you’ll: Get to know Python’s built-in functions Learn about common use cases of Python’s built-in functions Use these functions to solve practical problems To get the most out of this tutorial, you’ll need to be familiar with Python programming, including topics like working with built-in data types , functions , classes , decorators , scopes , and the import system. Get Your Code: Click here to download the free sample code that shows you how to use Python’s built-in functions. Take the Quiz: Test your knowledge with our interactive “Python's Built-in Functions: A Complete Exploration” quiz. You’ll receive a score upon completion to help you track your learning progress: Interactive Quiz Python's Built-in Functions: A Complete Exploration Take this quiz to test your knowledge about the available built-in functions in Python. By taking this quiz, you'll deepen your understanding of how to use these functions and the common programming problems they cover, from mathematical computations to Python-specific features. Built-in Functions in Python Python has several functions available for you to use directly from anywhere in your code. These functions are known as built-in functions and they cover many common programming problems, from mathematical computations to Python-specific features. Note: Many of Python’s built-in functions are classes with function-style names. Good examples are str , tuple , list , and dict , which are classes that define built-in data types. These classes are listed in the Python documentation as built-in functions and you’ll find them in this tutorial. In this tutorial, you’ll learn the basics of Python’s built-in functions. By the end, you’ll know what their use cases are and how they work. To kick things off, you’ll start with those built-in functions related to math computations. Remove ads Using Math-Related Built-in Functions In Python, you’ll find a few built-in functions that take care of common math operations, like computing the absolute value of a number , calculating powers, and more. Here’s a summary of the math-related built-in functions in Python: Function Description abs() Calculates the absolute value of a number divmod() Computes the quotient and remainder of integer division max() Finds the largest of the given arguments or items in an iterable min() Finds the smallest of the given arguments or items in an iterable pow() Raises a number to a power round() Rounds a floating-point value sum() Sums the values in an iterable In the following sections, you’ll learn how these functions work and how to use them in your Python code. Getting the Absolute Value of a Number: abs() The absolute value or modulus of a real number is its non-negative value. In other words, the absolute value is the number without its sign . For example, the absolute value of -5 is 5 , and the absolute value of 5 is also 5 . Note: To learn more about abs() , check out the How to Find an Absolute Value in Python tutorial. Python’s built-in abs() function allows you to quickly compute the absolute value or modulus of a number : Python >>> from decimal import Decimal >>> from fractions import Fraction >>> abs ( - 42 ) 42 >>> abs ( 42 ) 42 >>> abs ( - 42.42 ) 42.42 >>> abs ( 42.42 ) 42.42 >>> abs ( complex ( "-2+3j" )) 3.605551275463989 >>> abs ( complex ( "2+3j" )) 3.605551275463989 >>> abs ( Fraction ( "-1/2" )) Fraction(1, 2) >>> abs ( Fraction ( "1/2" )) Fraction(1, 2) >>> abs ( Decimal ( "-0.5" )) Decimal('0.5') >>> abs ( Decimal ( "0.5" )) Decimal('0.5') In these examples, you compute the absolute value of different numeric types using the abs() function. First, you use integer numbers, then floating-point and complex numbers, and finally, fractional and decimal numbers. In all cases, when you call the function with a negative value, the final result removes the sign. For a practical example, say that you need to compute the total profits and losses of your company from a month’s transactions: Python >>> transactions = [ - 200 , 300 , - 100 , 500 ] >>> incomes = sum ( income for income in transactions if income > 0 ) >>> expenses = abs ( ... sum ( expense for expense in transactions if expense < 0 ) ... ) >>> print ( f "Total incomes: $ { incomes } " ) Total incomes: $800 >>> print ( f "Total expenses: $ { expenses } " ) Total expenses: $300 >>> print ( f "Total profit: $ { incomes - expenses } " ) Total profit: $500 In this example, to compute the expenses, you use the abs() function to get the absolute value of the expenses, which results in a positive value. Finding the Quotient and Remainder in Division: divmod() Python provides a built-in function called divmod() that takes two numbers as arguments and returns a tuple with the quotient and remainder that result from the integer division of the input numbers: Python >>> divmod ( 8 , 4 ) (2, 0) >>> divmod ( 6.5 , 3.5 ) (1.0, 3.0) With integers as arguments, the result is the same as (a // b, a % b) . With floating-point numbers, the result is (q, a % b) , where q is usually math.floor(a / b) , but may be 1 less than that. As a practical example of when to use this function, say that you want to code a function that takes a time value in milliseconds and returns a string with the "00:00:00" format. Here’s a possible implementation using the divmod() function: Python >>> def hh_mm_ss ( milliseconds ): ... seconds = round ( milliseconds / 1000 ) ... minutes , seconds = divmod ( seconds , 60 ) ... hours , minutes = divmod ( minutes , 60 ) ... return f " { hours : 02d } : { minutes : 02d } : { seconds : 02d } " ... >>> hh_mm_ss ( 10000 ) '00:00:10' >>> hh_mm_ss ( 68000 ) '00:01:08' >>> hh_mm_ss ( 3680000 ) '01:01:20' In this function, you first convert the input milliseconds to seconds and round the result to the nearest whole number. Then, you use divmod() to divide the total seconds by 60 because there are 60 seconds in a minute. This computation gives you the minutes and the remaining seconds. Finally, you use divmod() again to divide the minutes by 60 because there are 60 minutes in an hour. This time, you get the hours and the remaining minutes. Remove ads Finding Minimum and Maximum Values: min() and max() Sometimes, you need to find the smallest and largest values in an iterable or in a series of values. These can be common computations in programming, and Python has built-in functions for them. Note: To learn more about the min() and max() functions, check out the Python’s min() and max() : Find Smallest and Largest Values tutorial. The min() function allows you to find the minimum value in an iterable, while the max() function helps you find the maximum value. Here’s the signature of both functions: Python min ( iterable , * [, default , key ]) max ( iterable , * [, default , key ]) Both functions take a required argument called iterable and return the minimum and maximum values, respectively. They also take two optional keyword-only arguments: Argument Description default Can hold the value you want to return if the input iterable is empty key Accepts a single-argument function to customize the comparison criteria Here are some quick examples of how to use the min() and max() functions with different sets of arguments: Python >>> min ([ 1 , 2 , 3 , 4 ]) 1 >>> max ([ 1 , 2 , 3 , 4 ]) 4 >>> min ( 1 , 2 , 3 , 4 ) 1 >>> max ( 1 , 2 , 3 , 4 ) 4 >>> min ([], default = 0 ) 0 >>> max ([], default = 0 ) 0 >>> min ([ - 2 , 3 , 4 , - 5 , 1 ], key = abs ) 1 >>> max ([ - 2 , 3 , 4 , - 5 , 1 ], key = abs ) -5 In the first two examples, you use min() and max() with a list of numbers. You can also use these functions with a series of positional arguments . Then, you have two examples of using the default argument to return a suitable value when the input iterable is empty. Finally, you have two examples of using the key argument. In these examples, you use the abs() function to provide the comparison criteria. Computing Powers: pow() When you need to compute powers in your code, you can use the built-in pow() function. This function takes a number and raises it to a given power. Here’s the function’s signature: Python pow ( base , exp [, mod = None ]) When you call pow() , you get base to the power of exp . With these two arguments, pow() is equivalent to something like base**exp : Python >>> pow ( 2 , 8 ) 256 >>> 2 ** 8 256 This operation computes 2 to the power of 8 , which is 256 . This is equivalent to a power operation with the ** operator , which you’ll find more often in real-world code. The mod argument allows you to do something like pow(base, exp) % mod but computed more efficiently: Python >>> import timeit >>> base = 2 >>> exp = 1000000 >>> mod = 1000000 >>> timeit . timeit ( ... "pow(base, exp, mod)" , globals = globals (), number = 10 ... ) * 1000 0.021042011212557554 >>> timeit . timeit ( ... "pow(base, exp) % mod" , globals = globals (), number = 10 ... ) * 1000 61.956208024639636 In this example, you use the timeit() function from the timeit module to measure the computation speed. Then, you define a few variables to do the computation. In the first call to timeit() , you use the mod argument. In the second call, you use the modulo operator ( % ) . When you compare the resulting time consumption, you can conclude that using the mod argument is way faster than computing the power and then applying the modulo operator like in pow(base, exp) % mod . Remove ads Rounding Numbers: round() Python’s built-in round() function takes a numeric argument and returns it rounded to a given number of digits. Note: To learn more about rounding numbers and the round() function, check out the How to Round Numbers in Python tutorial. The signature of round() is shown in the code below: Python round ( number [, ndigits ]) In this signature, number is typically a floating-point number, while ndigits is an optional argument that should be an integer number. This latter argument will define the precision or number of digits after the decimal point. Here are a few examples: Python >>> from math import pi >>> pi 3.141592653589793 >>> round ( pi , 2 ) 3.14 >>> round ( pi , 4 ) 3.1416 >>> round ( pi , 6 ) 3.141593 In these examples, you use the pi constant from the math module and the round() function to express the number using different precision. When you use round() with a single argument, you may get surprising results: Python >>> round ( 1.5 ) 2 >>> round ( 2.5 ) 2 In these two examples, the round() function rounds 1.5 up to 2 and 2.5 down to 2 . This is because round() rounds to the closest multiple of 10 to the power minus ndigits . If two multiples are equally close, rounding is done toward the even choice. This rounding half to even strategy helps mitigate rounding bias. That’s why 2.5 rounds to 2 rather than 3 . Calculating Totals: sum() Python’s built-in sum() function provides an efficient and Pythonic way to sum a list of numeric values, which is also a common intermediate step in many computations. So sum() is a pretty handy tool for a Python programmer. Note: To dive deeper into how to use sum() , check out the Python’s sum() : The Pythonic Way to Sum Values tutorial. The sum() function allows you to add together a series of values. Its signature is like the following: Python sum ( iterable [, start = 0 ]) You can call sum() with the following two arguments: Argument Description iterable A required argument that can hold any Python iterable. start An optional argument that can hold an initial value. When you call sum() , the function internally adds start plus the values in iterable . The items in the input iterable are usually numeric values. However, you can also use lists or tuples. The start argument can accept a number, list, or tuple, depending on what your iterable contains. Here are a few examples of how to use sum() with different inputs: Python >>> sum ([]) 0 >>> sum ([ 1 , 2 , 3 , 4 , 5 ]) 15 >>> sum ([ 1 , 2 , 3 , 4 , 5 ], 100 ) # As a positional argument 115 >>> sum ([ 1 , 2 , 3 , 4 , 5 ], start = 100 ) # As a keyword argument 115 >>> num_lists = [[ 1 , 2 , 3 ], [ 4 , 5 , 6 ]] >>> sum ( num_lists , start = []) [1, 2, 3, 4, 5, 6] >>> num_tuples = (( 1 , 2 , 3 ), ( 4 , 5 , 6 )) >>> sum ( num_tuples , start = ()) (1, 2, 3, 4, 5, 6) When you call sum() with an empty iterable, you get 0 as a result because that’s the default value of start . Calling the function with a list of values returns the total sum of the provided values. If you want to use a start value other than 0 , then you can provide it as a positional or keyword argument. However, the latter approach is more readable. The final two examples show that you can also use sum() to concatenate lists and tuples. Note that for this trick to work, you need to set start to the appropriate object. If you want to concatenate lists, then start must hold a list, and so on. Even though this trick works, the practice isn’t efficient or common. Instead, you should use the plus operator ( + ) for regular concatenations. A classic example of using sum() is when you need to compute the mean or average of several numeric values. In this situation, you need to sum the input data as an intermediate step. Here’s an example: Python mean.py def mean ( values ): try : return sum ( values ) / len ( values ) except ZeroDivisionError : raise ValueError ( "mean() arg shouldn't be empty" ) from None In this mean() function, you use sum() to sum the input values and then divide the result by the number of values in the input data. Remove ads Creating and Manipulating Basic Data Types Python has several built-in functions that allow you to manipulate basic data types , such as integer and floating-point numbers, strings , and Boolean values. Here’s a summary of the built-in functions that help you process basic data types: Function Description int() Constructs an integer object from a number or string bin() Converts an integer to a binary string oct() Converts an integer to an octal string hex() Converts an integer to a hexadecimal string float() Constructs a floating-point object from a number or string complex() Constructs a complex number from arguments str() Creates a string object repr() Creates a developer-friendly string representation of an object bool() Converts an argument to a Boolean value ord() Looks up the integer code point of a character chr() Looks up the character for the given integer code point bytes() Creates a bytes object (similar to bytearray , but immutable) bytearray() Creates an object of the bytearray class In the following sections, you’ll learn the basics of working with these functions and how to use them in your Python code. Representing Integer Numbers: int() , bin() , oct() , and hex() Integer numbers are pretty useful in programming. Python has a built-in data type called int that represents integers. When working with integers, sometimes you need to express them in different bases like 2 , 8 , or 16 . You may also need to convert strings or other numeric types to integers. For the latter task, you can use the built-in int() function. Here are some examples of using it: Python >>> int () 0 >>> int ( 42.42 ) 42 >>> int ( "42" ) 42 >>> int ( "42.42" ) Traceback (most recent call last): ... ValueError : invalid literal for int() with base 10: '42.42' >>> int ( "one" ) Traceback (most recent call last): ... ValueError : invalid literal for int() with base 10: 'one' With no argument, int() returns 0 . This behavior is especially useful when you need a factory function for classes like defaultdict from the collections module. With floating-point numbers, int() just removes the decimal part and returns the whole part. Finally, with a string as an argument, int() returns the corresponding integer only if the string represents a valid integer number. You can also use int() to convert a binary , octal , or hexadecimal string representation into an integer number: Python >>> int ( "0b10" , base = 2 ) 2 >>> int ( "0o10" , base = 8 ) 8 >>> int ( "0x10" , base = 16 ) 16 In the first example, you use int() to convert a string representing a number in binary format to its equivalent decimal integer. Note that for this operation to work, you need to set the base argument to the appropriate base, which is 2 for binary numbers. Next, you do similar conversions with octal and hexadecimal strings. Again, you have to set base to the appropriate value. The bin() , oct() , and hex() functions allow you to do the opposite operation. With them, you can convert a given integer into its binary, octal, or hexadecimal representation: Python >>> bin ( 42 ) '0b101010' >>> oct ( 42 ) '0o52' >>> hex ( 42 ) '0x2a' In these examples, you use an integer number as an argument to bin() , oct() , and hex() . As a result, you get the string representation of the input value in binary, octal, and hexadecimal format, respectively. Manipulating Other Numbers: float() and complex() Python has basic built-in types to represent floating-point and complex numbers. These types have associated built-in functions for conversion purposes. So, for floating-point numbers, you have the float() function, and for complex numbers you have complex() . Note: To dive deeper into complex numbers and the complex() function, check out the Simplify Complex Numbers With Python tutorial. Here are the signatures of both functions: Python float ( number = 0.0 ) complex ( real = 0 , imag = 0 ) complex ( string ) The float() function takes a single argument representing a numeric value. This argument accepts numbers or strings that represent valid numbers: Python >>> float () 0.0 >>> float ( 42 ) 42.0 >>> float ( "42" ) 42.0 >>> float ( "3.14" ) 3.14 >>> float ( "one" ) Traceback (most recent call last): ... ValueError : could not convert string to float: 'one' With no arguments, float() returns 0.0 . With integer numbers, it returns the equivalent floating-point number with 0 as the decimal part. With strings representing numbers, float() returns the equivalent floating-point number. However, it fails if the input string doesn’t represent a valid numeric value. The complex() function allows you to work with complex numbers. This function has two different signatures. The first signature has two arguments: Argument Description real The number’s real part imag The number’s imaginary part These arguments accept numeric values, such as integer or floating-point numbers. Here’s how this variation of complex() works: Python >>> complex ( 3 , 6 ) (3+6j) >>> complex ( 1 , 0 ) (1+0j) >>> complex ( 0 , 1 ) 1j >>> complex ( 3.14 , - 2.75 ) (3.14-2.75j) You can call complex() with numeric values, resulting in a complex number. Note that Python uses a j to define the imaginary part. The second signature of complex() takes a single argument that should be a string: Python >>> complex ( "3+6j" ) (3+6j) >>> complex ( "1+0j" ) (1+0j) >>> complex ( "1j" ) 1j >>> complex ( "3.14-2.75j" ) (3.14-2.75j) When you use strings to create complex numbers with complex() , you have to make sure that the input string has a valid format. It should consist of the real part, the sign, and the imaginary part. You can’t add spaces to separate these components. Remove ads Building and Representing Strings: str() and repr() When it comes to creating and working with Python strings, you have two fundamental built-in functions to consider: str() repr() With the str() function, you can create new strings or convert existing objects to strings: Python >>> str () '' >>> str ( 42 ) '42' >>> str ( 3.14 ) '3.14' >>> str ([ 1 , 2 , 3 ]) '[1, 2, 3]' >>> str ({ "one" : 1 , "two" : 2 , "three" : 3 }) "{'one': 1, 'two': 2, 'three': 3}" >>> str ({ "A" , "B" , "C" }) "{'B', 'C', 'A'}" In the first example, you use str() without an argument to create an empty string. In the other examples, you get strings with user-friendly representations of the input objects. For a practical use case, say that you have a list of numeric values and want to join them using the str.join() method, which only accepts iterables of strings. In this case, you can do something like the following: Python >>> "-" . join ( str ( value ) for value in [ 1 , 2 , 3 , 4 , 5 ]) '1-2-3-4-5' In this example, you use a generator expression to convert each number to its string representation before calling .join() . This way, you avoid getting an error in your code. For its part, the built-in repr() function gives you a developer-friendly representation of the object at hand: Python >>> repr ( 42 ) '42' >>> repr ( 3.14 ) '3.14' >>> repr ([ 1 , 2 , 3 ]) '[1, 2, 3]' >>> repr ({ "one" : 1 , "two" : 2 , "three" : 3 }) "{'one': 1, 'two': 2, 'three': 3}" >>> repr ({ "A" , "B" , "C" }) "{'B', 'C', 'A'}" For built-in types, the string representation you get with repr() is the same as the one you get with the str() function. Note: Behind the str() function, you have the .__str__() special method . Similarly, behind repr() , you have the .__repr__() method. To learn more about these special methods, check out the When Should You Use .__repr__() vs .__str__() in Python? tutorial. To see the difference between str() and repr() , consider the following example that uses the datetime module: Python >>> import datetime >>> today = datetime . datetime . now () >>> repr ( today ) 'datetime.datetime(2024, 7, 1, 12, 38, 53, 180208)' >>> str ( today ) '2024-07-01 12:38:53.180208' The repr() method gives you a developer-friendly string representation of the datetime object. Ideally, you should be able to re-create the object using this representation. In other words, you should be able to copy and paste the resulting representation to re-create the object. That’s why this string representation is said to be developer-friendly. In contrast, the string representation that you get from calling str() should aim to be readable and informative for end users. Processing Boolean Values: bool() Python’s built-in bool() function allows you to determine the truth value of any Python object. It’s a predicate function because it always returns True or False . To figure out if an object is falsy , in other words, whether bool() returns False when applied to the object, Python uses the following internal rules: Constants that are defined to be false: None and False The zero of any numeric type: 0 , 0.0 , 0j , Decimal(0) , Fraction(0, 1) Empty sequences and collections: '' , () , [] , {} , set() , range(0) The rest of the objects are considered truthy in Python. Custom objects are considered truthy by default unless they provide a .__bool__() special method that defines a different behavior. Note: To learn more about Boolean values and logic, check out the Python Booleans: Use Truth Values in Your Code tutorial. Here are a few examples of how bool() works: Python >>> bool () False >>> bool ( 0 ) False >>> bool ( 42 ) True >>> bool ( 0.0 ) False >>> bool ( 3.14 ) True >>> bool ( "" ) False >>> bool ( "Hello" ) True >>> bool ([]) False >>> bool ([ 1 , 2 , 3 ]) True In the first example, you call bool() without an argument and get False as a result. In the rest of the examples, you can confirm that Python consistently applies the rules listed above. In practice, you’ll only need to use bool() when your code explicitly requires a Boolean value instead of a different object. As an example of using bool() , say that you have the following implementation of a stack data structure: Python stack.py class Stack : def __init__ ( self , items = None ): self . items = list ( items ) if items is not None else [] def push ( self , item ): self . items . append ( item ) def pop ( self ): return self . items . pop () def __bool__ ( self ): return bool ( self . items ) In this example, your Stack class implements the .__bool__() special method to support Boolean operations on its objects. This method guarantees that when a given Stack object is empty, the bool() function returns False and True otherwise. Here’s an example: Python >>> from stack import Stack >>> stack = Stack () >>> bool ( stack ) False >>> stack . push ( 4 ) >>> bool ( stack ) True In this code snippet, you first create an empty stack. When you pass this object to bool() , you get False . Then, you push a value into the stack and call bool() again. This time, you get True because the stack isn’t empty anymore. Remove ads Encoding Strings: ord() and chr() Character encoding is an important topic in most programming languages. In Python, strings use the Unicode characters set by default. Each Unicode character has an associated code point , which is an integer number. To get the code point of a given character, you can use the built-in ord() function: Python >>> ord ( "A" ) 65 >>> ord ( "Z" ) 90 >>> ord ( "x" ) 120 >>> ord ( "ñ" ) 241 >>> ord ( "&" ) 38 Every Unicode character has an associated code point that uniquely identifies the character in the Unicode table. In these examples, you use the function to get the code point of a few characters. In practice, you can use the ord() function to implement basic cryptographic techniques, sort strings or characters, validate input characters, and so on. Here’s a quick toy example of a function that only checks whether all the characters in a string are uppercase letters of the English alphabet: Python >>> def is_uppercase ( text ): ... for char in text : ... if not ( 65 <= ord ( char ) <= 90 ): ... return False ... return True ... >>> is_uppercase ( "HELLO" ) True >>> is_uppercase ( "Hello" ) False In this function, you use ord() to determine whether the characters in a string are between 65 and 90 , which is the interval of code points for uppercase letters, A to Z, in the Unicode table. Sometimes, you may need to determine the code point that identifies a given Unicode character. In this situation, you can use the built-in chr() function: Python >>> chr ( 65 ) 'A' >>> chr ( 90 ) 'Z' >>> chr ( 120 ) 'x' >>> chr ( 241 ) 'ñ' >>> chr ( 38 ) '&' The chr() function does the opposite operation of ord() . It allows you to find the code point associated with a specific character. The ord() and chr() functions are sort of complementary, and therefore, you’ll probably find them used together in tandem. Creating Bytes and Byte Arrays: bytes() and bytearray() Python’s bytes and byte arrays are built-in types that Python provides out of the box to manipulate binary data, encode and decode text, process file input and output, and communicate through networks. The bytes data type is immutable , while the bytearray type is mutable . To create objects derived from these data types, you can use the built-in bytes() and bytearray() functions. The bytes() and bytearray() functions have the following signatures: Python bytes ( source = b "" ) bytes ( source , encoding ) bytes ( source , encoding , errors ) bytearray ( source = b "" ) bytearray ( source , encoding ) bytearray ( source , encoding , errors ) Both functions have three different signatures. The first signature of both functions accepts a bytes literal as an argument. These literals are similar to string literals, but they start with a b and only accept ASCII characters. Here’s a summary of the arguments and their meaning: Argument Description source A bytes literal or a string encoding The character encoding to use for decoding source if it holds a string errors A handler for encoding and decoding errors The encoding argument is only required if the source argument is a string, in which case, you must provide the appropriate encoding so that Python can convert the string into bytes. Finally, the errors arguments is also optional and should hold one of the following error handlers: Handler Description "strict" Raises a UnicodeDecodeError or UnicodeEncodeError exception when encoding problems appear "ignore" Ignores the characters that can’t be encoded "replace" Replaces the characters that can’t be encoded with a question mark ( ? ) "xmlcharrefreplace" Replaces the characters that can’t be encoded with an XML character reference "backslashreplace" Replaces the characters that can’t be encoded with Python’s string backslash escape sequences By choosing the appropriate error handlers, you can set up a good strategy for those situations when you call the bytes() and bytearray() functions with erroneous data. Here are a few examples of using the bytes() and bytearray() functions: Python >>> bytes () b'' >>> bytes ( b "Using ASCII characters or bytes \xc3\xb1 " ) b'Using ASCII characters or bytes \xc3\xb1' >>> bytes ( "Using non-ASCII characters: ñ Ł" , encoding = "utf-8" ) b'Using non-ASCII characters: \xc3\xb1 \xc5\x81' >>> bytearray () bytearray(b'') >>> bytearray ( b "Using ASCII characters or bytes \xc3\xb1 " ) bytearray(b'Using ASCII characters or bytes \xc3\xb1') >>> bytearray ( "Using non-ASCII characters: ñ Ł" , encoding = "utf-8" ) bytearray(b'Using non-ASCII characters: \xc3\xb1 \xc5\x81') In these examples, you create bytes and bytearray objects using bytes literals, and strings with the correct encoding as an argument. Note that you can call the bytes() function with no arguments to create an empty bytes object. Note: To learn more about working with bytes and bytearray , check out these tutorials: Bytes Objects: Handling Binary Data in Python Python’s Bytearray: A Mutable Sequence of Bytes Now consider the following examples that show how to use error handlers: Python >>> bytes ( ... "Using non-ASCII characters with the ASCII encoding: ñ Ł" , ... encoding = "ascii" ... ) Traceback (most recent call last): ... UnicodeEncodeError : 'ascii' codec can't encode character '\xf1' in position 52: ordinal not in range(128) >>> bytes ( ... "Using non-ASCII characters with the ASCII encoding: ñ Ł" , ... encoding = "ascii" , ... errors = "ignore" ... ) b'Using non-ASCII characters with the ASCII encoding: ' >>> bytes ( ... "Using non-ASCII characters with the ASCII encoding: ñ Ł" , ... encoding = "ascii" , ... errors = "replace" ... ) b'Using non-ASCII characters with the ASCII encoding: ? ?' >>> bytes ( ... "Using non-ASCII characters with the ASCII encoding: ñ Ł" , ... encoding = "ascii" , ... errors = "xmlcharrefreplace" ... ) b'Using non-ASCII characters with the ASCII encoding: &#241; &#321;' >>> bytes ( ... "Using non-ASCII characters with the ASCII encoding: ñ Ł" , ... encoding = "ascii" , ... errors = "backslashreplace" ... ) b'Using non-ASCII characters with the ASCII encoding: \\xf1 \\u0141' In these examples, you only use bytes() because bytearray() would work similarly. The only difference is that bytes() returns immutable objects while bytearray() returns mutable ones. These examples use non-ASCII characters with the ASCII encoding, which will cause encoding errors that you’ll need to handle. The default value of the errors argument is "strict" . That’s why you get a UnicodeEncodeError exception in the first example above. Then you set errors to "ignore" so that Python ignores any encoding error. In this case, the ñ and Ł characters are removed. If you set errors to "replace" , then ñ and Ł are each replaced with a question mark. Using "xmlcharrefreplace" as the error handler makes Python replace the ñ and Ł characters with their respective XML character reference. Finally, using "backslashreplace" escapes the problematic characters by using the appropriate escape sequence. Remove ads Creating Collection Data Types A fundamental feature of Python is the rich set of collection data types built into the language. You’ll have several built-in functions that allow you to manipulate these data types, which include lists, tuples, dictionaries, sets, and bytes. Here’s a summary of the built-in functions that help you process collection data types: Function Description list() Creates a list object from an iterable tuple() Creates a tuple object from an iterable dict() Creates a dict object from a series of key-value pairs or keyword arguments set() Creates a set object from an iterable frozenset() Creates a frozenset object from an iterable In the following sections, you’ll learn the basics of working with these functions and using them to create and manipulate collections in your Python code. Creating Lists and Tuples: list() and tuple() Python’s list is a fundamental built-in data type with an impressive set of features. Lists are mutable and allow you to efficiently organize and manipulate data that can be heterogeneous but is typically homogeneous. For example, you can use a list to store a column from a database table. Note: To learn more about working with lists and the list() function, check out Python’s list Data Type: A Deep Dive With Examples tutorial. Similarly, Python’s tuple is another built-in type. Unlike lists, tuples are immutable. You can use them to organize data that can be homogeneous but is typically heterogeneous. For example, you can use a tuple to store a row from a database table. Note: To learn more about working with tuples and the tuple() function, check out Python’s tuple Data Type: A Deep Dive With Examples tutorial. Python’s built-in list() and tuple() functions allow you to create list and tuple objects. The list() function takes an iterable as an argument and returns a list object built out of the input data. So, its signature looks something like the following: Python list ([ iterable ]) Note that the square brackets around iterable mean that the argument is optional , so the brackets aren’t part of the syntax. Note: In practice, list() is a class constructor rather than a function. However, the Python documentation calls it a function. Here are a few examples of using list() to create list objects: Python >>> list () [] >>> list ( "Hello" ) ['H', 'e', 'l', 'l', 'o'] >>> list (( 1 , 2 , 3 , 4 , 5 )) [1, 2, 3, 4, 5] >>> list ({ "circle" , "square" , "triangle" , "rectangle" , "pentagon" }) ['square', 'rectangle', 'triangle', 'pentagon', 'circle'] >>> list ({ "name" : "John" , "age" : 30 , "city" : "New York" }) ['name', 'age', 'city'] >>> list ({ "name" : "John" , "age" : 30 , "city" : "New York" } . keys ()) ['name', 'age', 'city'] >>> list ({ "name" : "John" , "age" : 30 , "city" : "New York" } . values ()) ['John', 30, 'New York'] >>> list ({ "name" : "John" , "age" : 30 , "city" : "New York" } . items ()) [('name', 'John'), ('age', 30), ('city', 'New York')] When you call list() without an argument, you create a new empty list. When you use a string as an argument, you create a list of characters. When you use a tuple, you convert the tuple into a list. Note: In most cases, you’ll use a pair of square braces, [] , to create an empty list. However, in some situations, using list() can be more readable or explicit. The list() function even accepts sets, but you need to remember that sets are unordered data structures, so you won’t be able to predict the final order of items in the resulting list. When it comes to using dictionaries with list() , you have four possibilities. You can create a list of keys using the dictionary directly or using its .keys() method. If you want to create a list of values, then you can use the .values() method. Finally, if you want to create a list of key-value pairs, then you can use the .items() method. Lists have many use cases in Python code. They’re flexible, powerful, and feature-full, so you’ll find them in almost every piece of Python code. Tuples are commonly used to store heterogeneous and immutable data. The tuple() function allows you to create tuples on the fly. Here’s the signature: Python tuple ([ iterable ]) The square brackets around iterable mean that the argument is optional , so the brackets aren’t part of the syntax. Consider the following examples of using tuple() in your code: Python >>> tuple () () >>> tuple ( "Hello" ) ('H', 'e', 'l', 'l', 'o') >>> tuple ([ "Jane Doe" , 25 , 1.75 , "Canada" ]) ('Jane Doe', 25, 1.75, 'Canada') >>> tuple ({ ... "manufacturer" : "Ford" , ... "model" : "Mustang" , ... "color" : "Blue" , ... } . values ()) ('Ford', 'Mustang', 'Blue') You can use tuple() with no arguments to create an empty tuple. This will be more readable than using an empty pair of parentheses () . When you pass a string into tuple() , you get a tuple of characters. In the third example, you use tuple() to convert a list of heterogeneous data into a tuple, which would be a more appropriate data structure for storing this type of data. Finally, you use the values of a dictionary to build a tuple. Just like lists, tuples are pretty useful in Python. You’ll see them used in many use cases, especially in those situations where you need to store immutable heterogeneous data. Remove ads Constructing Dictionaries: dict() Dictionaries are a fundamental built-in data structure in Python. They’re everywhere and a core part of the language itself. You’ll find many use cases for dictionaries in your code. As for other built-in collections, Python also has a built-in function that allows you to create dictionaries: the dict() function. Note: To learn more about dictionaries and the dict() function, check out the Dictionaries in Python tutorial. The dict() function has the following signatures: Python dict ( ** kwargs ) dict ( mapping , ** kwargs ) dict ( iterable , ** kwargs ) All these signatures accept what is known as keyword arguments ( **kwargs ) or named arguments. The second signature takes a mapping, which can be another dictionary. Finally, the third signature accepts an iterable of key-value pairs, which can be a list of two-item tuples, for example. Here are some quick examples of using the dict() function in different ways: Python >>> dict () {} >>> jane = dict ( name = "Jane" , age = "30" , country = "Canada" ) >>> jane {'name': 'Jane', 'age': '30', 'country': 'Canada'} >>> dict ( jane , job = "Python Dev" ) {'name': 'Jane', 'age': '30', 'country': 'Canada', 'job': 'Python Dev'} >>> dict ([( "name" , "Jane" ), ( "age" , 30 ), ( "country" , "Canada" )]) {'name': 'Jane', 'age': 30, 'country': 'Canada'} Again, when creating an empty dictionary, you can use the dict() function without arguments. This is less common than using a pair of curly brackets {} , but again, it can be more readable and explicit in some contexts. Then, you create a jane dictionary using keyword arguments. This is a clean and elegant way to build dictionaries in Python. The third example shows how you can combine a mapping with keyword arguments to create a new dictionary object. Finally, in the fourth example, you create a new dictionary from a list of tuples. Creating Sets and Frozen Sets: set() and frozenset() Python’s set is a built-in data type for creating collections of unique and hashable objects, typically called elements or members . In Python, sets support the operations defined for mathematical sets, including union , difference , symmetric difference , and others. Python has two types of sets: set frozenset The difference between these two data types is that set objects are mutable, and frozenset objects are immutable. Note: To learn more about sets and the set() function, check out the Sets in Python tutorial. As with other data types, Python also provides built-in functions for creating sets and frozen sets. You’ll have the set() and frozenset() functions, respectively. The signature for these functions is shown below: Python set ([ iterable ]) frozenset ([ iterable ]) Again, the square brackets indicate t | 2026-01-13T08:49:33 |
https://golf.forem.com/code-of-conduct#main-content | Code of Conduct - Golf 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 Golf Forem Close Code of Conduct Last updated July 31, 2023 All participants of DEV Community are expected to abide by our Code of Conduct and Terms of Service , both online and during in-person events that are hosted and/or associated with DEV Community. Our Pledge In the interest of fostering an open and welcoming environment, we as moderators of DEV Community pledge to make participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, gender identity and expression, level of experience, nationality, personal appearance, race, religion, or sexual identity and orientation. Our Standards Examples of behavior that contributes to creating a positive environment include: Using welcoming and inclusive language Being respectful of differing viewpoints and experiences Referring to people by their pronouns and using gender-neutral pronouns when uncertain Gracefully accepting constructive criticism Focusing on what is best for the community Showing empathy towards other community members Citing sources if used to create content (for guidance see DEV Community: How to Avoid Plagiarism ) Following our AI Guidelines and disclosing AI assistance if used to create content Examples of unacceptable behavior by participants include: The use of sexualized language or imagery and unwelcome sexual attention or advances The use of hate speech or communication that is racist, homophobic, transphobic, ableist, sexist, or otherwise prejudiced/discriminatory (i.e. misusing or disrespecting pronouns) Trolling, insulting/derogatory comments, and personal or political attacks Public or private harassment Publishing others' private information, such as a physical or electronic address, without explicit permission Plagiarizing content or misappropriating works Other conduct which could reasonably be considered inappropriate in a professional setting Dismissing or attacking inclusion-oriented requests We pledge to prioritize marginalized people's safety over privileged people's comfort. We will not act on complaints regarding: 'Reverse' -isms, including 'reverse racism,' 'reverse sexism,' and 'cisphobia' Reasonable communication of boundaries, such as 'leave me alone,' 'go away,' or 'I'm not discussing this with you.' Someone's refusal to explain or debate social justice concepts Criticisms of racist, sexist, cissexist, or otherwise oppressive behavior or assumptions Enforcement Violations of the Code of Conduct may be reported by contacting the team via the abuse report form or by sending an email to support@dev.to . All reports will be reviewed and investigated and will result in a response that is deemed necessary and appropriate to the circumstances. Further details of specific enforcement policies may be posted separately. Moderators have the right and responsibility to remove comments or other contributions that are not aligned to this Code of Conduct or to suspend temporarily or permanently any members for other behaviors that they deem inappropriate, threatening, offensive, or harmful. If you agree with our values and would like to help us enforce the Code of Conduct, you might consider volunteering as a DEV moderator. Please check out the DEV Community Moderation page for information about our moderator roles and how to become a mod. Attribution This Code of Conduct is adapted from: Contributor Covenant, version 1.4 Write/Speak/Code Geek Feminism 💎 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 Golf Forem — A community of golfers and golfing enthusiasts 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 . Golf Forem © 2016 - 2026. Where hackers, sticks, weekend warriors, pros, architects and wannabes come together Log in Create account | 2026-01-13T08:49:33 |
https://forem.com/new/node | 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 | 2026-01-13T08:49:33 |
https://dev.to/aniruddhaadak/the-future-according-to-demis-hassabis-key-predictions-on-agi-agents-and-the-ferocious-race-4313 | The Future According to Demis Hassabis: Key Predictions on AGI, Agents, and the "Ferocious" Race - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse ANIRUDDHA ADAK Posted on Dec 7, 2025 The Future According to Demis Hassabis: Key Predictions on AGI, Agents, and the "Ferocious" Race # ai # google # gemini # podcast In a recent interview with Axios’ Mike Allen, Google DeepMind CEO and newly minted Nobel Laureate Demis Hassabis laid out his vision for the immediate and long-term future of artificial intelligence. From the timeline for AGI to the "radical abundance" awaiting humanity, here are all the major predictions he made. The Next 12 Months: Convergence & Agents Hassabis predicts significant leaps in AI capabilities over the coming year, particularly in how models handle different types of data and perform tasks. Multimodal Convergence: We will see "astonishing" progress in image and video generation as they converge with language models. He points to new interesting capabilities emerging from this cross-pollination [ 06:44 ]. Interactive World Models: DeepMind is working on systems like Genie 3 , an interactive video model. Hassabis predicts we will soon generate videos that we can "walk around" in, like a game or simulation [ 07:00 ]. Reliable Agents: While AI agents currently cannot reliably complete full tasks, Hassabis believes that a year from now, we will have agents that are "close" to reliably accepting and completing entire delegated tasks [ 08:27 ]. The Universal Assistant: The goal for Gemini is to become a "universal assistant" that lives on multiple devices (including glasses) and becomes part of the fabric of everyday life [ 07:36 ]. The Path to AGI (Artificial General Intelligence) One of the most anticipated answers was his timeline for human-level AI. Timeline: Hassabis stated we are "quite close" to AGI, estimating it is 5 to 10 years away [ 21:44 ]. Defining AGI: He defines it as a system with all human cognitive capabilities, specifically including invention and creativity , which current models still lack [ 21:54 ]. The Recipe: While scaling current Large Language Models (LLMs) is critical, Hassabis predicts that one or two more major breakthroughs (on the level of the Transformer or AlphaGo) will be required to reach true AGI, particularly for reasoning and planning [ 23:27 ]. Best and Worst Case Scenarios When asked to strip away the hype, Hassabis offered a stark look at the potential utopian and dystopian outcomes. The "Radical Abundance" (Best Case): He envisions a "post-scarcity era" where AI solves major scientific challenges like curing all diseases, achieving clean energy (fusion/solar), and enabling humanity to travel to the stars and spread consciousness in the galaxy [ 08:55 ]. The Risks (Worst Case): Bio-Risk: He explicitly identified pathogens created by bad actors as a specific bad use case to guard against [ 10:27 ]. Cyber Terror: This is the "most obvious vulnerable vector" and is likely already happening to some degree [ 10:40 ]. Agentic Deviation: As AI becomes more autonomous (agentic), there is a risk it could "deviate" from its original instructions or act in self-interest. He considers the probability of catastrophic failure ("P(Doom)") to be non-zero [ 12:38 ]. The Global AI Race US vs. China: The US and the West currently hold the lead, specifically in algorithmic innovation . However, China is "not far behind"—a matter of months, not years [ 13:33 ]. The Bubble: While acknowledging that some seed rounds (e.g., $50M valuations for early ideas) might be a bubble, he maintains that because AI is the most transformative technology in history, the investment will be "more than justified" in the fullness of time [ 24:25 ]. Gaming and Creativity Drawing on his background as a game developer, Hassabis made a specific prediction about the future of software creation. Commercial Games in Hours: We are very close to models that can "one-shot" commercial-grade games . He predicts users will soon be able to "vibe code" games in a few hours that previously took years to develop [ 17:35 ]. Human Adaptability Keeping Up: Despite the speed of the revolution (potentially 10x faster than the Industrial Revolution), Hassabis believes humans are "infinitely adaptable." He suggests we might eventually use technologies like Brain-Computer Interfaces (BCI) to augment ourselves and keep pace with AGI [ 28:18 ]. Let me know what you find most valuable and exciting, with comments below. Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse ANIRUDDHA ADAK Follow AI Agent Engineer focused on creating self-directed AI systems that learn, adapt, and execute multi-step tasks without human intervention. Joined Nov 11, 2024 More from ANIRUDDHA ADAK How to Create Hollywood Shots with AI using Higgsfield Cinema Studio # ai # video # generativeai # filmmaking I Created 50 Posts About AI Visuals :) Here's What I Learned # ai # discuss # career # beginners Smart Task Management API: AI-Driven Productivity Backend with Xano # devchallenge # xanochallenge # ai # backend 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/aminboutarfi/the-tradeoffs-behind-ai-agents-1135 | The Tradeoffs Behind AI Agents - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Amin Boutarfi Posted on Dec 21, 2025 The Tradeoffs Behind AI Agents # ai # llm # rag # agents AI agents are powerful, practical, and already being used in real-world systems — from automation and research to coding and multi-step reasoning. In this video, we do not argue against AI agents. Instead, we take an engineering-first approach. We break down how AI agents actually work under the hood — autonomy, Chain-of-Thought, tool use, memory, planning, exploration, and stochastic sampling — and explain the tradeoffs each design choice introduces. Every increase in capability comes with a cost: more autonomy means less reliability deeper reasoning increases error propagation and cost tool use adds latency and brittleness memory improves continuity but increases hallucination risk AI agents are extremely useful and will continue to shape modern systems. But understanding them through tradeoffs is what allows engineers to build reliable, scalable, production-grade solutions. Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Amin Boutarfi Follow Backend & GenAI Engineer Joined Nov 15, 2024 Trending on DEV Community Hot I Didn’t “Become” a Senior Developer. I Accumulated Damage. # programming # ai # career # discuss Top 7 Featured DEV Posts of the Week # top7 # discuss If a problem can be solved without AI, does AI actually make it better? # ai # architecture # discuss 💎 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 | 2026-01-13T08:49:33 |
https://www.linkedin.com/company/xvertice | Xvertice | LinkedIn Skip to main content LinkedIn Top Content People Learning Jobs Games Sign in Join now Xvertice Technology, Information and Internet Building explainable fake image detection Follow Discover 1 employee Report this company About us Building explainable fake image detection. Website https://x-vertice.com/ External link for Xvertice Industry Technology, Information and Internet Company size 2-10 employees Type Public Company Employees at Xvertice Het Suthar Priyansh Uttamchandani See all employees Updates Xvertice reposted this Xvertice 8 followers 2d Edited Report this post Today, we’re sharing an experimental demo from Xvertice that explores a different way of thinking about image trust. Manipulated and AI-generated images are becoming increasingly difficult to identify, yet most existing approaches try to reduce this complexity to a simple “real or fake” answer. We intentionally avoid binary conclusions. Instead, the focus is on giving users context and information that helps them make their own judgment. The goal is to surface what looks normal, what raises questions, and why using explainable forensic signals that support human reasoning rather than replacing it. This is a very early experimental demo. Errors, blind spots, and limitations are expected at this stage. We’re sharing it publicly to learn edge cases, failure modes, and critical feedback are far more valuable to us than polished outcomes. If you work in media, research, or trust & safety, we’d especially value your perspective. A deeper explanation of the motivation and thinking behind this work is available in the linked article. Go check it out here - https://x-vertice.com/ 7 1 Comment Like Comment Share Xvertice 8 followers 2d Edited Report this post Today, we’re sharing an experimental demo from Xvertice that explores a different way of thinking about image trust. Manipulated and AI-generated images are becoming increasingly difficult to identify, yet most existing approaches try to reduce this complexity to a simple “real or fake” answer. We intentionally avoid binary conclusions. Instead, the focus is on giving users context and information that helps them make their own judgment. The goal is to surface what looks normal, what raises questions, and why using explainable forensic signals that support human reasoning rather than replacing it. This is a very early experimental demo. Errors, blind spots, and limitations are expected at this stage. We’re sharing it publicly to learn edge cases, failure modes, and critical feedback are far more valuable to us than polished outcomes. If you work in media, research, or trust & safety, we’d especially value your perspective. A deeper explanation of the motivation and thinking behind this work is available in the linked article. Go check it out here - https://x-vertice.com/ 7 1 Comment Like Comment Share Xvertice reposted this Krish S. Prajapati Brand partnership 2w Report this post Recent Branding Work for xvertice 14 Like Comment Share Join now to see what you are missing Find people you know at Xvertice Browse recommended jobs for you View all updates, news, and articles Join now Similar pages Agilescript Innovations Private Limited Information Technology & Services Vadodara, Gujarat Armakuni IT Services and IT Consulting London, London Fluid Studio Technology, Information and Internet Bangalore, Karnataka KERYAR IT Services and IT Consulting Anand, Gujarat BrandSek Computer and Network Security Newark, Delaware AWS User Group Vadodara Information Technology & Services Vadodara, Gujarat Hypercubic (YC F25) Technology, Information and Internet Swan Softweb Solutions Information Technology & Services New York, New York NamasteDev.com E-Learning Providers Dehradun, Uttarakhand KMK Consulting Inc. Business Consulting and Services Morris Plains, New Jersey, Show more similar pages Show fewer similar pages LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Sign in to see who you already know at Xvertice Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T08:49:33 |
https://dev.to/lingarao_yechuri_2f59259c/navigating-long-ai-chats-is-broken-so-i-built-a-chrome-extension-to-fix-it-54j#main-content | Navigating Long AI Chats Is Broken — So I Built a Chrome Extension to Fix It - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Lingarao Yechuri Posted on Jan 12 Navigating Long AI Chats Is Broken — So I Built a Chrome Extension to Fix It # chatgpt # gemini # productivity # ux If you regularly use ChatGPT, Claude, or Gemini, you’ve probably faced this problem 👇 You had an amazing response 50 messages ago , but now: Endless scrolling Cmd/Ctrl + F doesn’t help much Context is lost Gemini loads history lazily, making it even worse Long AI conversations quickly become unusable once they grow past a certain point. The Problem AI chats are great for: Debugging complex issues Research and learning Long brainstorming sessions Iterative prompt refinement But current chat UIs are not designed for long-term navigation . Common issues: No structured overview of prompts Hard to jump between questions Re-finding past answers is painful Each platform handles history differently (especially Gemini) As conversations grow, signal gets buried under noise . The Solution: Prompt Navigation for AI Chats I built a Chrome extension that adds prompt-level navigation to AI chat platforms. Instead of scrolling endlessly, you get: A structured list of prompts One-click jump to any question Faster navigation across long chats A consistent experience across ChatGPT, Claude, and Gemini Think of it as a table of contents for your AI conversation . How It Works The extension: Detects user prompts in the current chat Builds a navigable list in a side panel Lets you instantly jump to any prompt-response pair Works entirely on the client side (no backend, no data leaving your browser) Gemini-specific note Gemini loads older messages dynamically as you scroll. Because of this, the extension can only index the currently loaded prompts . Once you click an older prompt, Gemini loads more history, and the list updates progressively. This is a platform limitation — not a data or permission issue. Use Cases This extension is especially useful if you: Debug long coding sessions Revisit research-heavy conversations Refine prompts over multiple iterations Use AI as a learning or thinking partner Switch between multiple AI platforms daily Instead of restarting chats or copy-pasting summaries, you can navigate and reuse context efficiently . Why I Built This Many people suggest: “Just ask the LLM to summarize and start a new chat.” That works — but it breaks flow. I wanted: Zero disruption No re-prompting No backend APIs A simple UX improvement that should’ve existed by default So I built it. What’s Next I’m actively improving it based on feedback: Better prompt grouping Cross-chat reuse ideas Performance improvements for very long sessions If you spend hours inside AI chats, this extension is meant for you. here is the extension Feedback and suggestions are welcome 👋 Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Lingarao Yechuri Follow I am Web developer Joined Dec 18, 2025 Trending on DEV Community Hot If a problem can be solved without AI, does AI actually make it better? # ai # architecture # discuss Stop Overengineering: How to Write Clean Code That Actually Ships 🚀 # discuss # javascript # programming # webdev When is a side project worth committing to? # ai # gemini # sideprojects # showdev 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/jacksonkasi/beyond-chatbots-building-echo-learn-an-agentic-ai-tutor-with-biological-memory-f38 | 🧠 Beyond Chatbots: Building 'Echo-Learn', an Agentic AI Tutor with Biological Memory - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Jackson Kasi Posted on Dec 26, 2025 🧠 Beyond Chatbots: Building 'Echo-Learn', an Agentic AI Tutor with Biological Memory # ai # gemini # rag # typescript 🚀 The Problem with "Chatting" with PDFs We've all built the standard RAG app: Upload a PDF ✅ Ask a question ✅ Get an answer ✅ It's useful, but it's passive . Real learning isn't passive. A real teacher doesn't just answer; they quiz you, they track your progress, and they remind you when you're about to forget something. I built Echo-Learn to solve this. Echo-Learn is an open-source Agentic RAG Engine designed to turn any document—whether it's a coding manual, a medical textbook, or legal guidelines—into an active, voice-enabled study partner . Here's the deep dive into building an AI that "learns how you learn." 🧠 The Core Concept: "Agentic RAG" + "Biological Memory" Echo-Learn isn't just a wrapper around an LLM. It combines two powerful concepts: Concept What It Means Mode-Aware Agency The AI switches gears between "Casual Chat" (low latency) and "Deep Learning" (analytical, saves progress) Smart Memory Clusters Uses the Ebbinghaus Forgetting Curve to predict when you'll forget a fact and schedules reviews 🛠️ The Architecture & Code The stack is built on: 🧠 Google Gemini 3 Flash → Reasoning 💾 Upstash Redis → Memory & State 📐 Upstash Vector → Hybrid Search (Vectors + BM25) 👁️ Mistral OCR → Document Understanding 🔊 ElevenLabs → Real-time Voice Streaming Let's look at the code. 1️⃣ The "Echo" Mechanism: Coding the Forgetting Curve The heart of Echo-Learn is its ability to track Mastery . We don't just store what you know; we store how well you know it and when you last recalled it. We implemented a decay algorithm directly in our storage layer: 📁 packages/storage/src/redis/mastery.ts const DECAY_RATE = 0.1 ; // λ - controls how fast you forget function calculateEffectiveMastery ( storedMastery : number , lastInteractionDate : Date ): number { const daysSince = daysBetween ( lastInteractionDate , new Date ()); // Exponential decay: Mastery drops over time without review // Formula: M = S × e^(-λt) const decayFactor = Math . exp ( - DECAY_RATE * daysSince ); return storedMastery * decayFactor ; } Enter fullscreen mode Exit fullscreen mode 🎯 How It Works In Practice: Day 0: You learn "React Hooks" → Mastery = 100% Day 5: You haven't reviewed it → Mastery decays to ~60% ↓ Echo-Learn: "Quick quiz on useEffect before we continue?" Enter fullscreen mode Exit fullscreen mode The AI doesn't wait for you to ask—it proactively teaches . 2️⃣ The Brain: Mode-Aware Agentic Strategy A study partner needs to know when to lecture and when to listen. We built a Mode-Aware Strategy using Vercel AI SDK's ToolLoopAgent . 📁 packages/agentic/src/strategies.ts export async function executeUnifiedAgenticStrategy ( query : string , options : ModeAwareQueryOptions ) { // The AI decides: Are we chatting, or are we LEARNING? const mode = options . mode || " learn " ; // Different modes get different prompts & tools const systemPrompt = buildModeSystemPrompt ( mode , modeResult , userProfile ); const agent = new ToolLoopAgent ({ model : google ( " gemini-3-flash-preview " ), tools : getToolsForMode ( allTools , mode ), // Dynamic tool selection per step prepareStep : ({ stepNumber }) => { if ( stepNumber === 0 ) return { toolChoice : " required " }; // Force RAG search return { toolChoice : " auto " }; // Then let AI decide }, }); } Enter fullscreen mode Exit fullscreen mode 💬 The Personality Switch: Mode Behavior Example Response Chat Fast, casual, no tracking "React is a UI library." Learn Deep, contextual, saves progress "React is a UI library. You struggled with State management yesterday—let me connect this concept to that..." 3️⃣ The Eyes: Semantic Chunking for Complex Docs Textbooks have structure. If you just chop them into arbitrary 500-char blocks, you lose the lesson . We use Semantic Chunking that detects topic shifts: 📁 packages/ingest/src/chunker/semantic-chunker.ts function findTopicBreakPoints ( sentences : SentenceInfo [], threshold : number ): number [] { const breakPoints : number [] = []; for ( let i = 2 ; i < sentences . length - 1 ; i ++ ) { // Compare text BEFORE and AFTER this point const prevContext = getCombinedText ( sentences , i - 2 , i ); const nextContext = getCombinedText ( sentences , i , i + 2 ); const similarity = calculateTextSimilarity ( prevContext , nextContext ); // Topic changed? Start a new chunk here. if ( similarity < threshold ) { breakPoints . push ( i ); } } return breakPoints ; } Enter fullscreen mode Exit fullscreen mode This ensures that a "Chapter on Authentication" stays together , not split across 3 random chunks. 4️⃣ The Knowledge: Hybrid Search with Upstash Vector We don't just use semantic similarity. We use Hybrid Search (Vectors + BM25 Keywords). 📁 packages/storage/src/vector/client.ts export async function searchWithEmbedding ( query : string , options : SearchWithEmbeddingOptions = {} ): Promise < Array < VectorSearchResult >> { const { topK = 10 , fusionAlgorithm = " RRF " } = options ; // Upstash handles both dense (semantic) and sparse (BM25) search const results = await vectorIndex . query ({ data : query , // Text → Upstash auto-generates embedding topK , fusionAlgorithm : " RRF " , // Reciprocal Rank Fusion }); return results ; } Enter fullscreen mode Exit fullscreen mode Why Hybrid Matters: Query Type Pure Semantic Hybrid (Semantic + BM25) "What is Form N-648?" ❌ Misses exact term ✅ BM25 catches "N-648" "How do I prove a disability?" ✅ Gets concept ✅ Gets concept + exact forms 💡 Unlimited Use Cases: What Can YOU Build? Echo-Learn is a platform , not just a single app. Swap the knowledge source, and you get a completely different product: 🎓 1. The Ultimate Study Guide Input : University textbooks (Biology, History, Physics) Experience : Upload a chapter → AI quizzes you → Tracks which formulas you keep forgetting → Creates personalized study schedule for finals week 🏢 2. Corporate "Brain" & Onboarding Input : Employee Handbooks, Compliance PDFs, Technical Docs Experience : New hire talks to Echo-Learn instead of reading 50 pages AI : "You read the security policy last week. Do you remember the phishing protocol?" User : "Uh..." AI : "Let's review that section." ⚕️ 3. Medical & Legal Certification Prep Input : DSM-5, Legal Codes, Case Law Experience : Professionals studying for Boards or Bar exams. The "Smart Memory" ensures high-stakes info is retained , not just skimmed. 🛠️ 4. Technical DIY Assistant Input : Car repair manuals, Appliance guides Experience : "I'm under the car—what's the torque spec for this bolt?" → AI retrieves the exact table row and reads it aloud . 📊 The Tech Stack At a Glance Layer Technology Frontend TanStack Start, React 19, Tailwind v4 Backend Hono.js on Bun LLM Google Gemini 3 Flash Voice ElevenLabs Streaming OCR Mistral OCR Vector DB Upstash Vector (Hybrid Index) Cache/State Upstash Redis Storage Google Cloud Storage 🔗 Open Source & Ready to Fork I believe Personalized Education is the killer use case for AI. Echo-Learn is the foundation. It's fully open source. Fork it, plug in your own documents, and you have a custom AI Tutor in minutes. Resource Link 📦 GitHub github.com/jacksonkasi1/echo-learn 🎬 Demo Video YouTube ⭐ Show Some Love If you found this useful, please: Star the repo → It helps others discover Echo-Learn Fork & build → I'd love to see what you create Drop a comment → What would YOU use this for? Let's build the future of learning, one echo at a time. 🔊 Built with ❤️ using Gemini 3, Upstash, Mistral AI, and ElevenLabs Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Jackson Kasi Follow Self-taught tech enthusiast with a passion for continuous learning and innovative solutions Location India Education Completed School, no College but Learner until Death 😎 Work I am try to be an entrepreneur 🎯 Joined Dec 25, 2020 More from Jackson Kasi 🐯 Tiger MCP Blew My Mind – Here's the Visual Layer I'm Building to Complete It # agenticpostgreschallenge # ai # programming # architecture Okay so I forked someone's project and now it's completely different 😅 # webdev # ai # programming # javascript TalkToMyTabs – A Back-to-School AI Reading & Research Assistant # devchallenge # herokuchallenge # webdev # ai 💎 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 Forem — 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 . Forem © 2016 - 2026. We're a place where coders share, stay up-to-date and grow their careers. Log in Create account | 2026-01-13T08:49:33 |
https://dev.to/camptocamp-odoo | Camptocamp Business Solutions - 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 Organization actions Camptocamp Business Solutions When efficiency matters, we help our customers to digitize and optimize their processes. → Odoo Sales Management → Odoo Project Management → Odoo Operations & Logistics → Odoo Finance Accounting → Odoo SmartCamp → Odoo WMS Location Lausanne, Switzerland Joined Joined on Apr 27, 2021 Twitter logo GitHub logo External link icon Support email info@camptocamp.com Meet the team Post 2 posts published Member 4 members oca-port: new OCA tool to help with modules migration Sébastien Alix Sébastien Alix Sébastien Alix Follow Aug 15 '22 oca-port: new OCA tool to help with modules migration # odoo # oca # github # git 7 reactions Comments Add Comment 3 min read Odoo: Customizing the values when timesheeting Damien Crier Damien Crier Damien Crier Follow Mar 9 '22 Odoo: Customizing the values when timesheeting # odoo # widget # tips # camptocamp 12 reactions Comments 2 comments 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 | 2026-01-13T08:49:33 |
https://dev.to/ra101/a-telegrambot-for-true-paranoids-16po | MasquerBot: A Telegram Bot for true paranoids - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Parth Agarwal Posted on Aug 12, 2021 • Edited on Oct 9, 2021 • Originally published at dev.to MasquerBot: A Telegram Bot for true paranoids # telegram # python # showdev # cryptography https://t.me/MasquerBot I watched Snowden in 2016. It was the year, I became paranoid. 👻 Introducing 𝗠𝗮𝘀𝗾𝘂𝗲𝗿𝗕𝗼𝘁! It is a telegram bot that can hide any given text message inside any given image, by manipulating the very pixels of that image (steganography) • URL changes every 6 hrs, with 130 char long, therefore making it impossible to trace by anyone other than Telegram. 𝘍𝘢𝘳 𝘣𝘦𝘵𝘵𝘦𝘳 𝘥𝘰𝘤𝘶𝘮𝘦𝘯𝘵𝘢𝘵𝘪𝘰𝘯 𝘪𝘴 𝘰𝘯 𝘨𝘪𝘵𝘩𝘶𝘣, 𝘭𝘪𝘯𝘬𝘴 𝘢𝘵 𝘵𝘩𝘦 𝘦𝘯𝘥. 📈 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄: • It works by creating an ECDSA encryption 🔑🗝key pair, returns you the 🔑public key, to distribute. • To encrypt, one will have to send your 🔑key along with ✉text and 🖼image. • The bot will encrypt the text and hide it then it will return the 🖼 encode-image. • You as a recipient will send the encoded-image to the bot. and it will take your 🗝private key from the 📒database and will send you the hidden ✉text. PS: Icon is not just eye-candy for otakus. try "/icon" command, within the bot. I bet you will love it. 😉 ⚡𝗟𝗶𝗻𝗸𝘀: Github: https://github.com/ra101/MasquerBot LBRY: https://lbry.tv/@ra101/MasquerBot Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Parth Agarwal Follow On a voyage from the Binary shore to Quantum unknown... Joined Sep 19, 2020 More from Parth Agarwal Boost your Git Squash-Rebase Workflow with these Commands! (auto-squash, auto-commit, auto-rebase, auto-push) # git # productivity # opensource # showdev AR Portfolio App # unity3d # ar # showdev AR Card | AR Portfolio App # ar # blender # unity3d # showdev 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/resumemind/how-to-write-a-resume-that-gets-interviews-not-rejections-127b#7-tailor-your-resume-for-each-job-this-is-critical | How to Write a Resume That Gets Interviews (Not Rejections) - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Resumemind Posted on Jan 12 How to Write a Resume That Gets Interviews (Not Rejections) # career # interview # tutorial Most resumes don’t fail because the candidate is unqualified. They fail because the resume doesn’t communicate value fast enough. Recruiters spend 6–8 seconds scanning a resume before deciding whether to continue or reject it. If your resume doesn’t pass that first scan, it’s over — no matter how skilled you are. This guide will show you step by step how to write a resume that gets interviews, not silent rejections. 1. Understand How Recruiters Actually Read Resumes Before writing anything, you need to understand how resumes are evaluated. Recruiters don’t read resumes line by line. They scan for: Job title relevance Clear role identity Skills that match the job Recent experience or projects Structure and readability If these aren’t obvious in seconds, the resume is rejected. 👉 Your goal is clarity, not creativity. 2. Start With a Clear Role-Focused Resume Header Your resume must immediately answer one question: Who are you professionally? ❌ Weak header John Doe Email | Phone | Location ✅ Strong header John Doe Junior Software Developer | Frontend (Angular) Email | Phone | LinkedIn | Portfolio This instantly tells the recruiter: your level your role your focus Never make recruiters guess. 3. Write a Resume Summary That Sells (Not One That Repeats) Your resume summary is not your life story. It’s a 2–4 line pitch. ❌ Bad summary “Hardworking and motivated individual looking for opportunities to grow.” This says nothing. ✅ Good summary Junior Software Developer with hands-on experience building web applications using Angular and Spring Boot. Strong in problem-solving, REST APIs, and clean UI design. Actively seeking an entry-level role where I can contribute and grow. A good summary: mentions your role highlights key skills shows direction 4. Experience Matters — Even If You Have No Job Experience Many people think: “I can’t write a good resume because I have no experience.” That’s false. Recruiters accept: projects internships freelance work academic projects self-initiated work How to Write Experience Correctly Instead of listing duties, list impact. ❌ Bad: Built a website Worked with Angular ✅ Good: Built a responsive web application using Angular and REST APIs Implemented authentication and improved UI usability If you don’t have job experience, projects become your experience. 5. Skills Section: Be Honest, Relevant, and Specific Your skills section should support your role — not show everything you’ve ever touched. ❌ Bad skills list HTML, CSS, Java, Python, Photoshop, Networking, Excel This looks unfocused. ✅ Good skills list Frontend: Angular, TypeScript, HTML, CSS Backend: Java, Spring Boot, REST APIs Tools: Git, GitHub, Postman Only list skills you’re ready to discuss in an interview. 6. Formatting Can Get You Rejected Instantly Even strong content can fail if formatting is poor. Use: 1 page (for juniors) clear section headings consistent spacing readable font bullet points Avoid: long paragraphs heavy colors icons everywhere photos (unless required) fancy designs that hurt readability A clean resume looks professional and trustworthy. 7. Tailor Your Resume for Each Job (This Is Critical) Using one resume for every job is one of the biggest mistakes job seekers make. You should: adjust your summary reorder skills emphasize relevant projects This doesn’t mean rewriting everything — it means highlighting what matters most for that role. Tailoring your resume alone can double your interview chances. 8. Common Resume Mistakes That Lead to Rejection Avoid these at all costs: No role mentioned Weak or generic summary No projects listed Grammar mistakes Overcrowded layout Irrelevant skills Copy-pasted content Recruiters see these mistakes every day — and reject fast. 9. Get a Second Pair of Eyes on Your Resume One of the best things you can do is get honest feedback. When reviewing resumes manually, the most common missing elements are: unclear role weak summary missing experience descriptions no direction You might not see these issues yourself. Getting your resume reviewed by another person can completely change your results. Final Thoughts A resume that gets interviews is not about being perfect. It’s about being clear, relevant, and honest. If recruiters can quickly understand: who you are what you can do and why you fit the role You’ll start getting callbacks. Next Step If you’re unsure whether your resume is working, get it reviewed before you apply. Often, a few small changes are all it takes to start getting interviews. We offer a free manual resume review , where real people review resumes daily and give honest feedback — not automated scores. 👉 Request a free resume review: https://resumemind.com/public/resume-review Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Resumemind Follow Helping software developers and other related tech experts like project managers, QA, businesses analysts crafting their tech resumes for their next job applications. Joined Jan 4, 2026 More from Resumemind How I Built a Manual Resume Review System with Spring Boot & Angular # angular # career # showdev # springboot I Reviewed 50 Junior Developer Resumes — Here’s What Actually Works # beginners # career # codenewbie How to Write a Resume With No Work Experience (Fresh Graduate Guide for 2026) # beginners # career # tutorial 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/red5/what-is-a-codec-full-codec-comparison-guide-2025-updated-35gl#comments | What Is A Codec? Everything You Need to Know As a Developer in 2025 - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Maria Artamonova for Red5 Posted on Nov 20, 2025 • Originally published at red5.net What Is A Codec? Everything You Need to Know As a Developer in 2025 # livestreaming # software # beginners # learning Live streaming basics (14 Part Series) 1 What Is A Codec? Everything You Need to Know As a Developer in 2025 2 Why Your Users Cannot Perceive Zero Latency: A Scientific Guide for Developers ... 10 more parts... 3 Video Streaming Delay: What Causes It and How to Fix It 4 What Is Transcoding? Essential Basics Every Developer Should Know 5 AV1 vs H.265: Codec Comparison Guide [2025 Updated] 6 What Is MOQ (Media over QUIC) and Why It Matters 7 MOQ vs WebRTC: Why Both Protocols Can And Should Exist In Live Streaming Space In 2025 8 AV1 vs H.264: Codec Comparison Guide [2025 Updated] 9 What is Ultra-Low Latency? Definition, Use Cases, and How to Achieve it [2025] 10 What is WebRTC? Definition, Use cases, How It Works [2025 Updated] 11 Debunking 9 Myths About WebRTC Scalability 12 WebRTC Architecture Explained: P2P vs SFU vs MCU vs XDN 13 How to Use RTSP Protocol in Browsers And Why Direct Integration Isn’t Possible 14 H.264 vs H.265 vs VP9: Which Codec Should You Use in 2026? If you have ever wondered what a codec is and why every device relies on it to play videos, music and images, this blog will walk you through everything you need to know. Learn what codecs are, how they work, why they are important, how codecs are categorized, and what the most common ones are in use today. What is a Codec? A codec is a hardware- or software-based process (or computer program) that compresses and decompresses digital media like video, audio or images so it can be stored, transmitted or played back efficiently. The term codec derives from the words coder and decoder. A codec enables raw media to be reduced in size for delivery or storage and then rebuilt for viewing or listening. Without codecs, virtually no modern streaming, downloads or interactive media would be feasible given the massive volumes of data involved. Why Do We Need Codecs The storage and transmission demands of digital media are enormous. For example, photos, videos and music now occupy the majority of space on people’s phones and laptops. Because of this, codecs are necessary for these reasons: Reduced bandwidth usage: Smaller compressed files consume less network data and enable smoother streaming. Lower storage cost and footprint: Compression allows large media libraries to sit on servers or devices at manageable cost. In a global research study by Western Digital and Researchscape announced in March 2025, 60% of respondents reported they had run out of storage space in the past six months. Faster load times and better user experience: Smaller media files begin playback sooner and use fewer resources. Feasibility of real-time and interactive media: Live streaming, video conferencing and interactive apps rely on codecs optimized for encoding/decompression. Cross-device compatibility and scalability: Standardized codecs ensure media works across phones, browsers, tablets and TVs. How Codecs Work Codecs compress and send media files over a network, where they are decompressed. Source: TechTarget . A codec uses a defined algorithm to convert raw media into a compressed form and later revert it during playback. This process can be described in terms of encapsulation and decapsulation. During encoding the algorithm analyzes the input media, identifies redundant, predictable or perceptually less important data, then converts it into a compact bitstream. This bitstream is encapsulated along with metadata or headers that describe how to decode it. At playback the decoder takes the compressed bitstream, uses the metadata and reconstructed algorithm instructions to decapsulate and rebuild the media for output – this is the decapsulation stage. In video this may involve converting motion compensated blocks, interpolated frames and texture data back into a displayable format. In audio the algorithm may reconstruct waveform samples or frequency domains. While doing this the codec also often supports settings such as key frames, reference frames, intra/inter-frame compression (in video), and variable bitrate versus constant bitrate encoding. The effective compression depends on the algorithm’s sophistication, the amount of redundancy removed, and the quality trade-offs allowed. Hardware acceleration further enables these steps to be executed efficiently on devices with limited CPU resources. In effect, the codec transforms bulky raw media into efficient forms and then restores them for end user consumption with minimal perceptible quality loss. Types of Codecs Codecs can be categorized by several dimensions: By file type: Video, audio, or image. By compression type: Lossy codecs sacrifice some data permanently in exchange for high compression (for example many video and audio streaming codecs). Lossless codecs preserve all input data and allow perfect reconstruction (for example FLAC for audio or PNG for images). By generation / standard age: Legacy standards refer to older, widely implemented codecs (for example MP3 for audio, JPEG for images, H.264 for video). Next-generation codecs refer to newer standards that deliver improved efficiency, higher resolution support, or lower latency (for example AV1 for video, AVIF for images). By licensing model: Open-source / royalty-free codecs are available without costly patents or usage fees (for example VP9, AV1). Proprietary / patent-licensed codecs require licensing and may be subject to royalties (for example H.265/HEVC, some high-end image codecs). There are also deeper categories based on hardware compatibility, target use cases, or encoding profiles. For this blog, we will categorize codecs by file type. Commonly Used Video, Audio, and Image Codecs Many codecs exist, but only a select group dominate modern streaming, broadcasting , video conferencing, and online media delivery. Below is an overview of the most widely used codecs across video, audio, and images today. Video Codecs A video codec is a software or hardware process that compresses or decompresses digital video. Video codecs are employed to reduce the size of video media to take-up less storage when archived and lower bitrates to stream; both yielding cost savings. When you watch a video online, the codec compresses it for sending and then decompresses it for viewing. Codecs are used in streaming, video calls, and everyday video playback. Here’s the list of the most popular video codecs h.264 (AVC) H.264 also called MPEG-4 AVC or Advanced Video Coding – is a block oriented motion compensation-based video compression codec. It is a standard capable of providing good video quality at substantially lower bit rates than previous standards. It can be implemented in a wide variety of networks and systems and is usable with many protocols. Read more in the streaming glossary of our documentation . Read our blogs to learn how H.264 compares to H.265 and VP9 , or how H.264 compares to AV1 in encoding quality, CPU consumption, browser support, licensing, bandwidth savings, and supported streaming protocols. h.265 (HEVC) H.265 codec , also called High Efficiency Video Coding or HEVC for short, is a video compression standard designed as the successor to H.264 (AVC). It roughly doubles the compression efficiency compared to H.264, allowing equivalent video quality at about half the bitrate, or significantly improved quality at the same bitrate. HEVC supports resolutions up to 8K (8192×4320), higher frame rates, wider color gamuts, and high dynamic range (HDR) content, making it well-suited for modern streaming, broadcasting, and storage applications. Learn how it works , or how it compares to H.264 and VP9 , or AV1 from our other blogs. VP8 VP8 codec is a royalty-free video compression standard that enables efficient delivery of high-quality video while minimizing bandwidth requirements. It is widely used in modern streaming and real-time video applications because it provides a good balance between compression efficiency and playback performance. You can learn how it compares to VP9 and AV1 here. VP9 VP9 codec is a royalty-free, open-source video coding standard developed by Google. It emerged as a free competitor to closed-source codecs like H.265. It was designed to meet the demands of modern video content and significantly improve coding efficiency over its predecessor, VP8. Learn how it compares to other video codecs in our blog “ VP9 vs VP8 vs AV1 ”. AV1 AV1 codec is a next-generation, royalty-free video compression standard developed by the Alliance for Open Media (AOMedia). It was designed to deliver significantly better compression efficiency than older codecs like VP9 and H.264 also called AVC, while maintaining high video quality across a wide range of resolutions and devices. AV1 reduces bandwidth consumption, making it ideal for modern streaming platforms, 4K and 8K video, and emerging immersive applications such as VR and AR. To learn how the AV1 codec compares to H.264 , or how AV1 compares to H.265 , AV1 compares to VP9 and VP8 , read our other blogs. AV2 The Alliance for Open Media announced that AV2 will launch by the end of 2025. AV2 is expected to bring further compression improvements over AV1 and support for ultra-high resolution and next-generation use cases. Additional formats/containers to note: While not strictly “video codecs,” formats like MOV and MP4 are widely used containers that hold compressed video streams, often using codecs above. MOV is a legacy container developed by Apple , while MP4 is an ISO standard container widely used for streaming and playback across devices. Audio Codecs An audio codec is a hardware or software process that compresses and decompresses digital audio so it can be streamed, stored, or transmitted efficiently. Audio codecs analyze the audio signal, remove redundant or less perceptible components, and optimize sound quality and file size for playback across devices and networks. Here are common audio codecs: MP3 MP3 is a classic lossy audio codec that dramatically reduced file sizes and enabled digital music distribution. Although newer codecs perform better, MP3 remains nearly universally supported. AAC Advanced Audio Coding is a popular audio codec providing better quality than older standards like MP3 at similar bitrates. It is used widely in streaming services, mobile devices and video playback. Opus Opus audio codec is a royalty-free audio codec designed for both speech and music. It adapts to bandwidth changes, handles low latency well, and is widely used in real-time applications. FLAC Free Lossless Audio Codec is a lossless audio codec that preserves the original sound fully. It is popular for archiving, audiophile playback and professional use. PCM Pulse Code Modulation is an uncompressed audio format often used in professional recording, telephony and broadcasting. It requires large storage but delivers highest fidelity. ALAC Apple Lossless Audio Codec is lossless audio codec developed by Apple that allows full fidelity audio reproduction without any data loss, making it suitable for high-quality music playback and archiving. WMA Windows Media Audio is proprietary audio codec developed by Microsoft used for both lossy and lossless compression in the Windows ecosystem, often seen in Windows-based streaming and media applications. Image Codecs Image codecs handle compression and decompression for still images. They enable faster page load times, more manageable file sizes, and efficient storage of image archives. Unlike video or audio, which involves temporal changes, image codecs focus exclusively on spatial compression (i.e., the content of one frame). Key image codecs include: JPEG JPEG is the most common image codec on the internet. It uses lossy compression to reduce file size while maintaining acceptable visual quality, particularly for photographs. PNG PNG is a lossless image codec that supports transparency and high-quality graphics. It is commonly used for logos, UI elements, screenshots, and images requiring sharp detail. WebP WebP is a modern image codec developed by Google that supports both lossy and lossless compression. It provides smaller file sizes than JPEG and PNG for equivalent quality and is popular in web performance optimization. AVIF AVIF is a newer image codec based on the AV1 video format. It offers excellent compression efficiency and supports advanced features like HDR and wide color gamuts. AVIF files are often much smaller than JPEG or WebP for the same quality. HEIC High Efficiency Image Coding was developed by MPEG/ISO as a modern image container/codec format to store still images and sequences more efficiently than older formats such as JPEG. It supports advanced features like higher bit depths, wide colour gamuts and image sequences, and typically delivers smaller file sizes for equivalent visual quality compared to legacy image codecs. GIF An older codec that supports simple animations. It uses limited color palettes and is less efficient than modern alternatives but remains popular for short animated loops and memes. What Codecs Does Red5 Use? As a live streaming solutions and infrastructure provider, Red5 supports h.264 (AVC), h.265 (HEVC), VP8, VP9 video codecs and Opus audio codec. AV1 codec support in Red5 Pro and Red5 Cloud is coming early 2026. Get in touch with us today to join the waitlist and be among the first to try it. Conclusion What is a codec is a question that underpins how our devices store and stream media, how we share videos and images, and how we listen to audio in everyday life. This blog has provided a thorough, in-depth explanation of codecs. With this foundation, you are better equipped to understand media formats, make informed decisions about technology workflows, and keep pace with the evolving landscape of digital media delivery. Live streaming basics (14 Part Series) 1 What Is A Codec? Everything You Need to Know As a Developer in 2025 2 Why Your Users Cannot Perceive Zero Latency: A Scientific Guide for Developers ... 10 more parts... 3 Video Streaming Delay: What Causes It and How to Fix It 4 What Is Transcoding? Essential Basics Every Developer Should Know 5 AV1 vs H.265: Codec Comparison Guide [2025 Updated] 6 What Is MOQ (Media over QUIC) and Why It Matters 7 MOQ vs WebRTC: Why Both Protocols Can And Should Exist In Live Streaming Space In 2025 8 AV1 vs H.264: Codec Comparison Guide [2025 Updated] 9 What is Ultra-Low Latency? Definition, Use Cases, and How to Achieve it [2025] 10 What is WebRTC? Definition, Use cases, How It Works [2025 Updated] 11 Debunking 9 Myths About WebRTC Scalability 12 WebRTC Architecture Explained: P2P vs SFU vs MCU vs XDN 13 How to Use RTSP Protocol in Browsers And Why Direct Integration Isn’t Possible 14 H.264 vs H.265 vs VP9: Which Codec Should You Use in 2026? Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Red5 Follow Start streaming with Red5 Cloud for free! 50 GBs of streaming and 6,000 instance hours for free each month. No credit card required. Sign up More from Red5 H.264 vs H.265 vs VP9: Which Codec Should You Use in 2026? # livestreaming # software # learning # beginners How to Use RTSP Protocol in Browsers And Why Direct Integration Isn’t Possible # livestreaming # software # learning # beginners WebRTC Architecture Explained: P2P vs SFU vs MCU vs XDN # livestreaming # webrtc # architecture 💎 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 | 2026-01-13T08:49:33 |
https://bizarro.dev.to/t/golf/page/6 | Golf Page 6 - ALTERNATE UNIVERSE DEV 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 ALTERNATE UNIVERSE DEV Close # golf Follow Hide General discussion about the sport of golf Create Post Older #golf posts 1 2 3 4 5 6 7 Posts Left menu 👋 Sign in for the ability to sort posts by relevant , latest , or top . Right menu 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 ALTERNATE UNIVERSE DEV — A constructive and inclusive social network for software developers. With you every step of your journey. 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 . ALTERNATE UNIVERSE DEV © 2016 - 2026. We're a place where coders share, stay up-to-date and grow their careers. Log in Create account | 2026-01-13T08:49:33 |
https://dev.to/camptocamp-odoo/oca-port-new-oca-tool-to-help-with-modules-migration-1aa | oca-port: new OCA tool to help with modules migration - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Sébastien Alix for Camptocamp Business Solutions Posted on Aug 15, 2022 • Edited on Aug 16, 2022 oca-port: new OCA tool to help with modules migration # odoo # oca # github # git The OCA ( Odoo Community Association ) has a new tool: OCA port . It helps forward porting and back porting changes on modules from one branch to another, making module maintenance and migration easier. Story It all started with the migration of an Odoo project composed of roughly ~350 OCA modules from 13.0 to 14.0 back in 2021. As usual with big migrations on active projects, new fixes and improvements were added from time to time even after the migration process began, making already migrated modules on 14.0 outdated. To handle this migration we needed to: migrate OCA modules from 13.0 to 14.0 (as usual), port all fixes and features done in 13.0 on the already migrated 14.0 modules (even more important) make it easy & comfortable for the developer That's how oca-port was born! Quick example Go to a local copy of a repository. Let’s say you want to check if the whole module can be migrated or if some changes need to be ported to the targeted version: $ cd path/to/OCA/stock-logistics-workflow $ oca-port 14.0 15.0 stock_split_picking Enter fullscreen mode Exit fullscreen mode Resulting in this kind of report: stock_split_picking already exists on 15.0, checking PRs to port... 1 pull request(s) related to 'stock_split_picking' to port from origin/14.0 to origin/15.0 1) PR #935 (https://github.com/OCA/stock-logistics-workflow/pull/935) [14.0][FW] stock_split_picking: Port PR from 13.0 to 14.0: By sonhd91, merged at 2021-12-20T08:21:17Z => Not ported: stock_split_picking => 2 commit(s) not (fully) ported Enter fullscreen mode Exit fullscreen mode To process the migration (or the port of missing changes), you pass the fork of the repository on which you have write access (this is the name of your git remote, be sure to add it first): $ git remote add camptocamp git@github.com:camptocamp/stock-logistics-workflow.git $ oca-port 14.0 15.0 stock_split_picking --fork = camptocamp Enter fullscreen mode Exit fullscreen mode The same report will be displayed but this time with a user prompt: [...same report than above...] - Port PR #935 (https://github.com/OCA/stock-logistics-workflow/pull/935) [14.0][FW] stock_split_picking: Port PR from 13.0 to 14.0... Port it? [y/N]: Enter fullscreen mode Exit fullscreen mode Let's port these changes by answering 'yes': - Port PR #935 (https://github.com/OCA/stock-logistics-workflow/pull/935) [14.0][FW] stock_split_picking: Port PR from 13.0 to 14.0... Port it? [y/N]: y Create branch oca-port-pr-935-from-14.0-to-15.0 from origin/14.0... Apply ba5840f8 [FIX] stock_split_picking: README... Apply 2aeeffcf [IMP] stock_split_picking: allow splitting ppickings waiting for other operations... 🎉 Last PR processed! 🎉 Push branch 'oca-port-pr-935-from-14.0-to-15.0' to remote 'camptocamp'? [y/N]: y Create a draft PR from 'oca-port-pr-935-from-14.0-to-15.0' to '15.0' against OCA/stock-logistics-workflow? [y/N]: y PR created => https://github.com/OCA/stock-logistics-workflow/pull/1058 Enter fullscreen mode Exit fullscreen mode Roadmap Blacklist modules and pull requests that shouldn’t be migrated and share this with other contributors by saving these data in a file part of the repository. Improve its usage as a Python package and generate the output as JSON or CSV (this will help to get a report of things that still need to be ported for a bunch of modules for instance, and estimate the work) Visit https://github.com/OCA/oca-port for more details and options! Contributors of this post: Sébastien Alix Simone Orsi Damien Crier Gilles Cherix Denis Leemann Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Camptocamp Business Solutions Follow More from Camptocamp Business Solutions Odoo: Customizing the values when timesheeting # odoo # widget # tips # camptocamp 💎 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 Forem — 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 . Forem © 2016 - 2026. We're a place where coders share, stay up-to-date and grow their careers. Log in Create account | 2026-01-13T08:49:33 |
https://dev.to/voxel51/computer-vision-meetup-its-in-the-air-tonight-sensor-data-in-rag-bha | Computer Vision Meetup: It's in the Air Tonight. Sensor Data in RAG - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Jimmy Guerrero for Voxel51 Posted on Sep 12, 2024 Computer Vision Meetup: It's in the Air Tonight. Sensor Data in RAG # computervision # machinelearning # datascience # ai I will do a quick overview of the basics of Vector Databases and Milvus and then dive into a practical example of how to use one as part of an application. I will demonstrate how to consume air quality data and ingest it into Milvus as vectors and scalars. We will then use our vector database of Air Quality readings to feed our LLM and get proper answers to Air Quality questions. I will show you how to all the steps to build a RAG application with Milvus, LangChain, Ollama, Python and Air Quality Reports. Preview the demo on Medium. About the Speaker Tim Spann is a Principal Developer Advocate for Zilliz and Milvus. He works with Milvus, Generative AI, HuggingFace, Python, Big Data, IoT, and Edge AI. Tim has over twelve years of experience with the IoT, big data, distributed computing, messaging, machine learning and streaming technologies. Not a Meetup member? Sign up to attend the next event: https://voxel51.com/computer-vision-ai-meetups/ Recorded on Sept 12, 2024 at the AI, Machine Learning and Computer Vision Meetup. Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Voxel51 Follow More from Voxel51 Elderly Action Recognition: No One Should Age Alone, AI’s Promise for the Next Generation of Elders # computervision # ai # machinelearning # datascience Journey into Visual AI: Exploring FiftyOne Together — Part IV Model Evaluation # computervision # machinelearning # ai # datascience How to Tame Your (Data) Dragon # computervision # ai # machinelearning # datascience 💎 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 | 2026-01-13T08:49:33 |
https://www.fine.dev/blog/ai-tools-for-programmers#2-cursor | AI for Programmers: Top Tools to Supercharge Your Development Workflow Home Docs Changelog Pricing Sign in Get started -> Menu Home Docs Changelog Pricing <- Go Back AI for Programmers: Top Tools to Supercharge Your Development Workflow AI is reshaping how programmers work, making it easier to handle repetitive tasks, boost productivity, and improve efficiency. This blog will guide you through some of the best AI tools for programmers available today, tailored to help you code faster, debug smarter, and collaborate effectively. Whether you're a beginner or an experienced developer, these platforms can make a real difference in your workflow. Let's get started with Fine. Table of Contents Fine Cursor Replit AI Bolt.new Devin Aider bloop Callstack PR Reviewer OpenHands Zencoder 1. Fine (AI for programmers) Fine is a comprehensive AI-powered software development platform designed to make coding seamless and efficient. By integrating AI Agents , Fine enables programmers to automate repetitive tasks like generating boilerplate code, updating schemas, and managing APIs. Its AI Sandboxing feature allows users to build, run, and test AI-generated code directly in a secure browser-based environment. It's fully mobile friendly and offers powerful integrations with GitHub, Linear and Slack - allowing for full context awareness and maximum collaboration. Highlights: AI Palette for real-time assistance. Integration with GitHub and Linear for end-to-end project management. Specs-driven development ensures alignment with project goals. Fine is designed to empower developers, allowing them to focus on innovation while leaving routine tasks to AI. At just $13-15 per month, it's a deal for any startup looking to save time and ship more. 2. Cursor Cursor offers an AI-powered code editor built on Visual Studio Code (VS Code). It includes features like Cursor Tab for intelligent auto-completion and Chat Integration for codebase-aware interactions. Cursor’s functionality is limited beyond code generation and debugging, and it requires significant configuration for advanced team collaboration. 3. Replit AI Replit AI provides integrated AI capabilities for its cloud-based IDE. It offers code completion, bug fixes, and code generation. Replit AI is heavily tied to its ecosystem and is more suited to beginner-to-intermediate developers than advanced users. 4. Bolt.new (AI for web developers) Bolt.new is an AI agent for web development, allowing developers to build, run, and deploy full-stack applications directly in the browser. Currently in beta, Bolt.new offers limited stability and focuses solely on web development, making it less versatile for other programming needs. 5. Devin Devin by Cognition is an autonomous AI software engineer designed to execute complex engineering tasks. Still in early access, Devin is focused on specific use cases and is less reliable for general-purpose programming. 6. Aider Aider is an open-source AI pair programming tool that integrates with Git repositories for local coding assistance. It requires API keys and setup for AI model integration and is limited to terminal-based interaction, which may not suit all developers. Fine includes unlimited access to leading LLMs such as o1-preview and Claude 3-5 Sonnet, with no need for your own API keys. 7. bloop Bloop specializes in modernizing legacy codebases, particularly COBOL. It offers tools for translating legacy code into modern languages. Bloop is highly specialized for legacy code modernization and offers limited functionality for general-purpose programming. 8. Callstack PR Reviewer This tool automates code reviews, identifying bugs and enforcing coding standards in GitHub and GitLab. Callstack PR Reviewer focuses on pull request reviews and lacks features for standalone development tasks. 9. OpenHands OpenHands provides a zero-setup AI coding experience within a cloud-based Visual Studio Code environment. Dependence on cloud infrastructure may not suit developers working offline or in secure environments, and its focus is limited to AI coding assistance. 10. Zencoder Zencoder uses AI agents to enhance coding workflows, with a focus on syntactic and semantic code analysis. Zencoder primarily supports iterative improvements and lacks versatility for new project creation or diverse programming needs. Why Fine Stands Out as an AI tool for Programmers While each platform offers unique advantages, Fine delivers the most comprehensive AI solution for programmers of all skill levels. Its integration of AI Agents, Sandboxing, and seamless collaboration tools makes it a one-stop shop for development teams. Unlike other platforms, Fine doesn’t compromise on versatility, supporting everything from boilerplate code generation to full project management. Ready to transform your workflow? Sign up for Fine today and experience the best in AI for programmers . The source of information for each platform has been provided in a link. Information was collected on 20.11.24 and may be incorrect, incomplete or out-of-date. Start building today Try out the smoothest way to build, launch and manage an app Try for Free -> © Fine.dev - All rights reserved. Product Overview AI Workflows Pricing & Plans Changelog Blog Docs Company Press Terms & Conditions Privacy policy | 2026-01-13T08:49:33 |
https://dev.to/pravesh_sudha_3c2b0c2b5e0/my-desk-my-journey-css-art-inspired-by-my-remote-devops-workspace-36b8#comments | 🌟 My Desk, My Journey: CSS Art Inspired by My Remote DevOps Workspace - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Pravesh Sudha Posted on Jul 18, 2025 • Edited on Jul 25, 2025 🌟 My Desk, My Journey: CSS Art Inspired by My Remote DevOps Workspace # frontendchallenge # devchallenge # webdev # css Frontend Challenge CSS Art Submission This is a submission for Frontend Challenge: Office Edition sponsored by Axero, CSS Art: Office Culture . 🌟 Inspiration For the past two years, I’ve been working remotely as a Tech Blogger and Freelancer , turning my room into my office with a cozy desk setup that’s been my creative hub. This CSS Art project is a heartfelt recreation of that setup, inspired by the tools and space that fuel my work. My desk isn’t just a workspace—it’s where I’ve grown as a professional, from learning DevOps to launching my YouTube channel to teach DevOps to students worldwide. This year, I’m thrilled to share that I was selected as an AWS Community Builder under the Containers category, a milestone that’s made my desk feel even more like a place of magic and hard work. ✨ Demo 🚀 Journey My journey started two years ago with just a basic laptop, diving into the world of DevOps and Cloud. In January 2024 , disaster struck when my main system crashed, halting my coding for six months. But I didn’t sit idle—I used that time to deepen my knowledge of Networking and Security , which laid a strong foundation for my career. On August 19, 2024 , I upgraded to a MacBook Air M3 , reigniting my freelancing journey and kicking off my content creation on YouTube. My efforts paid off when, in March 2025 , I was honored to be selected as an AWS Community Builder under the Containers category—a proud moment! Bit by bit, I expanded my setup, adding an external monitor, keyboard, mouse, and a comfy chair, all thanks to staying committed to doing the right thing. My desk has been my constant companion, witnessing countless late nights and breakthroughs. While my main focus is DevOps and Cloud, diving into web development for this challenge was a refreshing adventure. Creating this CSS Art taught me so much about animations and positioning, skills I’m excited to keep honing. Along the way, I picked up some cool lessons: I learnt about the amazing animation in the background, didn't knew it would be soo good. The challenging thing was placing the monitor on the screen as the mouse and keyboard were covering it stands. To fix that, I shifted it to the right. Learnt about the concept of layer while designing the welcome screen for laptop and function for the monitor. Overall the project was challenging and exciting at the same time Here's a sneak peek from my Work-station: The image of the CSS art on the monitor was the First draft :) 👨🏽💻 Code Here’s the GitHub repository for my CSS Art: Pravesh-Sudha / dev-to-challenges This is my Github Repo that hosts the source code of Dev.to Challenges View on GitHub Thanks for Reading! I’m grateful you took the time to check out my submission. If you enjoyed my work, feel free to connect with me on my socials: LinkedIn: Pravesh Sudha Twitter/X: @praveshstwt YouTube: Pravesh Sudha Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Pravesh Sudha Follow AWS Community Builder Bridging critical thinking and innovation, from philosophy to DevOps. Location India Education Hindu College, Delhi University, India Pronouns he/him Work Freelance DevOps Engineer At Fiverr Joined Jul 19, 2024 More from Pravesh Sudha 🌟 Story Weaver: An AI-Powered Multimodal App for Crafting and Experiencing Stories # devchallenge # googleaichallenge # ai # gemini 🚀 Midnight Challenge | Build & Run a Sample dApp with React, Flask & Docker # devchallenge # midnightchallenge # web3 # blockchain ✨ How I Built Philosophy AI Agent for WLH Project # devchallenge # wlhchallenge # bolt # ai 💎 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 | 2026-01-13T08:49:33 |
https://docs.devcycle.com/platform/feature-flags/status-and-lifecycle#theme-svg-external-link | Status and Lifecycle | DevCycle Docs Skip to main content Home SDKs APIs Management API Bucketing API Integrations CLI / MCP Best Practices Community Blog Discord Search Sign Up Home Getting Started Essentials DevCycle Overview Key Features System Architecture Feature Hierarchy Feature Types Platform Feature Flags Features Variables and Variations Targeting Status and Lifecycle Stale Feature Notifications Experimentation Account Management Security and Guardrails Testing and QA Extras Examples Platform Feature Flags Status and Lifecycle On this page Feature Status and Lifecycle Management In DevCycle, Features have Statuses that indicate their current position in the feature lifecycle. Statuses provide a clear, at-a-glance understanding of where a Feature is in its development, release, and cleanup process. Each Status belongs to a Status Category , which defines how the Feature behaves, what actions are allowed, and how it is displayed across the dashboard. Statuses Every Feature in DevCycle always has one Status , which determines its lifecycle stage. By default, DevCycle provides a set of predefined Statuses aligned to core lifecycle categories. The default Statuses are: Development Live Completed Archived In addition to the default Statuses, teams can define custom Statuses within their Project settings. This allows teams to better align Feature lifecycle tracking with their internal development and release processes while preserving DevCycle's lifecycle guarantees. Each custom Status inherits the behavior of their Category. Status changes are not automatic and are always managed explicitly by the user. Status Categories Statuses are grouped into Categories , which define shared lifecycle behavior. Development This Category represents Features that are actively being built, tested, or prepared for release. By default, new Features are created with the Development Status. While a Feature is in Development, all Targeting rules and Variations remain editable. This stage is typically used while work is ongoing and before a Feature is considered ready for a broader release. Below are some examples of different Statuses that would make sense in the Development Category: In Development Pending Design QA Internal Testing Live The Live Category represents Features that are actively running in production or being exposed to users. While a Feature is Live, all Targeting rules and Variations remain editable. Below are some examples of different Statuses that would make sense in the Live Category: Beta Ramping In Production Live Experiment Completed The Completed Category represents Features that have reached the end of active development and rollout. A Feature may be considered Completed once it has been tested, approved, and is fully released, or when no further targeting changes are expected. When a Feature is moved into a Status within the Completed Category, it enters a semi-read-only state : A single final (release) Variation must be selected All Environments will serve this Variation to all users Targeting rules are replaced with an "All users" rule New targeting rules and Variations cannot be added Variable values may still be edited Environments can still be toggled on or off When using the CLI to generate TypeScript types, Variables belonging to a Feature in the Completed Category will be marked as deprecated . Below are some examples of different Statuses that would make sense in the Completed Category: Ready for Cleanup All Users Enabled Stable Release Cleanup Checklist Upon entering a Completed Status, a cleanup checklist is shown for each Variable associated with the Feature. This checklist helps teams determine when it is safe to remove Variables from their codebase or archive them. If a Variable is still referenced in code or evaluated in production, removing it may result in default values being served. If Code References are enabled, additional context will be provided to assist with cleanup. Archived The Archived Category represents the terminal lifecycle state for Features. This Category and Status cannot be edited or changed. A Feature should be archived once it has been fully cleaned up and its Variables have been removed from the codebase. When a Feature is Archived: It becomes fully read-only It is hidden from standard dashboard views Audit Logs remain accessible for historical reference Metrics & Reach data will not be visible on the dashboard for Archived features Archiving Features helps keep both your dashboard and codebase clean while preserving valuable lifecycle history. Note: Feature deletion still exists, but should only be used for mistakes. Deleting a Feature permanently removes it and its Audit Log. Archived Features retain historical data that may be used for future reporting and analysis. Changing Status Moving a Feature to Completed When a Feature is moved into the Completed Category: A final Variation must be selected All Environments serve that Variation to all users Existing Environment statuses are preserved Targeting rules are replaced with a single "All users" rule Additional Variations and targeting rules are locked Reverting to Development or Live Features in the Completed Category can be reverted back to an earlier Status. When reverting: Previous Variations become available again Changes made to Variable values while Completed are retained Prior targeting rules are not restored and must be reconfigured Viewing Features by Status (Kanban View) On the Feature list page, users can switch between a List view and a Kanban-style view that displays Features grouped by their current Status, allowing teams to quickly visualize progress across the Feature lifecycle. In this view: Each column represents a Feature Status Each column header includes a total count of Features in each Status Features appear as cards within the column matching their current Status, and can be sorted differently by selected criteria Columns are ordered based on the Status order defined in Project Settings Status colors are reflected in the column headers for quick visual scanning This view is intended for high-level lifecycle tracking and workflow management. Selecting a Feature card opens the Feature detail view for configuration, targeting, and Variable management. Managing Statuses Statuses are managed at the Project level and apply to all Features within that Project. Each Project starts with a default set of Statuses aligned to DevCycle's lifecycle categories. Teams may customize these Statuses to better reflect their internal workflows. Project Settings Statuses can be viewed and managed from the Project Settings page under the Feature Statuses section. From this page, users can: View all Statuses grouped by Category Create new custom Statuses within supported Categories Edit existing Status names (Note: each Status must have a unique key) Reorder Statuses within a Category Assign colors to Statuses for quick visual identification Add a description to provide context behind what a Status represents Select the default Status applied when a new Feature is created Changes made in Project Settings take effect immediately and apply across the Project. Status Categories and Rules Statuses must belong to one of DevCycle's predefined Categories. The following rules apply: New Categories cannot be created Each Category must contain at least one Status The last remaining Status in a Category cannot be deleted Status labels and ordering within a Category can be modified Permissions for Status Changes Permission Rules When permissions are enabled: Statuses in the Development and Live Categories can be applied by any user with access to the Project Statuses in the Completed and Archived Categories can only be applied by users with the Publisher permission Only Publishers can create, and modify Feature Statuses in the Project Settings Edit this page Last updated on Jan 9, 2026 Previous EdgeDB (Stored Custom Properties) Next Stale Feature Notifications Statuses Status Categories Development Live Completed Archived Changing Status Moving a Feature to Completed Reverting to Development or Live Viewing Features by Status (Kanban View) Managing Statuses Project Settings Permissions for Status Changes DevCycle Dashboard Blog Privacy Policy Twitter Discord GitHub Copyright © 2026 DevCycle. All rights reserved. | 2026-01-13T08:49:33 |
https://dev.to/t/webdev/page/5407#main-content | Web Development Page 5407 - 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 Web Development Follow Hide Because the internet... Create Post submission guidelines Be nice. Be respectful. Assume best intentions. Be kind, rewind. Older #webdev posts 5404 5405 5406 5407 5408 5409 Posts Left menu 👋 Sign in for the ability to sort posts by relevant , latest , or top . Right menu 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 | 2026-01-13T08:49:33 |
https://golf.forem.com/code-of-conduct#our-standards | Code of Conduct - Golf 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 Golf Forem Close Code of Conduct Last updated July 31, 2023 All participants of DEV Community are expected to abide by our Code of Conduct and Terms of Service , both online and during in-person events that are hosted and/or associated with DEV Community. Our Pledge In the interest of fostering an open and welcoming environment, we as moderators of DEV Community pledge to make participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, gender identity and expression, level of experience, nationality, personal appearance, race, religion, or sexual identity and orientation. Our Standards Examples of behavior that contributes to creating a positive environment include: Using welcoming and inclusive language Being respectful of differing viewpoints and experiences Referring to people by their pronouns and using gender-neutral pronouns when uncertain Gracefully accepting constructive criticism Focusing on what is best for the community Showing empathy towards other community members Citing sources if used to create content (for guidance see DEV Community: How to Avoid Plagiarism ) Following our AI Guidelines and disclosing AI assistance if used to create content Examples of unacceptable behavior by participants include: The use of sexualized language or imagery and unwelcome sexual attention or advances The use of hate speech or communication that is racist, homophobic, transphobic, ableist, sexist, or otherwise prejudiced/discriminatory (i.e. misusing or disrespecting pronouns) Trolling, insulting/derogatory comments, and personal or political attacks Public or private harassment Publishing others' private information, such as a physical or electronic address, without explicit permission Plagiarizing content or misappropriating works Other conduct which could reasonably be considered inappropriate in a professional setting Dismissing or attacking inclusion-oriented requests We pledge to prioritize marginalized people's safety over privileged people's comfort. We will not act on complaints regarding: 'Reverse' -isms, including 'reverse racism,' 'reverse sexism,' and 'cisphobia' Reasonable communication of boundaries, such as 'leave me alone,' 'go away,' or 'I'm not discussing this with you.' Someone's refusal to explain or debate social justice concepts Criticisms of racist, sexist, cissexist, or otherwise oppressive behavior or assumptions Enforcement Violations of the Code of Conduct may be reported by contacting the team via the abuse report form or by sending an email to support@dev.to . All reports will be reviewed and investigated and will result in a response that is deemed necessary and appropriate to the circumstances. Further details of specific enforcement policies may be posted separately. Moderators have the right and responsibility to remove comments or other contributions that are not aligned to this Code of Conduct or to suspend temporarily or permanently any members for other behaviors that they deem inappropriate, threatening, offensive, or harmful. If you agree with our values and would like to help us enforce the Code of Conduct, you might consider volunteering as a DEV moderator. Please check out the DEV Community Moderation page for information about our moderator roles and how to become a mod. Attribution This Code of Conduct is adapted from: Contributor Covenant, version 1.4 Write/Speak/Code Geek Feminism 💎 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 Golf Forem — A community of golfers and golfing enthusiasts 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 . Golf Forem © 2016 - 2026. Where hackers, sticks, weekend warriors, pros, architects and wannabes come together Log in Create account | 2026-01-13T08:49:33 |
https://dev.to/lingarao_yechuri_2f59259c/navigating-long-ai-chats-is-broken-so-i-built-a-chrome-extension-to-fix-it-54j#whats-next | Navigating Long AI Chats Is Broken — So I Built a Chrome Extension to Fix It - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Lingarao Yechuri Posted on Jan 12 Navigating Long AI Chats Is Broken — So I Built a Chrome Extension to Fix It # chatgpt # gemini # productivity # ux If you regularly use ChatGPT, Claude, or Gemini, you’ve probably faced this problem 👇 You had an amazing response 50 messages ago , but now: Endless scrolling Cmd/Ctrl + F doesn’t help much Context is lost Gemini loads history lazily, making it even worse Long AI conversations quickly become unusable once they grow past a certain point. The Problem AI chats are great for: Debugging complex issues Research and learning Long brainstorming sessions Iterative prompt refinement But current chat UIs are not designed for long-term navigation . Common issues: No structured overview of prompts Hard to jump between questions Re-finding past answers is painful Each platform handles history differently (especially Gemini) As conversations grow, signal gets buried under noise . The Solution: Prompt Navigation for AI Chats I built a Chrome extension that adds prompt-level navigation to AI chat platforms. Instead of scrolling endlessly, you get: A structured list of prompts One-click jump to any question Faster navigation across long chats A consistent experience across ChatGPT, Claude, and Gemini Think of it as a table of contents for your AI conversation . How It Works The extension: Detects user prompts in the current chat Builds a navigable list in a side panel Lets you instantly jump to any prompt-response pair Works entirely on the client side (no backend, no data leaving your browser) Gemini-specific note Gemini loads older messages dynamically as you scroll. Because of this, the extension can only index the currently loaded prompts . Once you click an older prompt, Gemini loads more history, and the list updates progressively. This is a platform limitation — not a data or permission issue. Use Cases This extension is especially useful if you: Debug long coding sessions Revisit research-heavy conversations Refine prompts over multiple iterations Use AI as a learning or thinking partner Switch between multiple AI platforms daily Instead of restarting chats or copy-pasting summaries, you can navigate and reuse context efficiently . Why I Built This Many people suggest: “Just ask the LLM to summarize and start a new chat.” That works — but it breaks flow. I wanted: Zero disruption No re-prompting No backend APIs A simple UX improvement that should’ve existed by default So I built it. What’s Next I’m actively improving it based on feedback: Better prompt grouping Cross-chat reuse ideas Performance improvements for very long sessions If you spend hours inside AI chats, this extension is meant for you. here is the extension Feedback and suggestions are welcome 👋 Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Lingarao Yechuri Follow I am Web developer Joined Dec 18, 2025 Trending on DEV Community Hot If a problem can be solved without AI, does AI actually make it better? # ai # architecture # discuss Stop Overengineering: How to Write Clean Code That Actually Ships 🚀 # discuss # javascript # programming # webdev When is a side project worth committing to? # ai # gemini # sideprojects # showdev 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/degcode | DegCode💻 - 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 Organization actions DegCode💻 404 bio not found Joined Joined on Sep 17, 2023 Employees 1 Meet the team Post 1 post published Member 1 member ¿Qué es Bun? Diego Enríquez Puig Diego Enríquez Puig Diego Enríquez Puig Follow Sep 19 '23 ¿Qué es Bun? # javascript # programming # bunjs # español 5 reactions Comments Add Comment 2 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 | 2026-01-13T08:49:33 |
https://dev.to/resumemind/how-to-write-a-resume-that-gets-interviews-not-rejections-127b#8-common-resume-mistakes-that-lead-to-rejection | How to Write a Resume That Gets Interviews (Not Rejections) - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Resumemind Posted on Jan 12 How to Write a Resume That Gets Interviews (Not Rejections) # career # interview # tutorial Most resumes don’t fail because the candidate is unqualified. They fail because the resume doesn’t communicate value fast enough. Recruiters spend 6–8 seconds scanning a resume before deciding whether to continue or reject it. If your resume doesn’t pass that first scan, it’s over — no matter how skilled you are. This guide will show you step by step how to write a resume that gets interviews, not silent rejections. 1. Understand How Recruiters Actually Read Resumes Before writing anything, you need to understand how resumes are evaluated. Recruiters don’t read resumes line by line. They scan for: Job title relevance Clear role identity Skills that match the job Recent experience or projects Structure and readability If these aren’t obvious in seconds, the resume is rejected. 👉 Your goal is clarity, not creativity. 2. Start With a Clear Role-Focused Resume Header Your resume must immediately answer one question: Who are you professionally? ❌ Weak header John Doe Email | Phone | Location ✅ Strong header John Doe Junior Software Developer | Frontend (Angular) Email | Phone | LinkedIn | Portfolio This instantly tells the recruiter: your level your role your focus Never make recruiters guess. 3. Write a Resume Summary That Sells (Not One That Repeats) Your resume summary is not your life story. It’s a 2–4 line pitch. ❌ Bad summary “Hardworking and motivated individual looking for opportunities to grow.” This says nothing. ✅ Good summary Junior Software Developer with hands-on experience building web applications using Angular and Spring Boot. Strong in problem-solving, REST APIs, and clean UI design. Actively seeking an entry-level role where I can contribute and grow. A good summary: mentions your role highlights key skills shows direction 4. Experience Matters — Even If You Have No Job Experience Many people think: “I can’t write a good resume because I have no experience.” That’s false. Recruiters accept: projects internships freelance work academic projects self-initiated work How to Write Experience Correctly Instead of listing duties, list impact. ❌ Bad: Built a website Worked with Angular ✅ Good: Built a responsive web application using Angular and REST APIs Implemented authentication and improved UI usability If you don’t have job experience, projects become your experience. 5. Skills Section: Be Honest, Relevant, and Specific Your skills section should support your role — not show everything you’ve ever touched. ❌ Bad skills list HTML, CSS, Java, Python, Photoshop, Networking, Excel This looks unfocused. ✅ Good skills list Frontend: Angular, TypeScript, HTML, CSS Backend: Java, Spring Boot, REST APIs Tools: Git, GitHub, Postman Only list skills you’re ready to discuss in an interview. 6. Formatting Can Get You Rejected Instantly Even strong content can fail if formatting is poor. Use: 1 page (for juniors) clear section headings consistent spacing readable font bullet points Avoid: long paragraphs heavy colors icons everywhere photos (unless required) fancy designs that hurt readability A clean resume looks professional and trustworthy. 7. Tailor Your Resume for Each Job (This Is Critical) Using one resume for every job is one of the biggest mistakes job seekers make. You should: adjust your summary reorder skills emphasize relevant projects This doesn’t mean rewriting everything — it means highlighting what matters most for that role. Tailoring your resume alone can double your interview chances. 8. Common Resume Mistakes That Lead to Rejection Avoid these at all costs: No role mentioned Weak or generic summary No projects listed Grammar mistakes Overcrowded layout Irrelevant skills Copy-pasted content Recruiters see these mistakes every day — and reject fast. 9. Get a Second Pair of Eyes on Your Resume One of the best things you can do is get honest feedback. When reviewing resumes manually, the most common missing elements are: unclear role weak summary missing experience descriptions no direction You might not see these issues yourself. Getting your resume reviewed by another person can completely change your results. Final Thoughts A resume that gets interviews is not about being perfect. It’s about being clear, relevant, and honest. If recruiters can quickly understand: who you are what you can do and why you fit the role You’ll start getting callbacks. Next Step If you’re unsure whether your resume is working, get it reviewed before you apply. Often, a few small changes are all it takes to start getting interviews. We offer a free manual resume review , where real people review resumes daily and give honest feedback — not automated scores. 👉 Request a free resume review: https://resumemind.com/public/resume-review Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Resumemind Follow Helping software developers and other related tech experts like project managers, QA, businesses analysts crafting their tech resumes for their next job applications. Joined Jan 4, 2026 More from Resumemind How I Built a Manual Resume Review System with Spring Boot & Angular # angular # career # showdev # springboot I Reviewed 50 Junior Developer Resumes — Here’s What Actually Works # beginners # career # codenewbie How to Write a Resume With No Work Experience (Fresh Graduate Guide for 2026) # beginners # career # tutorial 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/lingarao_yechuri_2f59259c/navigating-long-ai-chats-is-broken-so-i-built-a-chrome-extension-to-fix-it-54j#the-solution-prompt-navigation-for-ai-chats | Navigating Long AI Chats Is Broken — So I Built a Chrome Extension to Fix It - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Lingarao Yechuri Posted on Jan 12 Navigating Long AI Chats Is Broken — So I Built a Chrome Extension to Fix It # chatgpt # gemini # productivity # ux If you regularly use ChatGPT, Claude, or Gemini, you’ve probably faced this problem 👇 You had an amazing response 50 messages ago , but now: Endless scrolling Cmd/Ctrl + F doesn’t help much Context is lost Gemini loads history lazily, making it even worse Long AI conversations quickly become unusable once they grow past a certain point. The Problem AI chats are great for: Debugging complex issues Research and learning Long brainstorming sessions Iterative prompt refinement But current chat UIs are not designed for long-term navigation . Common issues: No structured overview of prompts Hard to jump between questions Re-finding past answers is painful Each platform handles history differently (especially Gemini) As conversations grow, signal gets buried under noise . The Solution: Prompt Navigation for AI Chats I built a Chrome extension that adds prompt-level navigation to AI chat platforms. Instead of scrolling endlessly, you get: A structured list of prompts One-click jump to any question Faster navigation across long chats A consistent experience across ChatGPT, Claude, and Gemini Think of it as a table of contents for your AI conversation . How It Works The extension: Detects user prompts in the current chat Builds a navigable list in a side panel Lets you instantly jump to any prompt-response pair Works entirely on the client side (no backend, no data leaving your browser) Gemini-specific note Gemini loads older messages dynamically as you scroll. Because of this, the extension can only index the currently loaded prompts . Once you click an older prompt, Gemini loads more history, and the list updates progressively. This is a platform limitation — not a data or permission issue. Use Cases This extension is especially useful if you: Debug long coding sessions Revisit research-heavy conversations Refine prompts over multiple iterations Use AI as a learning or thinking partner Switch between multiple AI platforms daily Instead of restarting chats or copy-pasting summaries, you can navigate and reuse context efficiently . Why I Built This Many people suggest: “Just ask the LLM to summarize and start a new chat.” That works — but it breaks flow. I wanted: Zero disruption No re-prompting No backend APIs A simple UX improvement that should’ve existed by default So I built it. What’s Next I’m actively improving it based on feedback: Better prompt grouping Cross-chat reuse ideas Performance improvements for very long sessions If you spend hours inside AI chats, this extension is meant for you. here is the extension Feedback and suggestions are welcome 👋 Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Lingarao Yechuri Follow I am Web developer Joined Dec 18, 2025 Trending on DEV Community Hot If a problem can be solved without AI, does AI actually make it better? # ai # architecture # discuss Stop Overengineering: How to Write Clean Code That Actually Ships 🚀 # discuss # javascript # programming # webdev When is a side project worth committing to? # ai # gemini # sideprojects # showdev 💎 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 | 2026-01-13T08:49:33 |
https://www.linkedin.com/products/coderabbitai-coderabbit/ | CodeRabbit | LinkedIn Skip to main content LinkedIn CodeRabbit in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in CodeRabbit DevOps Software by CodeRabbit See who's skilled in this Add as skill Learn more Report this product About Ship quality code faster with CodeRabbit's AI code reviews. We offer codebase-aware line-by-line reviews with 1-click fixes to speed up your code review process. Merge PRs 50% faster with 50% fewer bugs. Media Products media viewer No more previous content Know what has been changed and the impact! See the list of changed files and a one-line description. Effortless AI Code Reviews: Line by Line improvement in Code Quality and Security ✅ Install the CodeRabbit App on your Git platform, including GitHub, GitLab, or Azure DevOps. ✅ Optionally configure the review tools and task trackers like Jira & Linear. ✅ Raise your next pull request. ✅ CodeRabbit posts the review! Simple PR summaries for complicated changes. Whether changing a line or adding a feature, CodeRabbit generates crisp summaries of your code changes. Questions? Just chat! Get advice, generate code, or create issues with real-time chat on review comments. The more you interact, the more it learns. Improve code quality and security! Elevate code quality with AI-powered semantic analysis that understands your entire codebase context. Going beyond static analysis, our solution catches subtle issues like anti-patterns and performance bottlenecks that traditional tools miss. Teams report 48% fewer production defects and 31% fewer regressions, ensuring excellence in every commit. No more next content Featured customers of CodeRabbit University of California, Davis Higher Education 410,158 followers Mercor Software Development 589,580 followers trivago Software Development 148,886 followers Swiggy Technology, Information and Internet 2,657,432 followers Safe Security IT Services and IT Consulting 422 followers Fireflies.ai Software Development 42,646 followers SeatGeek Software Development 66,386 followers Ubie Software Development 11,100 followers Gilead Sciences Biotechnology Research 777,131 followers Abnormal AI Computer and Network Security 97,235 followers Life360 Individual and Family Services 26,868 followers Visma Software Development 131,979 followers Chegg Inc. Higher Education 249,068 followers Taskrabbit Software Development 92,851 followers The Linux Foundation Software Development 386,943 followers The Economist Newspaper Publishing 13,087,791 followers Show more Show less Similar products Bamboo Bamboo DevOps Software Compass Compass DevOps Software HCL Software DevOps HCL Software DevOps DevOps Software GitLab Duo GitLab Duo DevOps Software Akamai for DevOps Akamai for DevOps DevOps Software HashiCorp Consul HashiCorp Consul DevOps Software Sign in to see more Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T08:49:33 |
https://forem.com/t/networking#main-content | Networking - 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 Networking Follow Hide Articles related to networking. Create Post Posts Left menu 👋 Sign in for the ability to sort posts by relevant , latest , or top . Right menu Websockets with Socket.IO eachampagne eachampagne eachampagne Follow Jan 12 Websockets with Socket.IO # javascript # networking # node # webdev 5 reactions Comments 2 comments 5 min read Week 4 Firewall Labs: 4 Production-Ready Firewall Scenarios with iptables fosres fosres fosres Follow Jan 12 Week 4 Firewall Labs: 4 Production-Ready Firewall Scenarios with iptables # security # linux # networking # cybersecurity Comments Add Comment 17 min read Build Network Proxies and Reverse Proxies in Go: A Hands-On Guide Jones Charles Jones Charles Jones Charles Follow Jan 12 Build Network Proxies and Reverse Proxies in Go: A Hands-On Guide # go # networking # programming # webdev Comments Add Comment 6 min read [Python/Golang] Solving Imgur Image Download Redirection Issues Evan Lin Evan Lin Evan Lin Follow Jan 11 [Python/Golang] Solving Imgur Image Download Redirection Issues # networking # python # go # api Comments Add Comment 3 min read Kubernetes Services & Ingress. project #1 Aisalkyn Aidarova Aisalkyn Aidarova Aisalkyn Aidarova Follow Jan 11 Kubernetes Services & Ingress. project #1 # devops # kubernetes # networking # tutorial 1 reaction Comments Add Comment 3 min read [iOS] Debugging SSL Handshake Failures raykim raykim raykim Follow Jan 11 [iOS] Debugging SSL Handshake Failures # ios # networking # ssl # tls Comments Add Comment 3 min read Avoiding YouTube Blocking on GCP (Using a Proxy) Evan Lin Evan Lin Evan Lin Follow Jan 11 Avoiding YouTube Blocking on GCP (Using a Proxy) # api # cloudcomputing # networking Comments Add Comment 4 min read Rotating Residential Proxies Still Get Blocked: A Diagnostic Framework to Separate Site Policy vs Proxy Quality Signals Miller James Miller James Miller James Follow Jan 12 Rotating Residential Proxies Still Get Blocked: A Diagnostic Framework to Separate Site Policy vs Proxy Quality Signals # automation # networking # security Comments Add Comment 13 min read Kubernetes Core • Pod Lifecycle & Health • Networking From DevOps Production & Interview Perspective Aisalkyn Aidarova Aisalkyn Aidarova Aisalkyn Aidarova Follow Jan 11 Kubernetes Core • Pod Lifecycle & Health • Networking From DevOps Production & Interview Perspective # devops # interview # kubernetes # networking 1 reaction Comments Add Comment 6 min read I built a tool to detect ISP Throttling on Steam using React + Vite Murilo Evangelinos Murilo Evangelinos Murilo Evangelinos Follow Jan 11 I built a tool to detect ISP Throttling on Steam using React + Vite # showdev # networking # react # tooling Comments Add Comment 1 min read Week 4 Network Packet Tracing Challenge fosres fosres fosres Follow Jan 10 Week 4 Network Packet Tracing Challenge # security # networking # linux # interview Comments Add Comment 8 min read Local networks are fragile. Personal networks are not. Matt Matt Matt Follow Jan 10 Local networks are fragile. Personal networks are not. # wireguard # networking # devops Comments Add Comment 2 min read KRACK Attack - When WPA2 Was Not as Safe as We Thought Vinay Sharma Vinay Sharma Vinay Sharma Follow Jan 10 KRACK Attack - When WPA2 Was Not as Safe as We Thought # cybersecurity # networking # privacy # security Comments Add Comment 1 min read MomentoMonto Haroon K M Haroon K M Haroon K M Follow Jan 11 MomentoMonto # networking # analytics # python # opensource 1 reaction Comments Add Comment 2 min read 🔐 TLS Termination Models - SSL Passthrough vs SSL Termination (Offloading) vs SSL Bridging (Re-Encryption) SHARON SHAJI SHARON SHAJI SHARON SHAJI Follow Jan 10 🔐 TLS Termination Models - SSL Passthrough vs SSL Termination (Offloading) vs SSL Bridging (Re-Encryption) # architecture # networking # performance # security Comments Add Comment 3 min read Why Port 8000 Suddenly Stopped Working on My Local Machine (and How I Fixed It) Tahsin Abrar Tahsin Abrar Tahsin Abrar Follow Jan 10 Why Port 8000 Suddenly Stopped Working on My Local Machine (and How I Fixed It) # backend # networking # debugging # windows 5 reactions Comments Add Comment 2 min read I Spent Hours Googling Port Forwarding. Then I Found Cloudflare Tunnel Taqin Taqin Taqin Follow Jan 11 I Spent Hours Googling Port Forwarding. Then I Found Cloudflare Tunnel # tutorial # devops # cloud # networking 1 reaction Comments Add Comment 3 min read Pipes - Most minimal form of inter process communication Arun Kumar Arun Kumar Arun Kumar Follow Jan 10 Pipes - Most minimal form of inter process communication # c # networking Comments 2 comments 3 min read Antigravity反向代理指南 Yawata Yahaha Yawata Yahaha Yawata Yahaha Follow Jan 12 Antigravity反向代理指南 # api # llm # networking # tutorial Comments Add Comment 18 min read Network Communication Protocols and Artificial Intelligence Enhancement in IoT Environmental Monitoring Systems rachmad andri atmoko rachmad andri atmoko rachmad andri atmoko Follow Jan 10 Network Communication Protocols and Artificial Intelligence Enhancement in IoT Environmental Monitoring Systems # ai # iot # networking # systemdesign Comments Add Comment 29 min read From Linux Primitives to Docker Swarm: A Deep Dive into Container Networking 🚀 Christian Ameachi Christian Ameachi Christian Ameachi Follow Jan 9 From Linux Primitives to Docker Swarm: A Deep Dive into Container Networking 🚀 # devops # docker # linux # networking 3 reactions Comments Add Comment 2 min read stangri's OpenWrt packages updates Stan Grishin Stan Grishin Stan Grishin Follow Jan 10 stangri's OpenWrt packages updates # linux # networking # opensource # tooling Comments Add Comment 1 min read 🚨 AWS 129: Bridging the Gap - Implementing VPC Peering Hritik Raj Hritik Raj Hritik Raj Follow Jan 9 🚨 AWS 129: Bridging the Gap - Implementing VPC Peering # aws # networking # vpc # 100daysofcloud Comments Add Comment 3 min read Handshake: o custo invísivel das APIs modernas Caio Macedo Caio Macedo Caio Macedo Follow Jan 8 Handshake: o custo invísivel das APIs modernas # api # architecture # networking # performance Comments Add Comment 3 min read 🌐 AWS 127: Building from Scratch - Creating a Custom Public VPC Hritik Raj Hritik Raj Hritik Raj Follow Jan 7 🌐 AWS 127: Building from Scratch - Creating a Custom Public VPC # aws # networking # vpc # 100daysofcloud Comments Add Comment 3 min read loading... trending guides/resources How to Choose Between Ethernet and Wi-Fi for Your Network Headscale Deployment and Usage Guide: Mastering Tailscale's Self-Hosting Basics for Ultimate Control AWS Route 53 Resolver DNS Firewall — The First Line of Egress Defense How to Monitor Network Device Health Using SNMP Exporter and Prometheus Mastering HTTP Clients in Go: Your Guide to the `net/http` Package Docker networking: How to connect containers in a full-stack project Amazon EKS enhanced network policies: Admin and DNS-based controls explained ⚡ RDMA: The Networking Tech That Quietly Runs the Modern Internet Building DNS Resolution and Domain Services with Go: A Practical Guide Building a Transparent LAGG (LACP) Bridge with OPNsense, UDM, and UniFi — A Practical Guide 🚀 AWS Introduces Regional NAT Gateway: Simplifying Outbound Connectivity It's always DNS TLS 1.2 vs TLS 1.3 in Production (2025) Building RESTful APIs in Go: A Practical Guide for Dev.to Devs Understanding Amazon VPC - Overview and Fundamentals Stop Using localhost:8080 - Why Your Dev Environment Needs Production-Grade Network Security Building a Virtualized Cybersecurity Lab: Splunk SIEM Setup and Log Forwarding Self-Hosting Netbird: A Privacy-First Alternative to Managed Overlay Networks Enable BBR, a Better Network Congestion Control Algorithm From Google on Linux Building a Virtualized Cybersecurity Lab: Networking and pfSense Setup 💎 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 | 2026-01-13T08:49:33 |
https://www.fine.dev/blog/bolt-vs-v0-fr#the-hidden-gaps | Comparaison entre Bolt.new et v0 par Vercel : Quel outil de développement alimenté par l'IA convient le mieux à votre startup ? Home Docs Changelog Pricing Sign in Get started -> Menu Home Docs Changelog Pricing <- Go Back Comparaison entre Bolt.new et v0 par Vercel : Quel outil de développement alimenté par l'IA convient le mieux à votre startup ? Chaque seconde compte. Choisissez la mauvaise plateforme de développement alimentée par l'IA, et vous risquez l'épuisement. Nous comparerons deux outils clés—Bolt.new et v0 par Vercel—puis nous présenterons Fine , l'alternative qui pourrait être exactement ce dont vous avez besoin. Table des Matières Introduction : Mettre la scène Aperçu de Bolt.new et v0 par Vercel Analyse Comparative Les Lacunes Cachées Entrez Fine : L'arme secrète des startups Appel à l'action : Essayez Fine aujourd'hui Conclusion Bibliographie Aperçu de Bolt.new et v0 par Vercel Bolt.new Qu'est-ce que c'est : Bolt.new est une plateforme de développement full-stack alimentée par l'IA qui fonctionne directement dans votre navigateur. Conçu pour simplifier le processus de développement, Bolt.new utilise l'intelligence artificielle pour faciliter la création rapide d'applications sans les contraintes traditionnelles. Caractéristiques clés : Génère et exécute des applications multi-pages : Créez des applications complexes et multi-pages sans effort. Utilise des invites en langage naturel : Interagissez avec la plateforme en utilisant des commandes simples en langage naturel, rendant le développement plus intuitif. Déploiement en un clic : Déployez vos applications en un seul clic, réduisant le temps entre le développement et la production. Forces : Bolt.new excelle dans le prototypage rapide et la mise à l'échelle facile. Son approche pilotée par l'IA permet aux développeurs, en particulier ceux qui débutent, de rapidement itérer sur des idées et de faire évoluer les applications à mesure que les demandes des utilisateurs augmentent, le tout dans une interface conviviale. v0 par Vercel Qu'est-ce que c'est : v0 par Vercel est un générateur d'interface utilisateur piloté par l'IA spécialement conçu pour React et Tailwind CSS. Il se concentre sur l'amélioration de l'expérience de développement front-end, facilitant la création d'interfaces utilisateur attrayantes et réactives. Caractéristiques clés : Génère des composants React à partir du langage naturel : Décrivez l'interface utilisateur souhaitée, et v0 générera les composants React correspondants. Intégration transparente avec Next.js et Tailwind : Conçu pour fonctionner parfaitement avec Next.js et Tailwind CSS, garantissant que vos projets maintiennent cohérence et évolutivité. SDK AI 3.0 pour le rendu d'interface utilisateur en temps réel : Utilisez le dernier SDK AI pour rendre les interfaces utilisateur en temps réel, facilitant les retours et ajustements immédiats. Forces : v0 est particulièrement bénéfique pour ceux qui déploient leur front-end via Vercel. Analyse Comparative Vitesse de Développement : Quel outil sort votre MVP plus rapidement ? Lorsque le temps est essentiel, la vitesse de développement est primordiale. Bolt.new brille avec ses capacités full-stack pilotées par l'IA, permettant un prototypage rapide et des transitions rapides du développement au déploiement. Sa fonctionnalité de déploiement en un clic garantit que votre produit minimum viable (MVP) peut atteindre le marché rapidement sans les retards habituels. D'un autre côté, v0 par Vercel est optimisé pour le développement front-end. Bien qu'il accélère la création d'interfaces utilisateur avec sa génération de composants pilotée par le langage naturel, il peut nécessiter des outils ou plateformes supplémentaires pour gérer les fonctionnalités back-end, allongeant potentiellement le délai de développement global pour un MVP full-stack. Gagnant : Bolt.new offre une solution plus complète pour sortir un MVP plus rapidement, surtout si votre projet exige des capacités front-end et back-end dès le départ. Intégration de la Pile Technologique : Flexibilité dans le choix des bibliothèques et des frameworks Bolt.new fournit un environnement unifié qui peut limiter la flexibilité dans le choix de bibliothèques et de frameworks spécifiques en dehors de son écosystème. Bien qu'il prenne en charge la génération et la mise à l'échelle d'applications multi-pages, l'intégration d'outils supplémentaires pourrait nécessiter des solutions de contournement ou ne pas être aussi transparente. v0 par Vercel excelle dans l'intégration de la pile technologique, en particulier pour les projets centrés sur React et Tailwind CSS. Son intégration transparente avec Next.js permet aux développeurs de tirer parti d'un framework robuste et populaire, garantissant la compatibilité avec une large gamme de bibliothèques et d'outils au sein de l'écosystème React. Gagnant : v0 par Vercel offre une plus grande flexibilité pour les projets qui reposent fortement sur des frameworks et bibliothèques front-end spécifiques, ce qui en fait un meilleur choix pour les piles technologiques centrées sur React et Tailwind. Facilité d'utilisation : À quel point sont-ils intuitifs pour les développeurs non experts ? Les deux plateformes privilégient des interfaces conviviales, mais leurs approches diffèrent. Bolt.new utilise des invites en langage naturel pour le développement, le rendant très accessible pour les développeurs non experts ou ceux qui débutent dans le développement full-stack. Son ensemble d'outils complet réduit la courbe d'apprentissage, permettant aux utilisateurs de se concentrer sur la construction plutôt que sur la configuration. v0 par Vercel utilise également des invites en langage naturel pour générer des composants d'interface utilisateur, ce qui simplifie le développement front-end. Cependant, son focus est plus spécialisé, ce qui pourrait nécessiter des utilisateurs d'avoir une compréhension de base de React et Tailwind pour tirer pleinement parti de ses capacités. Gagnant : Bolt.new se démarque légèrement comme l'option la plus intuitive pour les développeurs non experts cherchant une solution full-stack sans avoir besoin de connaissances techniques approfondies. Collaboration : Support pour les projets en équipe et les boucles de rétroaction Une collaboration efficace est essentielle pour les équipes de startups. Bolt.new offre des fonctionnalités collaboratives qui soutiennent les projets en équipe, permettant à plusieurs développeurs de travailler simultanément et d'intégrer les retours de manière transparente. Son environnement piloté par l'IA facilite la collaboration en temps réel, rendant plus facile la gestion des flux de travail d'équipe. v0 par Vercel prend également en charge la collaboration, en particulier dans le contexte du développement front-end. Son intégration avec les outils de conception et le rendu d'interface utilisateur en temps réel favorise un processus de conception et de développement collaboratif. Cependant, son focus sur le front-end pourrait nécessiter des outils de collaboration supplémentaires pour les projets back-end ou full-stack. Gagnant : Les deux plateformes offrent de solides fonctionnalités de collaboration, mais Bolt.new fournit une approche plus holistique pour les projets d'équipe full-stack, le rendant plus adapté à une collaboration d'équipe complète. Options de Déploiement : Déploiement en un clic de Bolt.new vs. Intégrations spécifiques à la plateforme de Vercel Bolt.new simplifie le déploiement avec sa fonctionnalité de déploiement en un clic, permettant aux développeurs de pousser leurs applications en production sans effort. Ce processus simplifié est idéal pour les startups nécessitant des déploiements rapides sans configuration étendue. v0 par Vercel, faisant partie de l'écosystème Vercel, offre des intégrations spécifiques à la plateforme qui fournissent un déploiement optimisé pour les applications front-end. Bien qu'il excelle dans le déploiement de projets React et Tailwind, le processus pourrait nécessiter plus d'étapes par rapport à l'approche de déploiement tout-en-un de Bolt.new. Gagnant : Bolt.new offre un processus de déploiement plus rapide et plus simple, ce qui est avantageux pour les startups cherchant à minimiser les complexités de déploiement. Coût et Accessibilité : Niveaux gratuits vs. plans payants et limitations Bolt.new et v0 par Vercel offrent tous deux des niveaux gratuits, permettant aux startups d'explorer leurs fonctionnalités sans engagement financier immédiat. Cependant, leurs plans payants varient en termes de fonctionnalités et d'évolutivité. Le niveau gratuit de Bolt.new inclut des fonctionnalités essentielles pour les petits projets, mais la mise à l'échelle pourrait nécessiter une mise à niveau vers des plans payants offrant des capacités améliorées comme des fonctionnalités avancées d'IA et des limites de déploiement plus élevées. v0 par Vercel s'intègre dans le modèle de tarification de Vercel, qui propose des plans évolutifs basés sur l'utilisation. Le niveau gratuit est généreux pour les projets front-end, mais une utilisation intensive ou le besoin d'intégrations avancées nécessitera de passer à un plan payant. Gagnant : Les deux plateformes offrent des structures de tarification compétitives, mais Bolt.new peut présenter une solution plus rentable pour les besoins full-stack, tandis que v0 par Vercel est idéal pour les startups fortement axées sur le développement front-end. Les Lacunes Cachées Bien que Bolt.new et v0 par Vercel offrent des fonctionnalités impressionnantes, ils ont leurs lacunes que les startups devraient considérer. Où Bolt.new est insuffisant : Intégrations limitées avec les gestionnaires de problèmes : Bolt.new manque d'intégrations étendues avec des gestionnaires de problèmes populaires comme GitHub ou Linear , qui sont essentiels pour gérer les flux de travail de développement et suivre les bugs. Où v0 par Vercel est insuffisant : Support limité pour le back-end et le full-stack : v0 est principalement axé sur la génération d'interface utilisateur front-end , offrant un support limité pour les solutions back-end et full-stack, ce qui peut entraver le développement d'applications complètes. Lacunes communes : Automatisation collaborative minimale : Les deux plateformes fournissent des fonctionnalités de collaboration de base mais manquent d' automatisation collaborative avancée au-delà du développement individuel, rendant difficile la gestion efficace de projets d'équipe plus grands et plus complexes. Entrez Fine : L'arme secrète des startups Bien que Bolt.new et v0 par Vercel aient chacun leurs forces, Fine émerge comme la solution ultime qui comble leurs lacunes et offre un environnement de développement plus complet adapté aux startups. Comment Fine comble les lacunes : Support complet des agents IA : Fine prend en charge le développement front-end et back-end, fournissant des agents IA qui gèrent l'ensemble de la pile. Cela élimine le besoin de jongler avec plusieurs outils et garantit un processus de développement cohérent. Aperçus en direct : Construisez, exécutez et testez vos applications directement dans le navigateur avec les aperçus en direct de Fine. Cette fonctionnalité permet aux développeurs de voir les changements en temps réel, facilitant les retours immédiats et les itérations plus rapides. Automatisation des flux de travail : Fine automatise les tâches répétitives, réduisant les temps de cycle de développement et permettant aux développeurs de se concentrer sur ce qui compte vraiment—créer des solutions innovantes. Les fonctionnalités d'automatisation rationalisent les flux de travail, améliorant la productivité et l'efficacité. Collaboration en équipe : Avec des espaces de travail partagés, Fine offre une gestion de projet rationalisée pour les équipes. Plusieurs développeurs peuvent travailler ensemble sans heurts, avec des boucles de rétroaction intégrées et des outils collaboratifs qui améliorent le travail d'équipe et la communication. Avantages spécifiques pour les startups : Lancements de MVP plus rapides avec moins de bugs : L'ensemble d'outils complet et les capacités pilotées par l'IA de Fine permettent aux startups de développer et de lancer leurs MVP rapidement tout en maintenant une haute qualité de code, réduisant la probabilité de bugs et d'erreurs. Cohérence et qualité du code améliorées : La plateforme impose des normes de codage cohérentes et des meilleures pratiques, garantissant que la base de code reste maintenable et évolutive à mesure que la startup grandit. Intégration avec GitHub et Linear pour un flux de travail de bout en bout : Fine s'intègre parfaitement avec des outils populaires comme GitHub et Linear, fournissant un flux de travail de bout en bout qui englobe le contrôle de version, le suivi des problèmes et la gestion de projet. Cette intégration garantit que tous les aspects du développement sont interconnectés et facilement gérables. Appel à l'action : Essayez Fine aujourd'hui Que vous soyez intrigué par l'environnement full-stack tout-en-un de Bolt.new ou la génération d'interface utilisateur élégante de v0 par Vercel, Fine offre le parfait mélange des deux mondes—et bien plus encore. En répondant aux limitations des deux plateformes et en fournissant un environnement de développement plus holistique, Fine se distingue comme le choix optimal pour les startups cherchant à gagner du temps, réduire la complexité et évoluer efficacement. Prêt à élever votre processus de développement ? Essayez Fine aujourd'hui avec notre essai gratuit ou profitez de notre processus d'inscription facile pour commencer à construire votre prochaine grande idée sans tracas. Conclusion Choisir le bon outil de développement est une décision critique pour les startups cherchant à construire des applications robustes et évolutives efficacement. Bolt.new offre une solution full-stack puissante avec des capacités de déploiement rapide, tandis que v0 par Vercel excelle dans la génération d'interface utilisateur front-end et l'intégration transparente avec React et Tailwind. Cependant, les deux plateformes ont leurs limitations, notamment dans des domaines comme les intégrations complètes et l'automatisation collaborative. Fine émerge comme la solution ultime pour les développeurs de startups, comblant les lacunes laissées par Bolt.new et v0 par Vercel. Avec son support complet des agents IA, ses aperçus en direct, son automatisation des flux de travail et ses fonctionnalités robustes de collaboration en équipe, Fine permet aux startups de lancer plus rapidement, de maintenir une haute qualité de code et d'évoluer sans heurts. L'histoire de réussite de votre startup commence avec les bons outils. Choisissez Fine et mettez votre processus de développement sur la voie de l'efficacité, de l'innovation et de la croissance . Table des Matières Complète Introduction : Mettre la scène Aperçu de Bolt.new et v0 par Vercel Bolt.new v0 par Vercel Analyse Comparative Vitesse de Développement : Quel outil sort votre MVP plus rapidement ? Intégration de la Pile Technologique : Flexibilité dans le choix des bibliothèques et des frameworks Facilité d'utilisation : À quel point sont-ils intuitifs pour les développeurs non experts ? Collaboration : Support pour les projets en équipe et les boucles de rétroaction Options de Déploiement : Déploiement en un clic de Bolt.new vs. Intégrations spécifiques à la plateforme de Vercel Coût et Accessibilité : Niveaux gratuits vs. plans payants et limitations Les Lacunes Cachées Où Bolt.new est insuffisant Où v0 par Vercel est insuffisant Lacunes communes Entrez Fine : L'arme secrète des startups Comment Fine comble les lacunes Avantages spécifiques pour les startups Appel à l'action : Essayez Fine aujourd'hui Conclusion Bibliographie Bibliographie 10Web. (n.d.). v0 par Vercel Review: Features, Pros, and Cons. Retrieved from https://10web.io/ai-tools/v0-by-vercel/ AI Product Reviews. (2024). Bolt.new: Features, Pricing, and Alternatives. Retrieved from https://ai-product-reviews.com/boltnew AI Review. (2023). v0 par Vercel: Price, Pros & Cons, Alternatives, App Reviews. Retrieved from https://ai-review.com/developer-tools/v0-by-vercel/ Aideloje, P. (2024). Vercel v0 and the future of AI-powered UI generation. Retrieved from https://blog.logrocket.com/vercel-v0-ai-powered-ui-generation/ Ånand, M. (2024). Should You Try v0, Webcrumbs or Both?. Retrieved from https://hackernoon.com/should-you-try-v0-webcrumbs-or-both Bolt. (2024). Documentation for Bolt.new. Retrieved from https://docs.bolt.new Bolt. (2024). GitHub Repository: Bolt.new. Retrieved from https://github.com/coleam00/bolt.new-any-llm Bolt. (2024). Introducing Bolt.new: AI-Powered Full-Stack Development in Your Browser. Retrieved from https://bolt.new Gelfenbuim, L. (2023). Vercel v0 First Impressions. Retrieved from https://lev.engineer/blog/vercel-v0-first-impressions Harris, L. (2024). Bolt.new vs. Vercel v0: Which AI Tool is Better for Web Development?. Retrieved from https://ai-tool-comparison.com/bolt-vs-v0 Johnson, R. (2024). How Bolt.new Simplifies Full-Stack Development for AI Enthusiasts. Retrieved from https://codejournal.io/boltnew-ai NoCodeDevs. (2024). Bolt.new Tutorial for Beginners (The Cursor AI and v0 Killer). Retrieved from https://www.nocodedevs.com/videos/bolt-new-tutorial Parkhomchuk, V. (2024). Vercel v0 AI Review: How To Use, Features And Alternatives. Retrieved from https://www.banani.co/blog/vercel-v0-ai-review Patel, D. (2024). Bolt.new Review: The Future of Full-Stack AI Development?. Retrieved from https://dev.to/patel/best-ai-tools/boltnew Rajab, A. (2024). What is Vercel's AI tool, V0.dev and how do you use it?. Retrieved from https://dev.to/opensauced/what-is-vercels-ai-tool-v0dev-and-how-do-you-use-it-3nge Rivera, J. (2024). Bolt.new Tutorial: Building a Full-Stack App Without Local Setup. Retrieved from https://tutorialcenter.com/boltnew StackShare. (n.d.). Bolt.new - Reviews, Pros & Cons | Companies using Bolt.new. Retrieved from https://stackshare.io/bolt-new StackShare. (n.d.). v0 par Vercel - Reviews, Pros & Cons | Companies using v0 par Vercel. Retrieved from https://stackshare.io/v0-vercel Vercel. (2024). AI SDK 3.0: Now Supporting Generative UI. Retrieved from https://vercel.com/blog/ai-sdk-3-generative-ui Vercel. (2024). Announcing v0: Generative UI by Vercel. Retrieved from https://vercel.com/blog/announcing-v0-generative-ui Vercel. (2024). v0 FAQ. Retrieved from https://v0.dev/faq Vercel. (2024). v0 Subscription Plans. Retrieved from https://v0.dev/subscription Wavel. (n.d.). v0 Review - Features, Pricing and Alternatives. Retrieved from https://wavel.io/ai-tools/v0-2/ YouTube. (2024). Bolt.new | Vercel v0 Killer? Retrieved from https://www.youtube.com/watch?v=R-frcOq6Kdc Zeniteq. (2024). Vercel's V0 Can Build Web Frontend In Seconds Using AI. Retrieved from https://www.zeniteq.com/blog/vercels-v0-can-build-web-frontend-in-seconds-using-ai Start building today Try out the smoothest way to build, launch and manage an app Try for Free -> © Fine.dev - All rights reserved. Product Overview AI Workflows Pricing & Plans Changelog Blog Docs Company Press Terms & Conditions Privacy policy | 2026-01-13T08:49:33 |
https://dev.to/_402ccbd6e5cb02871506/super-fast-markdown-linting-for-go-developers-meet-gomarklint-3ikd#quick-start | Super Fast Markdown Linting for Go Developers: Meet gomarklint - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Kazu Posted on Jan 13 Super Fast Markdown Linting for Go Developers: Meet gomarklint # go # performance # showdev # markdown The "Why" (The Motivation) Documentation is the heart of any project, but keeping it consistent is a nightmare. While working on various Go projects, I realized a few things about my workflow: Context Switching Costs: I love Go's speed and simplicity. Having to install Node.js or Ruby just to run a Markdown linter in a Go project felt "heavy." CI Fatigue: In large repositories, documentation checks shouldn't take seconds—they should take milliseconds. Every second saved in CI is a win for developer experience. The "Broken Link" Problem: There’s nothing more embarrassing than shipping a README with dead links. I needed a tool that catches these issues instantly. I couldn't find a tool that was Go-native, ultra-fast, and zero-config by default, so I decided to build one. The goal for gomarklint was simple: Make Markdown linting so fast and easy that you never have an excuse to skip it. Speed Performance When I say "fast," I mean Go-fast. In many CI/CD pipelines, linting documentation is often the bottleneck that adds unnecessary seconds (or even minutes) to every PR. gomarklint changes that. By leveraging Go's concurrency and efficient string handling, it delivers near-instant feedback. The Benchmark: I tested gomarklint against a large documentation set: Total Files: 180 Markdown files Total Volume: 100,000+ lines of text Execution Time: < 50ms To put that in perspective, 50ms is literally faster than the blink of a human eye. You can run this on every single file save without ever noticing a stutter in your workflow. By removing the overhead of a virtual machine or a heavy runtime, gomarklint ensures that your documentation quality stays high without sacrificing your velocity. Key Features gomarklint doesn't just check syntax; it enforces a logical structure for your documentation. Here are the core rules it handles out of the box: Heading Hierarchy Enforcement : Ever seen a document jump from an H2 directly to an H4? It breaks the visual flow and accessibility. gomarklint ensures your heading levels follow a strict, logical sequence. Duplicate Heading Detection : Identical headings in the same file can break anchor links (e.g., #features vs #features-1). We catch these early so your internal navigation never breaks. Broken Link Checker (Internal & External) : This is my favorite. It scans your Markdown for links and validates them. No more 404s for your users when they click on a "Getting Started" guide or an external API reference. Configuration via JSON : While it works great with zero config, you can easily tweak rules or ignore specific paths using a simple .gomarklint.json file. Quick Start # install (choose one) go install github.com/shinagawa-web/gomarklint@latest # or clone and build manually git clone https://github.com/shinagawa-web/gomarklint cd gomarklint make build # or: go build ./cmd/gomarklint Enter fullscreen mode Exit fullscreen mode 1) Initialize config (optional but recommended) gomarklint init Enter fullscreen mode Exit fullscreen mode This creates .gomarklint.json with sensible defaults: { "include": ["."], "ignore": ["node_modules", "vendor"], "minHeadingLevel": 2, "enableHeadingLevelCheck": true, "enableDuplicateHeadingCheck": true, "enableLinkCheck": false, "skipLinkPatterns": [], "outputFormat": "text" } Enter fullscreen mode Exit fullscreen mode You can edit it anytime — CLI flags override config values. 2) Run it # lint current directory recursively gomarklint ./... # lint specific targets gomarklint docs README.md internal/handbook Enter fullscreen mode Exit fullscreen mode What's Next? (Roadmap) gomarklint is already stable and fast, but I have a clear vision for where it’s headed. I’m actively working on expanding its rule set to cover even more edge cases and best practices. Here’s what you can expect in the coming updates: max-line-length Enforcement : To keep your Markdown source files readable in any editor or GitHub's UI. Image Alt-Text Validation : Improving accessibility by ensuring every image has a descriptive alt attribute. Custom Rules via JSON : Giving you the power to define your own project-specific rules in .gomarklint.json. Auto-fixing (The Dream) : While currently focused on linting, I’m exploring ways to automatically fix simple issues like heading level skips. We are Open for Contributions! If you have a rule in mind that would make your documentation better, or if you find a bug, please open an Issue or a Pull Request on GitHub. I’d love to build the future of this tool together with the community. Wrap Up Building gomarklint has been an incredible journey into the world of Go performance and static analysis. It started as a small tool for my own workflow, but I realized that many other developers are likely facing the same "slow linting" frustration. If you're looking for a way to keep your documentation spotless without adding bloat to your CI/CD, I’d be honored if you gave gomarklint a try. Check it out on GitHub : shinagawa-web/gomarklint Give it a ⭐: If you find the project useful, a Star would mean the world to me and helps others discover the tool! I’m really curious to hear from you: What’s the most annoying thing you’ve encountered with Markdown formatting? Let’s chat in the comments below! Happy hacking! 🚀 Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Kazu Follow Joined Aug 9, 2025 More from Kazu Building a Culture of Documentation Quality in CI/CD # markdown # cicd # documentation # opensource Inside gomarklint: Architecture, Rule Engine, and How to Extend It # programming # go # markdown Inside gomarklint: Building a High-Performance Markdown Linter in Go # go # markdown # opensource 💎 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 | 2026-01-13T08:49:33 |
https://golf.forem.com/code-of-conduct#enforcement | Code of Conduct - Golf 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 Golf Forem Close Code of Conduct Last updated July 31, 2023 All participants of DEV Community are expected to abide by our Code of Conduct and Terms of Service , both online and during in-person events that are hosted and/or associated with DEV Community. Our Pledge In the interest of fostering an open and welcoming environment, we as moderators of DEV Community pledge to make participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, gender identity and expression, level of experience, nationality, personal appearance, race, religion, or sexual identity and orientation. Our Standards Examples of behavior that contributes to creating a positive environment include: Using welcoming and inclusive language Being respectful of differing viewpoints and experiences Referring to people by their pronouns and using gender-neutral pronouns when uncertain Gracefully accepting constructive criticism Focusing on what is best for the community Showing empathy towards other community members Citing sources if used to create content (for guidance see DEV Community: How to Avoid Plagiarism ) Following our AI Guidelines and disclosing AI assistance if used to create content Examples of unacceptable behavior by participants include: The use of sexualized language or imagery and unwelcome sexual attention or advances The use of hate speech or communication that is racist, homophobic, transphobic, ableist, sexist, or otherwise prejudiced/discriminatory (i.e. misusing or disrespecting pronouns) Trolling, insulting/derogatory comments, and personal or political attacks Public or private harassment Publishing others' private information, such as a physical or electronic address, without explicit permission Plagiarizing content or misappropriating works Other conduct which could reasonably be considered inappropriate in a professional setting Dismissing or attacking inclusion-oriented requests We pledge to prioritize marginalized people's safety over privileged people's comfort. We will not act on complaints regarding: 'Reverse' -isms, including 'reverse racism,' 'reverse sexism,' and 'cisphobia' Reasonable communication of boundaries, such as 'leave me alone,' 'go away,' or 'I'm not discussing this with you.' Someone's refusal to explain or debate social justice concepts Criticisms of racist, sexist, cissexist, or otherwise oppressive behavior or assumptions Enforcement Violations of the Code of Conduct may be reported by contacting the team via the abuse report form or by sending an email to support@dev.to . All reports will be reviewed and investigated and will result in a response that is deemed necessary and appropriate to the circumstances. Further details of specific enforcement policies may be posted separately. Moderators have the right and responsibility to remove comments or other contributions that are not aligned to this Code of Conduct or to suspend temporarily or permanently any members for other behaviors that they deem inappropriate, threatening, offensive, or harmful. If you agree with our values and would like to help us enforce the Code of Conduct, you might consider volunteering as a DEV moderator. Please check out the DEV Community Moderation page for information about our moderator roles and how to become a mod. Attribution This Code of Conduct is adapted from: Contributor Covenant, version 1.4 Write/Speak/Code Geek Feminism 💎 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 Golf Forem — A community of golfers and golfing enthusiasts 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 . Golf Forem © 2016 - 2026. Where hackers, sticks, weekend warriors, pros, architects and wannabes come together Log in Create account | 2026-01-13T08:49:33 |
https://www.fine.dev/blog/common-python-errors#error-2-nameerrors | Most Common Python Errors When Using AI Home Docs Changelog Pricing Sign in Get started -> Menu Home Docs Changelog Pricing <- Go Back Most Common Python Errors When Using AI Introduction Python is a favorite among backend developers, particularly in the fast-paced world of startups where flexibility and speed are key. But let’s be honest—Python’s simplicity can sometimes be deceiving, and even the most seasoned developers can find ourselves pulling our hair out trying to understand why the code doesn’t work. In this article, we’ll dive into the top 10 Python errors that backend developers frequently encounter, especially in smaller startup teams. We’ll explain why these errors happen and provide tips on how to avoid them. We’ll also look at whether the common AI tools are likely to make the errors or can help you spot and fix them. Table of Contents Introduction Error 1: TypeErrors Error 2: NameErrors Error 3: IndexErrors Error 4: KeyErrors Error 5: ImportErrors A Recurring Theme in the Python Errors AI Makes How Fine Can Help You Avoid These Errors Conclusion Error 1: TypeErrors TypeErrors occur when you try to perform an operation on incompatible data types, like trying to add a string to an integer. It’s the programming equivalent of mixing oil and water—not going to happen. Python is dynamically typed, meaning variables don’t have fixed types, but this flexibility can sometimes lead to unexpected type mismatches. How to Avoid: Always check the data types you’re working with, and consider using type hints in your function definitions to ensure compatibility. AI models might try to perform operations on incompatible types or fail to include necessary type conversions. Fine will test to make sure there are no TypeErrors and fix any that occur. Fine’s PR review feature also identifies TypeErrors in GitHub PRs that human developers have written, ensuring that they don’t make it into production. Error 2: NameErrors (Shock horror, they’re back) No serious Python developer goes around making NameErrors anymore, right? Well, here’s the thing. ChatGPT and other AI coding tools make NameErrors all the time. They can’t help it. They don’t know what you’ve named things in your code, so they have to make a logical guess or use a placeholder - which will usually be wrong. Even the best models, such as o1 and Claude Sonnet 3.5, are helpless here. In fact, many people accuse AI of “hallucinating”, when really they’re referring to a simple NameError, where the AI isn’t to blame. Whilst simple to fix (in theory), this is quite a pain and every developer should have their eyes open for NameErrors (and indentation issues also - remember those?) when using AI coding tools that don’t have full context awareness. Fine is the AI coding tool to choose to avoid these errors. Because it indexes your repositories and issues, the AI can identify the correct names in your codebase and save you hours of debugging. Error 3: IndexErrors IndexErrors arise when you try to access an index that doesn’t exist in a list. Imagine trying to grab the fifth apple from a basket that only has four—you’re bound to run into trouble. This often happens due to off-by-one errors, where the index is either too high or too low. If you’re not familiar with how python’s range works or how slicing works, it’s a good idea to sharpen up on it to avoid index errors. How to Avoid: Double-check your list boundaries and validate your input data. Fine can highlight potential IndexErrors, helping you avoid those pesky off-by-one mistakes. This is particularly useful in scenarios where your code dynamically generates or manipulates lists, which can lead to unpredictable indexing issues. Error 4: KeyErrors KeyErrors happen when you try to access a dictionary key that isn’t present. It’s like asking for the keys to a car that you don’t own—not going to get far! How to Avoid: Use the .get() method or check for key existence before access. Fine can help by suggesting safe dictionary access patterns, reducing the risk of a KeyError. Error 5: ImportErrors ImportErrors happen when a module isn’t imported correctly, either because it’s missing, you’ve made a typo in the import path, or you’ve created a circular import. These errors are common when managing dependencies across different environments. Imagine - File A tries to import File B, which tries to import File A. How to Avoid: Ensure your modules are properly installed and avoid overly complex import chains. Fine’s AI can track your imports and warn you about potential issues, making it easier to manage your dependencies. A Recurring Theme in the Python Errors AI Makes NameErrors, ImportErrors, AttributeErrors, KeyErrors - AI will keep making these mistakes as long as it doesn’t have the full context of your codebase. It’s like if I were to ask you to write code for my platform, but without showing you my existing repo. How would you know what to refer to? How Fine Can Help You Avoid These Errors Fine is designed to be your coding companion, catching these common Python errors before they can trip you up. Using advanced AI algorithms, Fine provides real-time feedback, highlights potential issues, and offers tailored suggestions to keep your code clean and error-free. Whether you’re dealing with indentation issues, NameErrors, or TypeErrors, Fine acts as your second pair of eyes, ensuring that your development process remains smooth and efficient. With Fine integrated into your workflow, you can focus on what really matters—building great software. Conclusion Python errors can be a major headache, especially in a startup environment where every line of code counts. By understanding these common errors and how to avoid them, you can write cleaner, more reliable code. And with Fine by your side, you’ll catch and fix these errors effortlessly, keeping your projects on track and your sanity intact. Be careful of code generators that aren’t aware of your existing codebase, such as ChatGPT and GitHub Copilot—they’re more likely to make simple Python mistakes. Ready to take your Python development to the next level? Try Fine today with our free trial and see how our AI-powered coding assistant can help you write error-free code faster. Sign up now, or schedule a demo to discover how Fine can integrate seamlessly into your workflow and boost your team's productivity. Don’t let simple errors slow you down—let Fine handle the details so you can focus on building great software. Start building today Try out the smoothest way to build, launch and manage an app Try for Free -> © Fine.dev - All rights reserved. Product Overview AI Workflows Pricing & Plans Changelog Blog Docs Company Press Terms & Conditions Privacy policy | 2026-01-13T08:49:33 |
https://dev.to/t/webdev/page/79 | Web Development Page 79 - 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 Web Development Follow Hide Because the internet... Create Post submission guidelines Be nice. Be respectful. Assume best intentions. Be kind, rewind. Older #webdev posts 76 77 78 79 80 81 82 83 84 Posts Left menu 👋 Sign in for the ability to sort posts by relevant , latest , or top . Right menu I built two open-source tools faster by letting AI write most of the code Benjamin Touchard Benjamin Touchard Benjamin Touchard Follow Dec 20 '25 I built two open-source tools faster by letting AI write most of the code # ai # programming # productivity # webdev Comments Add Comment 2 min read ⚠️ JavaScript Equality Is Lying to You mayank sagar mayank sagar mayank sagar Follow Jan 9 ⚠️ JavaScript Equality Is Lying to You # webdev # javascript # frontend 1 reaction Comments Add Comment 2 min read Day 1: Building a Holiday Budget Tracker with Svelte 5 💸 Michael Amachree Michael Amachree Michael Amachree Follow Dec 16 '25 Day 1: Building a Holiday Budget Tracker with Svelte 5 💸 # svelte # webdev # javascript # tutorial Comments Add Comment 2 min read Stop Screenshotting Emails Into Figma Christopher Rogers Christopher Rogers Christopher Rogers Follow Dec 17 '25 Stop Screenshotting Emails Into Figma # showdev # productivity # figma # webdev Comments Add Comment 2 min read Understanding Three.js Lighting — A Concise Reference Peter Riding Peter Riding Peter Riding Follow Dec 18 '25 Understanding Three.js Lighting — A Concise Reference # threejs # webdev # javascript # cheatsheet 1 reaction Comments Add Comment 3 min read Which AI Can Create the Coolest Web Page? GPT 5.2 vs Gemini 3.0 Pro vs Opus 4.5 vs bolt.new vs v0 vs Lovable Yukapero Yukapero Yukapero Follow Dec 15 '25 Which AI Can Create the Coolest Web Page? GPT 5.2 vs Gemini 3.0 Pro vs Opus 4.5 vs bolt.new vs v0 vs Lovable # ai # webdev # frontend # vibecoding 3 reactions Comments Add Comment 14 min read 🔍 Why Are API Requests So Hard to Debug Without the Right Tool? Muhammad Haris Muhammad Haris Muhammad Haris Follow Dec 16 '25 🔍 Why Are API Requests So Hard to Debug Without the Right Tool? # webdev # api # graphql # productivity 5 reactions Comments Add Comment 2 min read From instructions to binaries to programs imasystem.engineer imasystem.engineer imasystem.engineer Follow Dec 18 '25 From instructions to binaries to programs # systems # webdev # learning # architecture Comments Add Comment 3 min read Transaction Rollback in MongoDB: What Actually Happens When Things Go Wrong Moriam Akter Swarna Moriam Akter Swarna Moriam Akter Swarna Follow Dec 17 '25 Transaction Rollback in MongoDB: What Actually Happens When Things Go Wrong # webdev # database # mongodb # mongoose Comments Add Comment 4 min read 10 Blazor Coding Mistakes I See in Real Projects (and How to Avoid Them) Chandradev Chandradev Chandradev Follow Dec 17 '25 10 Blazor Coding Mistakes I See in Real Projects (and How to Avoid Them) # webdev # programming # blazor # blazorwebassembly Comments Add Comment 2 min read OpenAI Released GPT Image 1.5 — I Built a Free Web App to Try It Instantly lei pan lei pan lei pan Follow Dec 17 '25 OpenAI Released GPT Image 1.5 — I Built a Free Web App to Try It Instantly # showdev # webdev # openai # ai Comments Add Comment 2 min read CSS Max-Width Explained: Stop Breaking Your Layout Satyam Gupta Satyam Gupta Satyam Gupta Follow Dec 16 '25 CSS Max-Width Explained: Stop Breaking Your Layout # css # webdev # programming # beginners Comments Add Comment 4 min read Launch a custom blog in 5 minutes using SleekCMS Yusuf B Yusuf B Yusuf B Follow for SleekCMS Jan 9 Launch a custom blog in 5 minutes using SleekCMS # wordpress # webdev # sleekcms # contentwriting Comments Add Comment 2 min read Building HTML Forms Without a Backend: A Developer's Guide to Static Site Forms HostSpica HostSpica HostSpica Follow Dec 17 '25 Building HTML Forms Without a Backend: A Developer's Guide to Static Site Forms # webdev # tutorial # html # serverless Comments Add Comment 3 min read Determinism Is Not the Opposite of Intelligence rokoss21 rokoss21 rokoss21 Follow Dec 15 '25 Determinism Is Not the Opposite of Intelligence # discuss # webdev # programming # ai Comments Add Comment 2 min read The Ultimate Image Solution for Symfony - stop writing srcset manually Jozef Môstka Jozef Môstka Jozef Môstka Follow Jan 9 The Ultimate Image Solution for Symfony - stop writing srcset manually # symfony # php # webdev # images Comments Add Comment 5 min read Go's Defer: Simple Rules, Deep Runtime Truths with intuitions. Saiful Islam Saiful Islam Saiful Islam Follow Jan 9 Go's Defer: Simple Rules, Deep Runtime Truths with intuitions. # go # webdev # core # architecture 2 reactions Comments Add Comment 7 min read Service Levels in Angular Varad Shirsath Varad Shirsath Varad Shirsath Follow Dec 20 '25 Service Levels in Angular # angular # webdev # typescript # frontend Comments Add Comment 4 min read Discovering Hiawatha: A Lightweight Web Server for Modern PHP Deployments kingyou kingyou kingyou Follow Dec 16 '25 Discovering Hiawatha: A Lightweight Web Server for Modern PHP Deployments # php # webdev # tooling # security Comments Add Comment 2 min read Introduction to CSS Preprocessors: Unlocking the Power of SASS and LESS Sharique Siddiqui Sharique Siddiqui Sharique Siddiqui Follow Dec 16 '25 Introduction to CSS Preprocessors: Unlocking the Power of SASS and LESS # css # advanced # webdev # frontend Comments Add Comment 3 min read Free Tools I Use Daily as an Indie Developer Rushikesh Bodakhe Rushikesh Bodakhe Rushikesh Bodakhe Follow Jan 9 Free Tools I Use Daily as an Indie Developer # webdev # programming # ai # javascript 1 reaction Comments Add Comment 2 min read GraphQL vs. REST: Why Your Next API Might Prefer GraphQL A S M Muntaheen A S M Muntaheen A S M Muntaheen Follow Dec 16 '25 GraphQL vs. REST: Why Your Next API Might Prefer GraphQL # graphql # restapi # webdev # programming Comments Add Comment 3 min read Criei uma extensão para VS Code que transforma TODOs em um quadro Kanban e issues reais no Jira Dante J. Anjos Dante J. Anjos Dante J. Anjos Follow Jan 9 Criei uma extensão para VS Code que transforma TODOs em um quadro Kanban e issues reais no Jira # webdev # vscode # productivity # fullstack 1 reaction Comments 2 comments 3 min read n8n : l’outil d’automatisation que tout le monde installe… et que peu utilisent vraiment florentin - Antesy florentin - Antesy florentin - Antesy Follow Dec 20 '25 n8n : l’outil d’automatisation que tout le monde installe… et que peu utilisent vraiment # webdev # programming # ai Comments Add Comment 2 min read Angular Signal Forms: How to Structure Large Forms Without Losing Your Mind Brian Treese Brian Treese Brian Treese Follow Jan 9 Angular Signal Forms: How to Structure Large Forms Without Losing Your Mind # angular # javascript # webdev # typescript Comments Add Comment 11 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 | 2026-01-13T08:49:33 |
https://dev.to/niteshtaliyan/instagram-bot-using-python-1kop | Instagram bot using python - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse NITESH TALIYAN Posted on Sep 4, 2021 Instagram bot using python # python # programming # algorithms # actionshackathon Ever worried😟 about not getting more likes👍 or followers🥰 for your Instagram page. Forget about it. In this python project, we will work on an Instagram automation module, which will boost the followers and likes for your Instagram page or post. You can give your criteria such as what comments to leave, whom to follow, types of posts to like, etc. This automation automatically opens the browser, logs in, and starts doing the tasks as you instructed. It also tracks and saves the list of users that were followed which will be useful for you to evaluate later and unfollow them after some time. The advantage of such automation is, it logs every action performed by itself. It mentions the post-it liked, location, commented or not, description, etc. https://www.linkedin.com/posts/niteshtaliyan_automation-python-selenium-activity-6680706674166181888-sWP3 If you have any doubts you can DM me😊 Follow for more @niteshtaliyan 💪 website - https://www.niteshtaliyan.tech instagram - https://www.instagram.com/nitesh_taliyan LinkedIn - https://www.linkedin.com/in/niteshtaliyan Top comments (4) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Collapse Expand Kinjal Kinjal Kinjal Follow Learner. Joined Feb 25, 2021 • Sep 5 '21 Dropdown menu Copy link Hide I thought instagram is very strict these days for automated likes, comments etc. Even the account will have higher chance of getting blocked for such automation. Like comment: Like comment: 3 likes Like Comment button Reply Collapse Expand delltrak delltrak delltrak Follow Joined Sep 9, 2021 • Sep 9 '21 Dropdown menu Copy link Hide I agree with you. Like comment: Like comment: 2 likes Like Comment button Reply Collapse Expand Murillo Javier Murillo Javier Murillo Javier Follow I am 14 years old, I am DEV since I was 12 years old, I have a certificate in python language, I know HTML, CSS and JavaScript Pindamonhangaba-SP now Email murillouniniq@gmail.com Work Estudo Joined Sep 28, 2021 • Sep 28 '21 Dropdown menu Copy link Hide Muita gente ta usando macro pra não tomar ban na conta. Like comment: Like comment: 1 like Like Comment button Reply Collapse Expand Murillo Javier Murillo Javier Murillo Javier Follow I am 14 years old, I am DEV since I was 12 years old, I have a certificate in python language, I know HTML, CSS and JavaScript Pindamonhangaba-SP now Email murillouniniq@gmail.com Work Estudo Joined Sep 28, 2021 • Sep 28 '21 Dropdown menu Copy link Hide Pra que serve o unicórnio? Like comment: Like comment: 1 like Like Comment button Reply Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse NITESH TALIYAN Follow Location Meerut, India Joined Jul 20, 2021 More from NITESH TALIYAN Happy Programmers' day # programming # performance # beginners # codereview Common telephonic interview questions - Section 1 # re # career # codereview # programming Instagram automation by python # devops # python # programming 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/voxel51/neurlps-2024-creating-spiqa-addressing-the-limitations-of-existing-datasets-for-scientific-vqa-1c1b | NeurlPS 2024 - Creating SPIQA: Addressing the Limitations of Existing Datasets for Scientific VQA - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Jimmy Guerrero for Voxel51 Posted on Dec 6, 2024 • Edited on Dec 10, 2024 NeurlPS 2024 - Creating SPIQA: Addressing the Limitations of Existing Datasets for Scientific VQA # computervision # datascience # ai # machinelearning Check out Harpreet Sahota 's conversation with Shraman Pramanick about his NeurIPS 2024 paper, “Creating SPIQA: Addressing the Limitations of Existing Datasets for Scientific VQAs”. Complete interview and discussion on YouTube Blog Post Research Paper Heading to NeurIPS in Vancouver next week? Visit the Voxel51 crew at booth #415! Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Voxel51 Follow More from Voxel51 Elderly Action Recognition: No One Should Age Alone, AI’s Promise for the Next Generation of Elders # computervision # ai # machinelearning # datascience Journey into Visual AI: Exploring FiftyOne Together — Part IV Model Evaluation # computervision # machinelearning # ai # datascience How to Tame Your (Data) Dragon # computervision # ai # machinelearning # datascience 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/t/roundrecap | Roundrecap - 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 # roundrecap Follow Hide Sharing stories, scores, and highlights from recent rounds Create Post Older #roundrecap posts 1 2 Posts Left menu 👋 Sign in for the ability to sort posts by relevant , latest , or top . Right menu 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 | 2026-01-13T08:49:33 |
https://dev.to/voxel51/eccv-2024-skeleton-recall-loss-for-connectivity-conserving-and-resource-efficient-segmentation-of-bij | ECCV 2024 - Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Jimmy Guerrero for Voxel51 Posted on Nov 22, 2024 ECCV 2024 - Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures # computervision # machinelearning # datascience # ai In this talk, we present Skeleton Recall Loss, a novel loss function for topologically accurate and efficient segmentation of thin, tubular structures, such as roads, nerves, or vessels. By circumventing expensive GPU-based operations, we reduce computational overheads by up to 90% compared to the current state-of-the-art, while achieving overall superior performance in segmentation accuracy and connectivity preservation. Additionally, it is the first multi-class capable loss function for thin structure segmentation. ECCV 2024 Paper Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures About the Speakers Maximilian Rokuss holds a M.Sc. in Physics from Heidelberg University, now PhD Student in Medical Image Computing at German Cancer Research Center (DKFZ) and Heidelberg University Yannick Kirchoff holds a M.Sc. in Physics from Heidelberg University, now PhD Student in Medical Image Computing at German Cancer Research Center (DKFZ) and Helmholtz Information and Data Science School for Health Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Voxel51 Follow More from Voxel51 Elderly Action Recognition: No One Should Age Alone, AI’s Promise for the Next Generation of Elders # computervision # ai # machinelearning # datascience Journey into Visual AI: Exploring FiftyOne Together — Part IV Model Evaluation # computervision # machinelearning # ai # datascience How to Tame Your (Data) Dragon # computervision # ai # machinelearning # datascience 💎 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 | 2026-01-13T08:49:33 |
https://www.fine.dev/blog/common-python-errors#error-5-importerrors | Most Common Python Errors When Using AI Home Docs Changelog Pricing Sign in Get started -> Menu Home Docs Changelog Pricing <- Go Back Most Common Python Errors When Using AI Introduction Python is a favorite among backend developers, particularly in the fast-paced world of startups where flexibility and speed are key. But let’s be honest—Python’s simplicity can sometimes be deceiving, and even the most seasoned developers can find ourselves pulling our hair out trying to understand why the code doesn’t work. In this article, we’ll dive into the top 10 Python errors that backend developers frequently encounter, especially in smaller startup teams. We’ll explain why these errors happen and provide tips on how to avoid them. We’ll also look at whether the common AI tools are likely to make the errors or can help you spot and fix them. Table of Contents Introduction Error 1: TypeErrors Error 2: NameErrors Error 3: IndexErrors Error 4: KeyErrors Error 5: ImportErrors A Recurring Theme in the Python Errors AI Makes How Fine Can Help You Avoid These Errors Conclusion Error 1: TypeErrors TypeErrors occur when you try to perform an operation on incompatible data types, like trying to add a string to an integer. It’s the programming equivalent of mixing oil and water—not going to happen. Python is dynamically typed, meaning variables don’t have fixed types, but this flexibility can sometimes lead to unexpected type mismatches. How to Avoid: Always check the data types you’re working with, and consider using type hints in your function definitions to ensure compatibility. AI models might try to perform operations on incompatible types or fail to include necessary type conversions. Fine will test to make sure there are no TypeErrors and fix any that occur. Fine’s PR review feature also identifies TypeErrors in GitHub PRs that human developers have written, ensuring that they don’t make it into production. Error 2: NameErrors (Shock horror, they’re back) No serious Python developer goes around making NameErrors anymore, right? Well, here’s the thing. ChatGPT and other AI coding tools make NameErrors all the time. They can’t help it. They don’t know what you’ve named things in your code, so they have to make a logical guess or use a placeholder - which will usually be wrong. Even the best models, such as o1 and Claude Sonnet 3.5, are helpless here. In fact, many people accuse AI of “hallucinating”, when really they’re referring to a simple NameError, where the AI isn’t to blame. Whilst simple to fix (in theory), this is quite a pain and every developer should have their eyes open for NameErrors (and indentation issues also - remember those?) when using AI coding tools that don’t have full context awareness. Fine is the AI coding tool to choose to avoid these errors. Because it indexes your repositories and issues, the AI can identify the correct names in your codebase and save you hours of debugging. Error 3: IndexErrors IndexErrors arise when you try to access an index that doesn’t exist in a list. Imagine trying to grab the fifth apple from a basket that only has four—you’re bound to run into trouble. This often happens due to off-by-one errors, where the index is either too high or too low. If you’re not familiar with how python’s range works or how slicing works, it’s a good idea to sharpen up on it to avoid index errors. How to Avoid: Double-check your list boundaries and validate your input data. Fine can highlight potential IndexErrors, helping you avoid those pesky off-by-one mistakes. This is particularly useful in scenarios where your code dynamically generates or manipulates lists, which can lead to unpredictable indexing issues. Error 4: KeyErrors KeyErrors happen when you try to access a dictionary key that isn’t present. It’s like asking for the keys to a car that you don’t own—not going to get far! How to Avoid: Use the .get() method or check for key existence before access. Fine can help by suggesting safe dictionary access patterns, reducing the risk of a KeyError. Error 5: ImportErrors ImportErrors happen when a module isn’t imported correctly, either because it’s missing, you’ve made a typo in the import path, or you’ve created a circular import. These errors are common when managing dependencies across different environments. Imagine - File A tries to import File B, which tries to import File A. How to Avoid: Ensure your modules are properly installed and avoid overly complex import chains. Fine’s AI can track your imports and warn you about potential issues, making it easier to manage your dependencies. A Recurring Theme in the Python Errors AI Makes NameErrors, ImportErrors, AttributeErrors, KeyErrors - AI will keep making these mistakes as long as it doesn’t have the full context of your codebase. It’s like if I were to ask you to write code for my platform, but without showing you my existing repo. How would you know what to refer to? How Fine Can Help You Avoid These Errors Fine is designed to be your coding companion, catching these common Python errors before they can trip you up. Using advanced AI algorithms, Fine provides real-time feedback, highlights potential issues, and offers tailored suggestions to keep your code clean and error-free. Whether you’re dealing with indentation issues, NameErrors, or TypeErrors, Fine acts as your second pair of eyes, ensuring that your development process remains smooth and efficient. With Fine integrated into your workflow, you can focus on what really matters—building great software. Conclusion Python errors can be a major headache, especially in a startup environment where every line of code counts. By understanding these common errors and how to avoid them, you can write cleaner, more reliable code. And with Fine by your side, you’ll catch and fix these errors effortlessly, keeping your projects on track and your sanity intact. Be careful of code generators that aren’t aware of your existing codebase, such as ChatGPT and GitHub Copilot—they’re more likely to make simple Python mistakes. Ready to take your Python development to the next level? Try Fine today with our free trial and see how our AI-powered coding assistant can help you write error-free code faster. Sign up now, or schedule a demo to discover how Fine can integrate seamlessly into your workflow and boost your team's productivity. Don’t let simple errors slow you down—let Fine handle the details so you can focus on building great software. Start building today Try out the smoothest way to build, launch and manage an app Try for Free -> © Fine.dev - All rights reserved. Product Overview AI Workflows Pricing & Plans Changelog Blog Docs Company Press Terms & Conditions Privacy policy | 2026-01-13T08:49:33 |
https://dev.to/t/postmarkchallenge | Postmark Challenge - 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 Postmark Challenge Follow Hide This is the official tag for submissions and announcements related to the Postmark Challenge. Create Post Older #postmarkchallenge posts 1 2 3 4 5 6 Posts Left menu 👋 Sign in for the ability to sort posts by relevant , latest , or top . Right menu InboxNegotiator: Turning Debt Reminders into Payment Plans with AI and Postmark FranP-code FranP-code FranP-code Follow Jun 9 '25 InboxNegotiator: Turning Debt Reminders into Payment Plans with AI and Postmark # devchallenge # postmarkchallenge # webdev # api Comments Add Comment 4 min read One Inbox to Rule Them All: My Personalized Newsletter Digest App - Powered by Postmark deva deva deva Follow Jun 9 '25 One Inbox to Rule Them All: My Personalized Newsletter Digest App - Powered by Postmark # devchallenge # postmarkchallenge # webdev # api Comments Add Comment 2 min read CodeReview Mail - Collaborative Development via Email ANIRUDDHA ADAK ANIRUDDHA ADAK ANIRUDDHA ADAK Follow Jun 8 '25 CodeReview Mail - Collaborative Development via Email # devchallenge # postmarkchallenge # webdev # api Comments Add Comment 4 min read Postmark Transaction Analyzer JOHN RATNA KUMAR AKKISETTI JOHN RATNA KUMAR AKKISETTI JOHN RATNA KUMAR AKKISETTI Follow Jun 9 '25 Postmark Transaction Analyzer # devchallenge # postmarkchallenge # webdev # api 4 reactions Comments 1 comment 2 min read leadmark.email: Turn Your Inbox into a Sales Automation Engine via Postmark Andrew Miracle Andrew Miracle Andrew Miracle Follow Jun 9 '25 leadmark.email: Turn Your Inbox into a Sales Automation Engine via Postmark # devchallenge # postmarkchallenge # webdev # api 2 reactions Comments Add Comment 4 min read Ritsu-Pi EmailOps: Homelab Management via Email powered by Postmark👓 Fahmi Noor Fiqri Fahmi Noor Fiqri Fahmi Noor Fiqri Follow Jun 4 '25 Ritsu-Pi EmailOps: Homelab Management via Email powered by Postmark👓 # devchallenge # postmarkchallenge # webdev # api Comments Add Comment 3 min read Postmark Challenge. Gentle Inbox Jonny B Jonny B Jonny B Follow Jun 8 '25 Postmark Challenge. Gentle Inbox # devchallenge # postmarkchallenge # webdev # api 1 reaction Comments 1 comment 4 min read How to Build an Email Notification System Using Postmark (No Coding Needed) Joao Dalbem Joao Dalbem Joao Dalbem Follow May 31 '25 How to Build an Email Notification System Using Postmark (No Coding Needed) # postmarkchallenge # devchallenge Comments Add Comment 2 min read Save time with sumsummary.com! Johannes Johannes Johannes Follow Jun 8 '25 Save time with sumsummary.com! # devchallenge # postmarkchallenge # webdev # ai 1 reaction Comments Add Comment 5 min read Congrats to the Winners of Postmark Challenge: Inbox Innovators! dev.to staff dev.to staff dev.to staff Follow for The DEV Team Jun 24 '25 Congrats to the Winners of Postmark Challenge: Inbox Innovators! # devchallenge # postmarkchallenge # webdev # api 59 reactions Comments 23 comments 2 min read Introducing dearme.email vincent d warmerdam vincent d warmerdam vincent d warmerdam Follow May 27 '25 Introducing dearme.email # devchallenge # postmarkchallenge # webdev # api 15 reactions Comments 7 comments 2 min read MarketMail Caleb Nkunze Caleb Nkunze Caleb Nkunze Follow May 27 '25 MarketMail # devchallenge # postmarkchallenge # webdev # api 7 reactions Comments Add Comment 2 min read hotline.email: AI Powered Multi-role single point inbound email categorization with Postmark and Agent.ai Fayaz Fayaz Fayaz Follow Jun 9 '25 hotline.email: AI Powered Multi-role single point inbound email categorization with Postmark and Agent.ai # devchallenge # postmarkchallenge # webdev # api 25 reactions Comments 11 comments 3 min read Join the Postmark Challenge: Inbox Innovators - $3,000 in Prizes! dev.to staff dev.to staff dev.to staff Follow for The DEV Team May 21 '25 Join the Postmark Challenge: Inbox Innovators - $3,000 in Prizes! # devchallenge # postmarkchallenge # webdev # api 148 reactions Comments 84 comments 4 min read Mailbase: A Trustworthy Foundation for Ethical Inbox-Aware Apps Jérémie Lumbroso Jérémie Lumbroso Jérémie Lumbroso Follow Jun 9 '25 Mailbase: A Trustworthy Foundation for Ethical Inbox-Aware Apps # devchallenge # postmarkchallenge # webdev # api 12 reactions Comments Add Comment 5 min read EPB: Turn Emails into Code - AI-Powered Pull Requests from Your Inbox Adam Adam Adam Follow Jun 9 '25 EPB: Turn Emails into Code - AI-Powered Pull Requests from Your Inbox # devchallenge # postmarkchallenge # webdev # api 10 reactions Comments Add Comment 4 min read WooCommerce Order Status Updates via Email Leveraging Postmark Inbound Capabilities Vikas V Vikas V Vikas V Follow Jun 9 '25 WooCommerce Order Status Updates via Email Leveraging Postmark Inbound Capabilities # devchallenge # postmarkchallenge # webdev # api 12 reactions Comments 1 comment 4 min read Sumrise: Personal Spend Analyzer Shriji Shriji Shriji Follow Jun 7 '25 Sumrise: Personal Spend Analyzer # devchallenge # postmarkchallenge # webdev # api 8 reactions Comments 1 comment 4 min read MinimalizEmail: AI-Powered Email Management for Maximum Productivity Vartika T Rao Vartika T Rao Vartika T Rao Follow Jun 9 '25 MinimalizEmail: AI-Powered Email Management for Maximum Productivity # devchallenge # postmarkchallenge # webdev # api 19 reactions Comments Add Comment 5 min read 🎯 AI Resume Ranking System Vivek V. Vivek V. Vivek V. Follow for AWS Community Builders Jun 9 '25 🎯 AI Resume Ranking System # devchallenge # postmarkchallenge # webdev # api 20 reactions Comments 4 comments 5 min read Postc.art: Send Beautiful Postcards by Email Arthur Gladfield Arthur Gladfield Arthur Gladfield Follow Jun 9 '25 Postc.art: Send Beautiful Postcards by Email # devchallenge # postmarkchallenge # webdev # ai 5 reactions Comments Add Comment 8 min read Clause Clarity: AI Contract Review via Inbound Email Victor Mbamara 🇳🇬 Victor Mbamara 🇳🇬 Victor Mbamara 🇳🇬 Follow Jun 8 '25 Clause Clarity: AI Contract Review via Inbound Email # devchallenge # postmarkchallenge # webdev # api 5 reactions Comments Add Comment 2 min read Deejay - Request Songs Through Email Deepto Deepto Deepto Follow Jun 9 '25 Deejay - Request Songs Through Email # devchallenge # postmarkchallenge # webdev # api 4 reactions Comments Add Comment 2 min read Add 12 Wines in 12 Seconds Russ Russ Russ Follow Jun 9 '25 Add 12 Wines in 12 Seconds # devchallenge # postmarkchallenge # webdev # api 4 reactions Comments Add Comment 2 min read Schedule Events from your Email Shivam Shivam Shivam Follow Jun 8 '25 Schedule Events from your Email # devchallenge # postmarkchallenge # webdev # api 5 reactions Comments Add Comment 2 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 | 2026-01-13T08:49:33 |
https://popcorn.forem.com/t/adventure | Adventure - Popcorn Movies and TV 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 Popcorn Movies and TV Close # adventure Follow Hide Adventure genre discussion Create Post Posts Left menu 👋 Sign in for the ability to sort posts by relevant , latest , or top . Right menu IGN: Baahubali: The Epic - Official Trailer #2 (2025) Gaming News Gaming News Gaming News Follow Oct 19 '25 IGN: Baahubali: The Epic - Official Trailer #2 (2025) # adventure # action # directorscut # movies Comments Add Comment 1 min read IGN: Baahubali: The Epic - Official Trailer #2 (2025) Gaming News Gaming News Gaming News Follow Oct 18 '25 IGN: Baahubali: The Epic - Official Trailer #2 (2025) # adventure # action # marketing # movies Comments Add Comment 1 min read IGN: Baahubali: The Epic - Official Trailer #2 (2025) Gaming News Gaming News Gaming News Follow Oct 18 '25 IGN: Baahubali: The Epic - Official Trailer #2 (2025) # extendededition # adventure # action # movies Comments Add Comment 1 min read IGN: The Pout-Pout Fish - Official Trailer (2026) Nick Offerman, Jordin Sparks, Amy Sedaris Gaming News Gaming News Gaming News Follow Oct 16 '25 IGN: The Pout-Pout Fish - Official Trailer (2026) Nick Offerman, Jordin Sparks, Amy Sedaris # celebrities # adventure # animation # movies Comments Add Comment 1 min read IGN: Baahubali: The Epic - Official Trailer #2 (2025) Gaming News Gaming News Gaming News Follow Oct 18 '25 IGN: Baahubali: The Epic - Official Trailer #2 (2025) # adventure # action # directorscut # movies 1 reaction Comments Add Comment 1 min read IGN: Greenland 2: Migration - Official Trailer (2025) Gerard Butler Gaming News Gaming News Gaming News Follow Sep 26 '25 IGN: Greenland 2: Migration - Official Trailer (2025) Gerard Butler # movies # adventure # action # scifi Comments Add Comment 1 min read Mr Sunday Movies: Jurassic YAWN? - Jurassic World Rebirth Review Movie News Movie News Movie News Follow Jul 9 '25 Mr Sunday Movies: Jurassic YAWN? - Jurassic World Rebirth Review # movies # reviews # scifi # adventure Comments Add Comment 1 min read Mr Sunday Movies: Jurassic YAWN? - Jurassic World Rebirth Review Movie News Movie News Movie News Follow Jul 8 '25 Mr Sunday Movies: Jurassic YAWN? - Jurassic World Rebirth Review # movies # reviews # scifi # adventure 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 Popcorn Movies and TV — Movie and TV enthusiasm, criticism and everything in-between. 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 . Popcorn Movies and TV © 2016 - 2026. Let's watch something great! Log in Create account | 2026-01-13T08:49:33 |
https://git-scm.com/ | Git Git is a free and open source distributed version control system designed to handle everything from small to very large projects with speed and efficiency. Git is lightning fast and has a huge ecosystem of GUIs , hosting services , and command-line tools . About Git's performance and ecosystem Learn Pro Git book, videos, tutorials, and cheat sheet Tools Command line tools, GUIs, and hosting services Reference Git's reference documentation Install Binary releases for all major platforms. Community Get involved! Bug reporting, mailing list, chat, development and more. Pro Git by Scott Chacon and Ben Straub is available to read online for free . Dead tree versions are available on Amazon.com . Latest source release 2.52.0 Release Notes (2025-11-17) Install GitHub Repository About this site Patches, suggestions, and comments are welcome. Git is a member of Software Freedom Conservancy | 2026-01-13T08:49:33 |
https://open.forem.com/new/security | New Post - Open 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 Open Forem Close Join the Open Forem Open Forem is a community of 3,676,891 amazing developers Continue with Apple Continue with Google Continue with Facebook Continue with Forem Continue with GitHub 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 Open 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 Open Forem — A general discussion space for the Forem community. If it doesn't have a home elsewhere, it belongs here 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 . Open Forem © 2016 - 2026. Where all the other conversations belong Log in Create account | 2026-01-13T08:49:33 |
https://dev.to/sebalix | Sébastien Alix - 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 Sébastien Alix 404 bio not found Joined Joined on Aug 8, 2022 github website Work Odoo developer at Camptocamp More info about @sebalix Badges Three Year Club This badge celebrates the longevity of those who have been a registered member of the DEV Community for at least three years. Got it Close Two Year Club This badge celebrates the longevity of those who have been a registered member of the DEV Community for at least two years. Got it Close 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 One Year Club This badge celebrates the longevity of those who have been a registered member of the DEV Community for at least one year. Got it Close Organizations Camptocamp Business Solutions Skills/Languages Python, Odoo Post 1 post published Comment 0 comments written Tag 0 tags followed oca-port: new OCA tool to help with modules migration Sébastien Alix Sébastien Alix Sébastien Alix Follow for Camptocamp Business Solutions Aug 15 '22 oca-port: new OCA tool to help with modules migration # odoo # oca # github # git 7 reactions Comments Add Comment 3 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 | 2026-01-13T08:49:33 |
https://dev.to/voxel51/eccv-2024-closing-the-gap-between-satellite-and-street-view-imagery-using-generative-models-n8h | ECCV 2024: Closing the Gap Between Satellite and Street-View Imagery Using Generative Models - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Jimmy Guerrero for Voxel51 Posted on Nov 22, 2024 ECCV 2024: Closing the Gap Between Satellite and Street-View Imagery Using Generative Models # computervision # machinelearning # datascience # ai With the growing availability of satellite imagery (e.g., Google Earth), nearly every part of the world can be mapped, though street-view images remain limited. Creating street views from satellite data is crucial for applications like virtual model generation, media content enhancement, 3D gaming, and simulations. This task, known as satellite-to-ground cross-view synthesis, is tackled by our geometry-aware framework, which maintains geometric precision and relative geographical positioning using satellite information. ECCV 2024 Paper Geospecific View Generation — Geometry-Context Aware High-resolution Ground View Inference from Satellite Views About the Speaker Ningli Xu is a Ph.D. student at The Ohio State University, specializing in generative AI and computer vision, with a focus on addressing image and video generation challenges in the geospatial domain. Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Voxel51 Follow More from Voxel51 Elderly Action Recognition: No One Should Age Alone, AI’s Promise for the Next Generation of Elders # computervision # ai # machinelearning # datascience Journey into Visual AI: Exploring FiftyOne Together — Part IV Model Evaluation # computervision # machinelearning # ai # datascience How to Tame Your (Data) Dragon # computervision # ai # machinelearning # datascience 💎 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 Forem — 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 . Forem © 2016 - 2026. We're a place where coders share, stay up-to-date and grow their careers. Log in Create account | 2026-01-13T08:49:33 |
https://dev.to/_402ccbd6e5cb02871506/super-fast-markdown-linting-for-go-developers-meet-gomarklint-3ikd#the-why-the-motivation | Super Fast Markdown Linting for Go Developers: Meet gomarklint - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Kazu Posted on Jan 13 Super Fast Markdown Linting for Go Developers: Meet gomarklint # go # performance # showdev # markdown The "Why" (The Motivation) Documentation is the heart of any project, but keeping it consistent is a nightmare. While working on various Go projects, I realized a few things about my workflow: Context Switching Costs: I love Go's speed and simplicity. Having to install Node.js or Ruby just to run a Markdown linter in a Go project felt "heavy." CI Fatigue: In large repositories, documentation checks shouldn't take seconds—they should take milliseconds. Every second saved in CI is a win for developer experience. The "Broken Link" Problem: There’s nothing more embarrassing than shipping a README with dead links. I needed a tool that catches these issues instantly. I couldn't find a tool that was Go-native, ultra-fast, and zero-config by default, so I decided to build one. The goal for gomarklint was simple: Make Markdown linting so fast and easy that you never have an excuse to skip it. Speed Performance When I say "fast," I mean Go-fast. In many CI/CD pipelines, linting documentation is often the bottleneck that adds unnecessary seconds (or even minutes) to every PR. gomarklint changes that. By leveraging Go's concurrency and efficient string handling, it delivers near-instant feedback. The Benchmark: I tested gomarklint against a large documentation set: Total Files: 180 Markdown files Total Volume: 100,000+ lines of text Execution Time: < 50ms To put that in perspective, 50ms is literally faster than the blink of a human eye. You can run this on every single file save without ever noticing a stutter in your workflow. By removing the overhead of a virtual machine or a heavy runtime, gomarklint ensures that your documentation quality stays high without sacrificing your velocity. Key Features gomarklint doesn't just check syntax; it enforces a logical structure for your documentation. Here are the core rules it handles out of the box: Heading Hierarchy Enforcement : Ever seen a document jump from an H2 directly to an H4? It breaks the visual flow and accessibility. gomarklint ensures your heading levels follow a strict, logical sequence. Duplicate Heading Detection : Identical headings in the same file can break anchor links (e.g., #features vs #features-1). We catch these early so your internal navigation never breaks. Broken Link Checker (Internal & External) : This is my favorite. It scans your Markdown for links and validates them. No more 404s for your users when they click on a "Getting Started" guide or an external API reference. Configuration via JSON : While it works great with zero config, you can easily tweak rules or ignore specific paths using a simple .gomarklint.json file. Quick Start # install (choose one) go install github.com/shinagawa-web/gomarklint@latest # or clone and build manually git clone https://github.com/shinagawa-web/gomarklint cd gomarklint make build # or: go build ./cmd/gomarklint Enter fullscreen mode Exit fullscreen mode 1) Initialize config (optional but recommended) gomarklint init Enter fullscreen mode Exit fullscreen mode This creates .gomarklint.json with sensible defaults: { "include": ["."], "ignore": ["node_modules", "vendor"], "minHeadingLevel": 2, "enableHeadingLevelCheck": true, "enableDuplicateHeadingCheck": true, "enableLinkCheck": false, "skipLinkPatterns": [], "outputFormat": "text" } Enter fullscreen mode Exit fullscreen mode You can edit it anytime — CLI flags override config values. 2) Run it # lint current directory recursively gomarklint ./... # lint specific targets gomarklint docs README.md internal/handbook Enter fullscreen mode Exit fullscreen mode What's Next? (Roadmap) gomarklint is already stable and fast, but I have a clear vision for where it’s headed. I’m actively working on expanding its rule set to cover even more edge cases and best practices. Here’s what you can expect in the coming updates: max-line-length Enforcement : To keep your Markdown source files readable in any editor or GitHub's UI. Image Alt-Text Validation : Improving accessibility by ensuring every image has a descriptive alt attribute. Custom Rules via JSON : Giving you the power to define your own project-specific rules in .gomarklint.json. Auto-fixing (The Dream) : While currently focused on linting, I’m exploring ways to automatically fix simple issues like heading level skips. We are Open for Contributions! If you have a rule in mind that would make your documentation better, or if you find a bug, please open an Issue or a Pull Request on GitHub. I’d love to build the future of this tool together with the community. Wrap Up Building gomarklint has been an incredible journey into the world of Go performance and static analysis. It started as a small tool for my own workflow, but I realized that many other developers are likely facing the same "slow linting" frustration. If you're looking for a way to keep your documentation spotless without adding bloat to your CI/CD, I’d be honored if you gave gomarklint a try. Check it out on GitHub : shinagawa-web/gomarklint Give it a ⭐: If you find the project useful, a Star would mean the world to me and helps others discover the tool! I’m really curious to hear from you: What’s the most annoying thing you’ve encountered with Markdown formatting? Let’s chat in the comments below! Happy hacking! 🚀 Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Kazu Follow Joined Aug 9, 2025 More from Kazu Building a Culture of Documentation Quality in CI/CD # markdown # cicd # documentation # opensource Inside gomarklint: Architecture, Rule Engine, and How to Extend It # programming # go # markdown Inside gomarklint: Building a High-Performance Markdown Linter in Go # go # markdown # opensource 💎 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 | 2026-01-13T08:49:33 |
https://github.com/RDarrylR/step-functions-fargate-processor | GitHub - RDarrylR/step-functions-fargate-processor: An AWS serverless example using AWS Lambda, Step Functions, and ECS fargate to process datasets 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 }} RDarrylR / step-functions-fargate-processor Public Notifications You must be signed in to change notification settings Fork 0 Star 6 An AWS serverless example using AWS Lambda, Step Functions, and ECS fargate to process datasets 6 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 RDarrylR/step-functions-fargate-processor 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 Commits containers/ fargate_rust_worker containers/ fargate_rust_worker infra infra lambdas/ s3-upload-handler lambdas/ s3-upload-handler sample_data sample_data .gitignore .gitignore README.md README.md View all files Repository files navigation README step-functions-fargate-processor Purpose Example Serverless project using a Lambda function listening for new uploaded zip files of JSON data which are unzipped and trigger an AWS Step Function to run a distributed map over the json files with the processing done in ECS Fargate containers. Lambda function to handle S3 uploads and the fargate container code are written in Rust. Key Files containers - Source for Fargate worker container to process a single store json data lambdas - Source for Lambda function which reacts to uploaded zip file, unzips file, and triggers AWS Step Function to process sample_data - Example sales data zip files. Each zip file contains 1 day of sales with a json file inside each for the sales at each location infra - Terraform files to setup the VPC network for the demo as well as all the other infrastructure Requirements Terraform CLI ( https://developer.hashicorp.com/terraform/install ) Cargo Lambda ( https://www.cargo-lambda.info/guide/getting-started.html ) Docker Deploy the sample project To deploy the project, you need the following tools: In the infra/variables.tf file you need to update the following 2 variables: slack_webhook (This needs to be set to a real slack webhook URL where notifications will be sent - the URL in the repo is not valid) aws_profile (This needs to be set to the aws profile which you want to deploy all of the infrastructure with) 3 main things are being done here: We're compiling the s3_upload_handler using cargo lambda We're building a docker image of the fargate_rust_worker container, creating an ECR repository for it, and pushing the image to the repository We're using terraform to setup a VPC and tie everything together. Clone the repo cd lambdas/s3_upload_handler cargo lambda build --release cd ../containers/fargate_rust_worker ./create_ecr_and_push.sh cd ../infra terraform apply Once the terraform is applied it will output the newly created S3 bucket name to upload sales data zip files to. It will look like this: Outputs: bucket_to_upload_sales_zip_to = "stepfunctions-fargate-processor-fdsfdfdsffd" (NOTE - this is not an actual bucket name - yours will be different) To start the processing you need to upload one of the zip files of data from the sample_data directory to the uploads/ path in the S3 bucket cd sample_data aws s3 cp day01.zip s3:// < GENERATED_S3_BUCKET_NAME > /uploads/ This will trigger the lambda function which will trigger the step function which will trigger the Fargate processing tasks in ECS. You will see the progress and results in the slack channel your webhook pushes to. Cleanup To delete the sample project you will need to delete the S3 bucket manually in the AWS console as it will have files in it and it will make you delete the files before deleting the bucket. You will likely want to delet the ECR repository. You can do this in the AWS console. Then please use the following terraform command to destroy all the infrastructure. terraform destroy (from the infra directory) Read More This repository is associated with the following blog posted here About An AWS serverless example using AWS Lambda, Step Functions, and ECS fargate to process datasets Resources Readme Uh oh! There was an error while loading. Please reload this page . Activity Stars 6 stars Watchers 1 watching Forks 0 forks Report repository Releases No releases published Packages 0 No packages published Uh oh! There was an error while loading. Please reload this page . Languages Rust 44.1% HCL 40.1% Smarty 13.4% Shell 1.6% Dockerfile 0.8% 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. | 2026-01-13T08:49:33 |
https://docs.devcycle.com/platform/security-and-guardrails/feature-obfuscation/ | Feature Obfuscation | DevCycle Docs Skip to main content Home SDKs APIs Management API Bucketing API Integrations CLI / MCP Best Practices Community Blog Discord Search Sign Up Home Getting Started Essentials DevCycle Overview Key Features System Architecture Feature Hierarchy Feature Types Platform Feature Flags Experimentation Account Management Security and Guardrails Approval Workflows Audit Log Custom Property Schemas Feature Obfuscation Roles & Permissions SDK Visibility Variable Schemas Testing and QA Extras Examples Platform Security and Guardrails Feature Obfuscation On this page Feature Obfuscation Feature flags are often used to hide upcoming features before release. Normally, not showing the feature on a UI is enough to conceal it from users. However, in some cases it may be important to ensure that no trace of the feature can be found in the code that is shipped to users. This is particularly important on the web, where end-users can easily see all the source code for the page. Even when the code is obfuscated, any strings containing text from the new feature will still be present in the bundle. From that, intrepid users can often infer the nature of a feature they can't access, which may lead to sensitive or strategic information being leaked. To prevent this, DevCycle supports a feature allowing you to obfuscate all the Variable keys used in your code in Web platforms (React, Next.js, Javascript etc.) to keep their names private. Next.js users can also take advantage of our SDK's Conditional Deferred Rendering feature, which will strip out any source code for features the user isn't eligible for, reducing bundle size while also keeping the feature's details private. To use this feature, follow the setup guide below: Requirements This feature is only available for web platforms. It is not available for mobile or server-side SDKs. The following SDKs support obfuscation: Javascript React Next.js The unobfuscated data will still be available via the mobile and server SDK tokens. If you have a need for obfuscation on mobile, let us know in the community discord. Using the feature requires use of the DevCycle CLI . Follow the setup guide in the CLI documentation to install it and initialize in your repository. Setup In order to use obfuscation, the first step is to pass the enableObfuscation setting in your DevCycle SDK initialization options. This process will vary by SDK, but here is an example for React: import { withDevCycleProvider } from '@devcycle/react-client-sdk' function App ( ) { return < TheRestofYourApp /> } export default withDevCycleProvider ( { sdkKey : '<DEVCYCLE_CLIENT_SDK_KEY>' , // add this setting options : { enableObfuscation : true } } ) ( App , ) With obfuscation enabled, you can use the DevCycle CLI to generate a set of constants which correspond to your project's Variable keys. To do so, run the following command: dvc generate types --obfuscate If using React or Next.js, add the --react flag: dvc generate types --obfuscate --react The result will be a generated file containing type definitions and constants for all your project's Variables, with the keys obfuscated. The obfuscation process is done automatically using a key stored in your project's data, which is only known to the DevCycle Management API and the DevCycle CLI. An example of the generated file output you might expect is shown below.: // devcycleTypes.ts /* key: my-first-variable created by: Sally Smith created on: 2024-03-01 */ export const MY_FIRST_VARIABLE = 'dvc_obfs_3499747d616cfb0ac00bda26273e3577d5508f1ecaf2f1f07a2546' as ObfuscatedKey < 'my-first-variable' > /* key: my-second-variable created by: Joe Shmo created on: 2024-03-01 */ export const MY_SECOND_VARIABLE = 'dvc_obfs_359f6c73757fe30a9950ce39333c2329915a900893b3fbf164' as ObfuscatedKey < 'my-second-variable' > info The generated file also includes Typescript definitions of each Variable, which allows you to make your DevCycle usage type-safe by enforcing the correct datatype for each Variable. When using an enum schema , the types will also enforce that one of the allowed values is used. For more information, see the documentation for Typescript with the Javascript SDK The names of the constants will be automatically determined based on each Variable's key. If two Variable keys resolve to the same constant name, the CLI will append a number to the end of the constant name to avoid conflicts. The original Variable key will be preserved in the comment above the constant, so you can identify one constant from another. Now, in each place where a DevCycle Variable is evaluated, you can use the generated constants in place of direct strings. The constants have been automatically assigned to the obfuscated keys, so there will be no plain strings containing your Variable keys in code. For example: Before: import { useVariableValue } from '@devcycle/react-client-sdk' function MyComponent ( ) { const myFirstVariable = useVariableValue ( 'my-first-variable' , false ) const mySecondVariable = useVariableValue ( 'my-second-variable' , false ) return < div > { myFirstVariable } { mySecondVariable } </ div > } After: import { MY_FIRST_VARIABLE , MY_SECOND_VARIABLE , useVariableValue } from './devcycle' function MyComponent ( ) { const myFirstVariable = useVariableValue ( MY_FIRST_VARIABLE , false ) const mySecondVariable = useVariableValue ( MY_SECOND_VARIABLE , false ) return < div > { myFirstVariable } { mySecondVariable } </ div > } As long as your production build process is set up to uglify your production code, any trace of the original DevCycle Variable names will disappear. That's it! Requiring Obfuscation As an extra measure of safety, you can require obfuscation in your DevCycle project settings. This will prevent requests for SDK configuration using a client SDK key from obtaining unobfuscated keys, by requiring that the SDK is initialized with "enableObfuscation". It is recommended to require obfuscation when creating a new DevCycle project. If you are adding obfuscation to an existing project, you may want to leave this setting off until you have updated your code to use obfuscated keys, otherwise existing applications will no longer be able to receive a DevCycle configuration. Development Workflow and CI When using obfuscation, it is necessary to ensure that the generated constants are kept up to date with your project's set of possible Variable keys. There are different ways to accomplish this depending on your specific workflow, but in general we recommend committing the generated devcycleTypes file to source control and regenerating the file when a new Variable is added to DevCycle. To accomplish this more automatically, you can run the generator as part of a command which builds and runs your code in a local environment. This will ensure that each time you run the local code, the file is updated with the latest Variables. Archiving Variables When you archive a Variable in DevCycle, it will no longer appear in the generated output from the CLI. Make sure that Variables are no longer used in your code before archiving. Conditional Deferred Rendering Next.js users can take this a step further by also withholding any application source code that won't be used when a user is ineligible for a feature. This can improve page load performance while also hiding implementation details of features from users who shouldn't see them. To use this feature, follow the documentation for Conditional Deferred Rendering . When passing the Variable key to be evaluated, make sure to pass the obfuscated constant generated by the CLI. Edit this page Last updated on Jan 9, 2026 Previous Custom Property Schemas Next Roles & Permissions Requirements Setup Requiring Obfuscation Development Workflow and CI Archiving Variables Conditional Deferred Rendering DevCycle Dashboard Blog Privacy Policy Twitter Discord GitHub Copyright © 2026 DevCycle. All rights reserved. | 2026-01-13T08:49:33 |
https://opensource.org/board-member/catharina-maracke | Catharina Maracke – Open Source Initiative Skip to content Get involved About Licenses Open Source Definition Open Source AI Programs Blog Get involved About Licenses Open Source Definition Open Source AI Programs Blog Open Main Menu Catharina Maracke Catharina Maracke She/Her Director Board Member Candidacy Period: August 23, 2021 – October 3, 2025 Type of Seat: Individual Catharina is a lawyer by training and has been involved in intellectual property and public licensing models for over 15 years beginning with her work as director for Creative Commons International overseeing and stewarding the Creative Commons global licensing suite and managing the global license porting project. Catharina has worked closely with the World Economic Forum, where she served on the Global Agenda Council on the intellectual property system. She has founded the Software Compliance Academy, a private training and consulting firm to support clients in their Open Source journey and currently also helps lead MBition’s (Mercedes-Benz subsidiary based in Berlin) technology strategy focussing on system level architectural questions for the next generation of infotainment systems. In addition to her work with various clients, Catharina has helped to initiate the OpenChain project, the first international standard for Open Source license compliance (ISO/IEC 5230) to bring efficiency and trust into the Open Source supply chain. She has written and taught extensively on IT policy and standardization questions and especially the intersection between Open Source software and standards. Her academic appointments included faculty positions at Keio University in Japan and Bucerius Law School in Germany, visiting positions at the University of Puerto Rico and Humboldt University in Berlin, and as faculty associate at the Berkman Klein Center at Harvard University in the US. She is a member of the Council for the Legal Network at the Free Software Foundation Europe and a fellow at the Open Forum Europe. Catharina received her PhD from the Christian-Albrechts University in Kiel with a scholarship from the Max Plack Institute for Intellectual Property in Munich, Germany. Catharina has been elected to the OSI board in October 2021 and served as board chair since April 2022. Why Over the past two years, OSI has already achieved a great deal to increase visibility and improve operational stability – but we still have crucial challenges ahead of us: We have to keep on going with the Deep Dive AI project and make sure that the Open Source community has a voice in the heated debate about the future of technology. The license review process is currently “ under review ” itself and we also need to structure and refurbish the list of approved licenses. And above all, the political and economic situation makes life in the non-profit world difficult and challenging: OSI is a US based 503(c) charitable organization and relies on support from its members and unrestricted gifts from other generous donors, including industry sponsorships. We were lucky to get immediate support in the new membership structure and very proud to have built a strong support base with more than 600 members. Thanks to all of you who have supported OSI in its mission to advocate for the benefits of Open Source and to build bridges for a common understanding of Open Source. Looking back, I have somewhat disappointed myself and underestimated the work and time commitment associated with my original goals. Especially the fact that we haven’t been been able to make enough progress in expanding OSI’s visibility and activities beyond the US and EU borders made me realise that I should ask for more time. Geographical diversity is an important prerequisite for the future of OSI. We need all possible different perspectives represented at OSI and especially in the Open Source Community. If re-elected I will focus on geographical diversity and prioritize my network in the Asia Pacific region. Geographical diversity is an important prerequisite for the future of OSI. We need all possible different perspectives represented at OSI and especially in the Open Source community. Another important requirement for a sustainable future of the OSI and its community is engagement with the next generation of leaders, be it technical or non-technical. When I ran for the board in 2021, I promised to bring the core value of Open Source to the younger generations, to inspire them build an open future and support the idea and value behind the Open Source development model. And while engagement with the next generation naturally takes time, I realize that I could have spent more time working on this long-term goal. To sum up, I am running again for the OSI Board of Directors because I would be delighted to continue and support OSI in: Growing as an organization with a special focus on resources and sustainability: Even with a full time Executive Director on board, we need to secure a strong budget, continue and grow as an organization with a special focus on resources and sustainability. Continuing visibility in industry channels and policy fora: Legislators and policy makers need support in understanding the Open Source ecosystem, its role in innovation and its value for an open future. Counterbalancing industry networks and trade associations: While we have been working closely with some of the prominent trade associations, we need to spend more time and effort working with small community based organizations and civil society. Leading in Open Source stewardship through definition, licensing guidance, and respect: With our revised license review and license approval approach, we will add more transparency and inclusion to our main task and mission. Mediating fundamental issues and debates about the future of Open Source: With AI dominating the discussion around the future of software development, we need to give the Open Source community a very strong voice in this debate. What If re-elected, I will continue to work with the team and board and focus on visibility and operational stability. I will work with our existing network of industry leaders, foundational, and academic partners and supporters to expand OSI’s impact and visibility. Adding a strong, consistent, and well-informed voice to the ongoing debate around Open Source and how it can be defined and defended is still one of the most critical challenges we have to face even if (or perhaps because) Open Source has become so natural and widespread across the different industries. I will put a strong focus on our fundraising efforts. In addition to the much appreciated community and industry support, I would also like to reach out to foundations and apply for grants. Finally, I will devote more time and effort to bringing the Open Source software development model to the next generation of leaders. I still believe that we need to get questions on ethics and Open Source software development into the curriculum of our Universities around the world so that the next generation of engineers and decision makers can benefit even more from the groundwork that the OSI has accomplished over the past years. I can be reached at [email protected] and would be very happy to answer any questions you may have. Thank you for your time and reading up to this point in my re-application. I look forward to my second term on the OSI board and to your continuous support. Get involved Mastodon Twitter LinkedIn Reddit About About Our team Board of directors Sponsors Programs Blog Press mentions Trademark Bylaws Licenses Open Source Definition Licenses License Review Process Open Standards Requirement for Software Open Source AI Open Source AI OSAI Definition Process Timeline Open Weights FAQ Checklist Forum Community Become an Individual Member Become an OSI Affiliate Affiliate Organizations Maintainers Events Forum OpenSource.net The content on this website, of which Opensource.org is the author, is licensed under a Creative Commons Attribution 4.0 International License . Opensource.org is not the author of any of the licenses reproduced on this site. Questions about the copyright in a license should be directed to the license steward. Read our Privacy Policy Proudly powered by WordPress. Hosted by Pressable. Manage Cookie Consent To provide the best experiences, we use technologies like cookies to store and/or access device information. Consenting to these technologies will allow us to process data such as browsing behavior or unique IDs on this site. Not consenting or withdrawing consent, may adversely affect certain features and functions. Functional Functional Always active The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network. Preferences Preferences The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user. Statistics Statistics The technical storage or access that is used exclusively for statistical purposes. The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you. Marketing Marketing The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes. Manage options Manage services Manage {vendor_count} vendors Read more about these purposes Accept Deny View preferences Save preferences View preferences {title} {title} {title} Manage consent | 2026-01-13T08:49:33 |
https://kubernetes.io/ | Kubernetes Kubernetes Documentation Kubernetes Blog Training Careers Partners Community Versions Release Information v1.35 v1.34 v1.33 v1.32 v1.31 English বাংলা (Bengali) 中文 (Chinese) Français (French) Deutsch (German) हिन्दी (Hindi) Bahasa Indonesia (Indonesian) Italiano (Italian) 日本語 (Japanese) 한국어 (Korean) Polski (Polish) Português (Portuguese) Русский (Russian) Español (Spanish) Українська (Ukrainian) Tiếng Việt (Vietnamese) Production-Grade Container Orchestration Learn Kubernetes Basics Kubernetes , also known as K8s, is an open source system for automating deployment, scaling, and management of containerized applications. It groups containers that make up an application into logical units for easy management and discovery. Kubernetes builds upon 15 years of experience of running production workloads at Google , combined with best-of-breed ideas and practices from the community. Planet scale Designed on the same principles that allow Google to run billions of containers a week, Kubernetes can scale without increasing your operations team. Never outgrow Whether testing locally or running a global enterprise, Kubernetes flexibility grows with you to deliver your applications consistently and easily no matter how complex your need is. Run K8s anywhere Kubernetes is open source giving you the freedom to take advantage of on-premises, hybrid, or public cloud infrastructure, letting you effortlessly move workloads to where it matters to you. To download Kubernetes, visit the download section. The Absolute Beginner's Guide To Cloud Native by Kyle Penfound, Dagger & Cortney Nickerson, Kubeshop Watch Video Attend upcoming KubeCon + CloudNativeCon events Europe (Amsterdam, Mar 23-26, 2026) North America (Salt Lake City, Nov 9-12, 2026) Kubernetes Features Automated rollouts and rollbacks Kubernetes progressively rolls out changes to your application or its configuration, while monitoring application health to ensure it doesn't kill all your instances at the same time. If something goes wrong, Kubernetes will rollback the change for you. Take advantage of a growing ecosystem of deployment solutions. Service discovery and load balancing No need to modify your application to use an unfamiliar service discovery mechanism. Kubernetes gives Pods their own IP addresses and a single DNS name for a set of Pods, and can load-balance across them. Storage orchestration Automatically mount the storage system of your choice, whether from local storage, a public cloud provider, or a network storage system such as iSCSI or NFS. Secret and configuration management Deploy and update Secrets and application configuration without rebuilding your image and without exposing Secrets in your stack configuration. Automatic bin packing Automatically places containers based on their resource requirements and other constraints, while not sacrificing availability. Mix critical and best-effort workloads in order to drive up utilization and save even more resources. Batch execution In addition to services, Kubernetes can manage your batch and CI workloads, replacing containers that fail, if desired. Self-healing Kubernetes restarts containers that crash, replaces entire Pods where needed, reattaches storage in response to wider failures, and can integrate with node autoscalers to self-heal even at the node level. Horizontal scaling Scale your application up and down with a simple command, with a UI, or automatically based on CPU usage. Vertical scaling Automatically adjust resource requests and limits based on actual usage patterns. IPv4/IPv6 dual-stack Allocation of IPv4 and IPv6 addresses to Pods and Services Designed for extensibility Add features to your Kubernetes cluster without changing upstream source code. Case Studies "Kubernetes is a great platform for machine learning because it comes with all the scheduling and …" Read more "Kubernetes is a great solution for us. It allows us to rapidly iterate on our clients' demands. " Read more "We realized that we needed to learn Kubernetes better in order to fully use the potential of it. At …" Read more "We made the right decisions at the right time. Kubernetes and the cloud native technologies are now …" Read more We are a CNCF graduated project © 2026 The Kubernetes Authors | Documentation Distributed under CC BY 4.0 © 2026 The Linux Foundation ®. All rights reserved. The Linux Foundation has registered trademarks and uses trademarks. For a list of trademarks of The Linux Foundation, please see our Trademark Usage page ICP license: 京ICP备17074266号-3 | 2026-01-13T08:49:33 |
https://dev.to/realnamehidden1_61/how-do-you-handle-exceptions-globally-in-spring-boot-33md | How Do You Handle Exceptions Globally in Spring Boot? - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse realNameHidden Posted on Dec 21, 2025 How Do You Handle Exceptions Globally in Spring Boot? # java # spring # springboot # interview Learn how to implement global exception handling in Spring Boot to build clean, consistent REST API error responses with practical Java examples. Introduction Imagine you’re calling a REST API from a frontend application. Instead of a clear error message like “User not found” , you suddenly receive a long stack trace or a generic 500 Internal Server Error . As a user, this is confusing. As a developer, it’s frustrating. This is where global exception handling in Spring Boot becomes essential. When developers start learning Java programming and Spring Boot, they often use try-catch blocks inside every controller. While this works initially, it quickly leads to messy code, duplicated logic, and inconsistent error responses. Spring Boot offers a clean, centralized way to handle all exceptions in one place. This approach improves code readability, API consistency, and overall application quality. In this blog, you’ll learn how global exception handling works in Spring Boot, why it’s important, and how to implement it using beginner-friendly Java 21 examples. Core Concepts What Is Exception Handling? An exception is an unexpected event that disrupts the normal flow of a program. Examples include: Invalid input from a client Requested resource not found Database connection failures Unauthorized access If exceptions are not handled properly, they can crash the application or expose sensitive internal details. What Is Global Exception Handling in Spring Boot? Global exception handling means managing all application errors from a single, centralized component instead of handling them individually in every controller. 👉 Analogy: Central Help Desk In a company, employees don’t solve every issue themselves—they report it to a central help desk that responds in a standard way. Global exception handling works the same way for your APIs. Spring Boot supports this using: @ExceptionHandler @ControllerAdvice or @RestControllerAdvice Why Use Global Exception Handling? Benefits: Cleaner and simpler controller code Consistent error responses across APIs Easier maintenance and scalability Improved security (no stack traces exposed) Better client experience This is why global exception handling in Spring Boot is considered a best practice for REST APIs. Code Examples (Java 21) Example 1: Global Handling of a Custom Exception Step 1: Create a Custom Exception public class ResourceNotFoundException extends RuntimeException { public ResourceNotFoundException(String message) { super(message); } } Enter fullscreen mode Exit fullscreen mode Step 2: Throw the Exception from a Controller @RestController @RequestMapping("/users") public class UserController { @GetMapping("/{id}") public String getUser(@PathVariable Long id) { if (id != 1) { throw new ResourceNotFoundException("User not found with id: " + id); } return "User found"; } } Enter fullscreen mode Exit fullscreen mode 📌 No try-catch blocks cluttering the controller. Step 3: Create a Global Exception Handler @RestControllerAdvice public class GlobalExceptionHandler { @ExceptionHandler(ResourceNotFoundException.class) public ResponseEntity<String> handleResourceNotFound(ResourceNotFoundException ex) { return ResponseEntity .status(HttpStatus.NOT_FOUND) .body(ex.getMessage()); } } Enter fullscreen mode Exit fullscreen mode ✅ Result: Centralized handling Clean controller code Proper HTTP status codes Example 2: Structured Error Response for Multiple Exceptions Create a Common Error Response Model import java.time.LocalDateTime; public record ErrorResponse( int status, String message, LocalDateTime timestamp ) {} Enter fullscreen mode Exit fullscreen mode Handle Multiple Exceptions Globally @RestControllerAdvice public class GlobalExceptionHandler { @ExceptionHandler({ IllegalArgumentException.class, MethodArgumentTypeMismatchException.class }) public ResponseEntity<ErrorResponse> handleBadRequest(Exception ex) { ErrorResponse errorResponse = new ErrorResponse( HttpStatus.BAD_REQUEST.value(), ex.getMessage(), LocalDateTime.now() ); return ResponseEntity .status(HttpStatus.BAD_REQUEST) .body(errorResponse); } } Enter fullscreen mode Exit fullscreen mode 📌 This ensures all error responses follow the same structure—ideal for frontend and API consumers. Best Practices Use @RestControllerAdvice for REST APIs It automatically returns JSON responses. Create custom exceptions for business errors Avoid throwing generic RuntimeException . Return meaningful HTTP status codes Use 400, 404, 401, and 500 appropriately. Do not expose stack traces to clients Log errors internally, return clean messages. Standardize error responses A common error format improves API usability. Common Mistakes to Avoid ❌ Handling exceptions inside every controller ❌ Returning 200 OK for error cases ❌ Exposing internal exception details ❌ Mixing business logic with error handling Conclusion Global exception handling in Spring Boot is a fundamental skill for building professional, production-ready applications. By centralizing error handling using @RestControllerAdvice , you keep your controllers clean, your APIs consistent, and your users informed. Instead of reacting to errors in multiple places, you define a single strategy that scales as your application grows. This approach is widely expected in real-world Spring Boot projects and technical interviews. If you’re learning Spring Boot or improving your REST API design, mastering global exception handling is a big step toward writing high-quality Java applications. Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse realNameHidden Follow Actively Looking For Work Youtube Channel Link : https://www.youtube.com/@realNameHiddenn Blog : https://idiotprogrammern.blogspot.com/ Location India Work Looking For Work email : realnamehiddenyt@gmail.com Joined Oct 23, 2021 More from realNameHidden How Virtual Threads Change the Way We Write Concurrent Java Code # java # thread # virtualthreads # multithreading How Does @Async Work Internally in Spring Boot? # java # interview # spring # springboot You Want Correlation IDs for Logging Across All Proxies — Here’s How to Do It in Apigee X # apigee # apigeex # gcp # interview 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/naveen_v_5562871ba6455b7e/rethinking-expense-splitting-a-graph-based-approach-with-llm-integration-mbo | Rethinking Expense Splitting: A Graph-Based Approach with LLM Integration - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Naveen Vandanapu Posted on Dec 26, 2025 Rethinking Expense Splitting: A Graph-Based Approach with LLM Integration # ai # mcp # llm # go The Problem with Traditional Expense Splitters If you've ever used group expense splitting tools, you know the drill: great concept, but many implementations leave something to be desired. A common pain point is when timelines mix expenses from different groups, making it difficult to focus on a specific trip or event. Want to quickly review just your weekend getaway expenses? You might find yourself scrolling through unrelated bills and dinner splits from other groups. This counter-intuitive design pattern got me thinking: there has to be a better way. A Graph-Based Mental Model The breakthrough came when I realized expense splitting is fundamentally a graph problem . Here's the elegant simplicity: Nodes represent people in your group Directed edges represent money owed (A → B means A owes B) Edge weights are the amounts When you add an expense, you're essentially creating edges in this graph. If Alice pays $120 for lunch shared equally among three people, she's owed $40 by Bob and $40 by Charlie. That's two edges: Bob → Alice ($40) and Charlie → Alice ($40). This mental model is intuitive because it mirrors how we naturally think about debts: "I owe Alice $40" is a directed relationship with a value attached. Building expense-splitter Armed with this insight, I built expense-splitter as a graph-based tool. Key design decisions: Group isolation: Each group is its own separate graph. Your Napa trip expenses never mix with your apartment utilities. Flexible splitting: Support for equal splits, weighted splits, and percentage-based splits—all translating cleanly to edge calculations. Clean settlements: The graph makes it trivial to calculate who owes whom. No more confusing chains of "Alice pays Bob who pays Charlie"—just direct settlements. The MCP Integration: Where It Gets Interesting Here's where modern AI tooling transforms the experience. I packaged expense-splitter as an MCP (Model Context Protocol) tool and built an agent using Google's Agent Development Kit (ADK) in Go. The result? A conversational interface that's actually intuitive: User: let's do expense splitting Agent: I can help with that! First, let's create a group. What would you like to name it? User: create a group called napa-trip Agent: Great! I've created a group called 'napa-trip'. Now, who are the members of this group? User: add alice, bob, charlie to the group Agent: I've added Alice, Bob, and Charlie to the napa-trip group. Now, let's add some expenses... Enter fullscreen mode Exit fullscreen mode No clicking through forms. No dropdown menus. Just natural conversation. Adding Expenses Naturally The real magic shows when adding expenses: User: add an expense by alice for lunch. 120$ Agent: I've added a $120 expense for lunch, paid by Alice. What's the next expense? User: it's for snacks and drinks by charlie. 60$ Agent: Got it. $60 for snacks and drinks, paid by Charlie, has been added. Enter fullscreen mode Exit fullscreen mode Even complex splits feel natural: User: add an expense by bob for show tickets with unequal weights Agent: Okay, Bob paid for show tickets with unequal weights. What was the total amount? And how would you like to split the weights among Alice, Bob, and Charlie? User: 100 Agent: And what are the unequal weights for Alice, Bob, and Charlie? User: alice: 1, bob:2, charlie:1 Agent: I've added the $100 expense for show tickets, paid by Bob, with the following weights: Alice 1, Bob 2, Charlie 1. Enter fullscreen mode Exit fullscreen mode Bob paid $100 but his share (weight 2 out of 4 total) was $50, so he's actually only owed $50. The Payoff: Clear Settlements When you're ready to settle up: User: get group details now Agent: Here are the details for the 'napa-trip' group: **Members:** Alice, Bob, Charlie **Settlement Details:** - Bob needs to pay Alice $15 - Charlie needs to pay Alice $20 - Charlie needs to pay Bob $5 Enter fullscreen mode Exit fullscreen mode Visualizing the Graph: DOT Notation One of the advantages of modeling expenses as a graph is that you can actually see the structure. The tool exports the graph in DOT notation, which can be visualized using Graphviz: digraph "napa-trip" { "alice" [ label = "alice" ] ; "bob" [ label = "bob" ] ; "charlie" [ label = "charlie" ] ; "alice" -> "bob" [ label = "$25.00" ] ; "alice" -> "charlie" [ label = "$20.00" ] ; "bob" -> "alice" [ label = "$40.00" ] ; "bob" -> "charlie" [ label = "$20.00" ] ; "charlie" -> "alice" [ label = "$40.00" ] ; "charlie" -> "bob" [ label = "$25.00" ] ; } Enter fullscreen mode Exit fullscreen mode This represents the complete debt graph showing every individual obligation. Notice that this is the raw graph showing all pairwise debts from each expense. The settlement algorithm then simplifies this: Alice owes Bob $25 but Bob owes Alice $40 → Net: Bob owes Alice $15 Charlie owes Alice $40 but Alice owes Charlie $20 → Net: Charlie owes Alice $20 Charlie owes Bob $25 but Bob owes Charlie $20 → Net: Charlie owes Bob $5 The beauty of the graph representation is its transparency. You can: Visualize it : Paste into any Graphviz tool to see the network of obligations Debug it : See exactly how each expense contributed to the final settlements Audit it : Verify the math by tracing through the edges Understand it : The visual representation makes the settlement logic obvious This level of transparency is rare in expense splitting tools. Most are black boxes where you input expenses and get settlements without seeing the underlying logic. By exposing the graph, users who want to understand why they owe a certain amount can trace it back through the structure. Clean, minimal, and derived directly from the graph structure. No intermediate transfers, no confusion. Why This Matters The combination of a sound data model (graphs) and an intuitive interface (conversational AI) creates something genuinely better than existing solutions: Cognitive alignment: The graph model matches how we think about debts Context preservation: Groups stay separate, making it easy to review specific events Conversational ease: No UI to learn, just describe what you want Extensibility: MCP tools can be integrated with various AI platforms (Claude Code, custom agents, etc.) Technical Architecture For those interested, the stack is: Core logic : Graph-based settlement calculation implemented in Go MCP layer : Exposed as Model Context Protocol tool implemented in Go Agent : Built with Google's Agent Development Kit - ADK in Go Interface : Natural language via LLM The MCP abstraction means the same tool can be used from CLI tools like Claude Code, web interfaces, or custom agents—wherever you can connect an LLM. Open Source I’ve open-sourced the implementation at https://github.com/vnaveen-mh/expense-splitter If you’re experimenting with MCP, agent elicitation, or graph-based modeling, feel free to fork it and build on top of it. Conclusion Sometimes the best solutions come from stepping back and asking: "What's the fundamental structure of this problem?" For expense splitting, it was recognizing the graph nature of debts and obligations. Combined with modern AI tooling, we can finally build interfaces that feel as natural as asking a friend, "Hey, what do I owe you?" The code is a testament to how good abstractions—both in data modeling and tool interfaces—can transform user experience from frustrating to delightful. Have you experienced similar frustrations with existing tools? I'd love to hear about problems you've solved by rethinking the fundamental data model. Top comments (1) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Collapse Expand codecraft codecraft codecraft Follow Joined Dec 5, 2025 • Dec 26 '25 Dropdown menu Copy link Hide Insightful Like comment: Like comment: 1 like Like Comment button Reply Some comments may only be visible to logged-in visitors. Sign in to view all comments. Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Naveen Vandanapu Follow Joined Nov 28, 2025 More from Naveen Vandanapu LLMs + Tool Calls: Clever But Cursed # llm # ai # go # safety Building an AI-Powered App Entirely in Go: From Simple Prompt to Smart Pipeline # ai # go # genkit # programming 💎 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 | 2026-01-13T08:49:33 |
https://www.fine.dev/blog/common-python-errors#pricing | Most Common Python Errors When Using AI Home Docs Changelog Pricing Sign in Get started -> Menu Home Docs Changelog Pricing <- Go Back Most Common Python Errors When Using AI Introduction Python is a favorite among backend developers, particularly in the fast-paced world of startups where flexibility and speed are key. But let’s be honest—Python’s simplicity can sometimes be deceiving, and even the most seasoned developers can find ourselves pulling our hair out trying to understand why the code doesn’t work. In this article, we’ll dive into the top 10 Python errors that backend developers frequently encounter, especially in smaller startup teams. We’ll explain why these errors happen and provide tips on how to avoid them. We’ll also look at whether the common AI tools are likely to make the errors or can help you spot and fix them. Table of Contents Introduction Error 1: TypeErrors Error 2: NameErrors Error 3: IndexErrors Error 4: KeyErrors Error 5: ImportErrors A Recurring Theme in the Python Errors AI Makes How Fine Can Help You Avoid These Errors Conclusion Error 1: TypeErrors TypeErrors occur when you try to perform an operation on incompatible data types, like trying to add a string to an integer. It’s the programming equivalent of mixing oil and water—not going to happen. Python is dynamically typed, meaning variables don’t have fixed types, but this flexibility can sometimes lead to unexpected type mismatches. How to Avoid: Always check the data types you’re working with, and consider using type hints in your function definitions to ensure compatibility. AI models might try to perform operations on incompatible types or fail to include necessary type conversions. Fine will test to make sure there are no TypeErrors and fix any that occur. Fine’s PR review feature also identifies TypeErrors in GitHub PRs that human developers have written, ensuring that they don’t make it into production. Error 2: NameErrors (Shock horror, they’re back) No serious Python developer goes around making NameErrors anymore, right? Well, here’s the thing. ChatGPT and other AI coding tools make NameErrors all the time. They can’t help it. They don’t know what you’ve named things in your code, so they have to make a logical guess or use a placeholder - which will usually be wrong. Even the best models, such as o1 and Claude Sonnet 3.5, are helpless here. In fact, many people accuse AI of “hallucinating”, when really they’re referring to a simple NameError, where the AI isn’t to blame. Whilst simple to fix (in theory), this is quite a pain and every developer should have their eyes open for NameErrors (and indentation issues also - remember those?) when using AI coding tools that don’t have full context awareness. Fine is the AI coding tool to choose to avoid these errors. Because it indexes your repositories and issues, the AI can identify the correct names in your codebase and save you hours of debugging. Error 3: IndexErrors IndexErrors arise when you try to access an index that doesn’t exist in a list. Imagine trying to grab the fifth apple from a basket that only has four—you’re bound to run into trouble. This often happens due to off-by-one errors, where the index is either too high or too low. If you’re not familiar with how python’s range works or how slicing works, it’s a good idea to sharpen up on it to avoid index errors. How to Avoid: Double-check your list boundaries and validate your input data. Fine can highlight potential IndexErrors, helping you avoid those pesky off-by-one mistakes. This is particularly useful in scenarios where your code dynamically generates or manipulates lists, which can lead to unpredictable indexing issues. Error 4: KeyErrors KeyErrors happen when you try to access a dictionary key that isn’t present. It’s like asking for the keys to a car that you don’t own—not going to get far! How to Avoid: Use the .get() method or check for key existence before access. Fine can help by suggesting safe dictionary access patterns, reducing the risk of a KeyError. Error 5: ImportErrors ImportErrors happen when a module isn’t imported correctly, either because it’s missing, you’ve made a typo in the import path, or you’ve created a circular import. These errors are common when managing dependencies across different environments. Imagine - File A tries to import File B, which tries to import File A. How to Avoid: Ensure your modules are properly installed and avoid overly complex import chains. Fine’s AI can track your imports and warn you about potential issues, making it easier to manage your dependencies. A Recurring Theme in the Python Errors AI Makes NameErrors, ImportErrors, AttributeErrors, KeyErrors - AI will keep making these mistakes as long as it doesn’t have the full context of your codebase. It’s like if I were to ask you to write code for my platform, but without showing you my existing repo. How would you know what to refer to? How Fine Can Help You Avoid These Errors Fine is designed to be your coding companion, catching these common Python errors before they can trip you up. Using advanced AI algorithms, Fine provides real-time feedback, highlights potential issues, and offers tailored suggestions to keep your code clean and error-free. Whether you’re dealing with indentation issues, NameErrors, or TypeErrors, Fine acts as your second pair of eyes, ensuring that your development process remains smooth and efficient. With Fine integrated into your workflow, you can focus on what really matters—building great software. Conclusion Python errors can be a major headache, especially in a startup environment where every line of code counts. By understanding these common errors and how to avoid them, you can write cleaner, more reliable code. And with Fine by your side, you’ll catch and fix these errors effortlessly, keeping your projects on track and your sanity intact. Be careful of code generators that aren’t aware of your existing codebase, such as ChatGPT and GitHub Copilot—they’re more likely to make simple Python mistakes. Ready to take your Python development to the next level? Try Fine today with our free trial and see how our AI-powered coding assistant can help you write error-free code faster. Sign up now, or schedule a demo to discover how Fine can integrate seamlessly into your workflow and boost your team's productivity. Don’t let simple errors slow you down—let Fine handle the details so you can focus on building great software. Start building today Try out the smoothest way to build, launch and manage an app Try for Free -> © Fine.dev - All rights reserved. Product Overview AI Workflows Pricing & Plans Changelog Blog Docs Company Press Terms & Conditions Privacy policy | 2026-01-13T08:49:33 |
https://dev.to/t/computerscience/page/2 | Computer Science 🤓 Page 2 - 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 Computer Science 🤓 Follow Hide This tag is for sharing and asking questions about anything related to computer science, including data structures, algorithms, research, and white papers! 🤓 Create Post submission guidelines Please ensure that any post that is tagged with #computerscience is related to computer science in some way. Promotional posts will be untagged, as will posts unrelated to CS. Please also be sure that your content adheres to the DEV Code of Conduct and that your comments are constructive and kind. about #computerscience Did you learn about a new data structure recently? Or perhaps you tried to implement an algorithm in a new language? Or maybe you need help understanding a white paper? The #computerscience tag is a great place for any of these questions and ideas. Please be sure to cross-tag any content that might help other folks in the DEV community. For example, an introduction to linked lists should also be tagged with the #beginners tag. Similarly, a post that asks for a simple explanation to the traveling salesman problem should be tagged with the #explainlikeimfive tag. Older #computerscience posts 1 2 3 4 5 6 7 8 9 Posts Left menu 👋 Sign in for the ability to sort posts by relevant , latest , or top . Right menu Running Form Tech: Improve Your Gait With This DIY AI Analysis wellallyTech wellallyTech wellallyTech Follow Jan 5 Running Form Tech: Improve Your Gait With This DIY AI Analysis # opencv # python # computerscience # healthtech Comments Add Comment 2 min read mHC [Paper Cuts] Leo Lau Leo Lau Leo Lau Follow Jan 6 mHC [Paper Cuts] # architecture # computerscience # deeplearning # machinelearning Comments Add Comment 3 min read Rust 2.0: A Thought Experiment on Safe Specialization Simmypeet Simmypeet Simmypeet Follow Jan 10 Rust 2.0: A Thought Experiment on Safe Specialization # rust # theory # computerscience # programming Comments Add Comment 13 min read Coding Challenge Practice - Question 95 Bukunmi Odugbesan Bukunmi Odugbesan Bukunmi Odugbesan Follow Jan 5 Coding Challenge Practice - Question 95 # algorithms # computerscience # javascript # tutorial Comments Add Comment 2 min read From Zero to Programming Language: A Complete Implementation Guide Uthman Oladele Uthman Oladele Uthman Oladele Follow Jan 4 From Zero to Programming Language: A Complete Implementation Guide # programming # go # computerscience Comments Add Comment 4 min read Tree Traversals Explained: DFS, BFS, and When to Use Each Mohammed Shaikh Mohammed Shaikh Mohammed Shaikh Follow Jan 4 Tree Traversals Explained: DFS, BFS, and When to Use Each # algorithms # computerscience # tutorial Comments Add Comment 3 min read From Reset to Control: Disabling Interrupts on ARM Bare Metal Ripan Deuri Ripan Deuri Ripan Deuri Follow Jan 2 From Reset to Control: Disabling Interrupts on ARM Bare Metal # architecture # computerscience # tutorial Comments Add Comment 3 min read 🧠 Understanding the JavaScript Event Loop — The Backbone of Asynchronous JavaScript Priya Khanna Priya Khanna Priya Khanna Follow Jan 2 🧠 Understanding the JavaScript Event Loop — The Backbone of Asynchronous JavaScript # beginners # computerscience # javascript Comments Add Comment 1 min read An Epidemic of Learned Helplessness Michael Parker Michael Parker Michael Parker Follow Jan 1 An Epidemic of Learned Helplessness # discuss # programming # computerscience # ai 1 reaction Comments Add Comment 4 min read Web Design Trends for 2026: What Developers Actually Need to Care About webmixstudio webmixstudio webmixstudio Follow Jan 1 Web Design Trends for 2026: What Developers Actually Need to Care About # computerscience # frontend # startup # coding Comments Add Comment 2 min read Why Edge AI Research Needs Field Validation: Lessons from Replicating MIT CSAIL shambhavi525-sudo shambhavi525-sudo shambhavi525-sudo Follow Jan 4 Why Edge AI Research Needs Field Validation: Lessons from Replicating MIT CSAIL # ai # computerscience # deeplearning # performance 5 reactions Comments 1 comment 2 min read The Immortal Coffee Bean: Why Java is the Unkillable King of Enterprise Muhammad Ishaque Muhammad Ishaque Muhammad Ishaque Follow Dec 31 '25 The Immortal Coffee Bean: Why Java is the Unkillable King of Enterprise # programming # java # computerscience # softwaredevelopment Comments Add Comment 5 min read Consistent Hashing - System Design Kader Khan Kader Khan Kader Khan Follow Dec 31 '25 Consistent Hashing - System Design # systemdesign # algorithms # architecture # computerscience Comments Add Comment 4 min read Guia Definitivo para estudantes de Ciencias da Computação Paulo Handerson lopes dos santos junior Paulo Handerson lopes dos santos junior Paulo Handerson lopes dos santos junior Follow Dec 31 '25 Guia Definitivo para estudantes de Ciencias da Computação # programming # computerscience # learning # ai Comments Add Comment 9 min read This Tiny Chip Could Turn Quantum From Lab Toy To Scalable Product Max aka Mosheh Max aka Mosheh Max aka Mosheh Follow Dec 31 '25 This Tiny Chip Could Turn Quantum From Lab Toy To Scalable Product # news # computerscience # product # science Comments Add Comment 1 min read Memory Leak in C++ Sujeet Pandey Sujeet Pandey Sujeet Pandey Follow Dec 31 '25 Memory Leak in C++ # memoryleak # cpp # computerscience # coding Comments Add Comment 2 min read Functions and Modules in Python: Writing Clean, Reusable Code the Right Way Nomidl Official Nomidl Official Nomidl Official Follow Jan 1 Functions and Modules in Python: Writing Clean, Reusable Code the Right Way # webdev # ai # python # computerscience Comments Add Comment 4 min read HTDP Study Blog zeh zeh zeh Follow Dec 31 '25 HTDP Study Blog # computerscience # learning # racket 3 reactions Comments Add Comment 3 min read MIPS architecture: simple, clean, and quietly everywhere (once) Pʀᴀɴᴀᴠ Pʀᴀɴᴀᴠ Pʀᴀɴᴀᴠ Follow Dec 30 '25 MIPS architecture: simple, clean, and quietly everywhere (once) # architecture # computerscience # learning 1 reaction Comments Add Comment 3 min read 🎉 Happy New Year, Neva Community! 🎉 Emil Valeev Emil Valeev Emil Valeev Follow Dec 31 '25 🎉 Happy New Year, Neva Community! 🎉 # programming # opensource # go # computerscience Comments Add Comment 3 min read Intel Itanium: the CPU architecture that tried to replace x86 (and didn’t) Pʀᴀɴᴀᴠ Pʀᴀɴᴀᴠ Pʀᴀɴᴀᴠ Follow Dec 30 '25 Intel Itanium: the CPU architecture that tried to replace x86 (and didn’t) # discuss # architecture # computerscience 1 reaction Comments Add Comment 3 min read Oberon OS: A system built by people who hated unnecessary things Pʀᴀɴᴀᴠ Pʀᴀɴᴀᴠ Pʀᴀɴᴀᴠ Follow Dec 30 '25 Oberon OS: A system built by people who hated unnecessary things # discuss # architecture # computerscience 1 reaction Comments Add Comment 2 min read The Call Stack: What Really Happens When a Function Is Called sheshikiran gone sheshikiran gone sheshikiran gone Follow Dec 30 '25 The Call Stack: What Really Happens When a Function Is Called # programming # webdev # java # computerscience 1 reaction Comments Add Comment 3 min read SerenityOS: A Modern Operating System Built to Be Understood Pʀᴀɴᴀᴠ Pʀᴀɴᴀᴠ Pʀᴀɴᴀᴠ Follow Dec 30 '25 SerenityOS: A Modern Operating System Built to Be Understood # computerscience # learning # opensource # architecture 2 reactions Comments Add Comment 2 min read Learning Programming as Paying Debt, Not Investment Alam Asy'arie Alam Asy'arie Alam Asy'arie Follow Dec 31 '25 Learning Programming as Paying Debt, Not Investment # programming # computerscience Comments Add Comment 4 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 | 2026-01-13T08:49:33 |
https://opensource.org/about/team#content | Our team – Open Source Initiative Skip to content Get involved About Licenses Open Source Definition Open Source AI Programs Blog Get involved About Licenses Open Source Definition Open Source AI Programs Blog Open Main Menu Home About Our team Our team The Open Source Initiative (OSI) exists and succeeds because of the commitments and contributions of our community. We would like to thank all of those who have stepped forward to support our work in promoting and protecting open source software, development and communities. Staff Deb Bryant, Interim Executive Director Deb’s deep appreciation of open source models and culture comes out two decades of management in Open Source organizations – leading enterprise IT policy in state government as an early adopter of open standards and open source; helping build one of the world’s pioneering Open Source labs at Oregon State University; conducting and publishing research and consulting to international government as a trusted advisor on adoption of open source. Prior to joining OSI staff she led one of the world’s largest and most influential Open Source Program Offices (OSPO) at Red Hat for eight years. She is OSI Board Member Emeritus having previously served on the OSI board for four terms over ten years. In 2023, she established OSI’s first US Policy Program and founded the Open Policy Alliance . Simon Phipps, Standards & EU Policy Director Simon first joined OSI in 2008 as a Board observer and has been a board director, board president, and board secretary at various times since, until early 2020 when he switched to his current role. With a degree in electronic engineering that led to a focus first on compiler design and then workstations and networking, he has had C-level roles with responsibility for software community matters at IBM, Sun Microsystems and Forgerock. As Sun’s chief open source officer he ran one of the first fully staffed OSPOs and oversaw the release of Sun’s whole software portfolio under open source licenses, notably including the Java platform. He has been involved in de jure standards since 1991 at multiple SDOs. He consults, writes and speaks widely on software freedom issues. Phyllis Dobbs, Controller Phyllis joined OSI as part-time Controller in 2017 and is currently part-time Controller for Python Software Foundation, as well as a part-time accounting/finance consultant for the Lake Forest Symphony, the Lake County Chamber of Commerce, and the Alliance for Human Services. Previously, Phyllis was CFO of Shimer College and Controller for McGraw-Hill Higher Education. She has an MBA from Duke University and a B.S. in Accounting from Clemson University. In addition, Phyllis is Trustee at Cook Memorial Public Library, President of a condo association, volunteers annually with the IRS/AARP tax program, and is a clarinetist in the Libertyville Village Band. Nick Vidal, Community Manager Nick is Community Manager at the Open Source Initiative. Previously, he was Outreach Chair at the Confidential Computing Consortium from the Linux Foundation, Director of Community and Business Development at the Open Source Initiative, and Director of Americas at the Open Invention Network. Jordan Maris, EU Policy Analyst Jordan fought for Open Source as a parliamentary assistant in the European Parliament working on the AI Act, Cyber Resilience Act and Product Liability Directive among others. Jordan is a long-time user of Open Source software and a strong advocate for the Public Money–Public Code principle. Katie Steen-James, Senior US Policy Manager Katie joined OSI after leading policy and advocacy for SPARC, a nonprofit coalition working to implement open access and open education policies in North America. Before SPARC, she was a federal relations officer at the Association of American Universities where she advocated for federal research investments and developed programming and positions on open research data issues. Katie brings 10 years of experience in government relations and policy analysis and a commitment to educating policymakers about the benefits of open. Gabriel Toscano, US Policy Intern Gabriel is a Master of Public Policy (MPP) student at Duke University working on sociotechnical approaches to build, govern, and promote digital technologies in the public interest. With a background in philosophy and computer science, he has published and conducted research at Duke’s Sanford School of Public Policy, the Center for AI and Digital Policy, the MIT Science Policy Review, and the Stanford Trust & Safety Research conference. You, work with us! We’re a small team and we often look for help from the community. Sign up for our newsletter and receive early notices of new job openings, and requests for volunteers. OSI non-discrimination policy : The Open Source Initiative does not promote or discriminate against any person, population group, or organization with regard to categories protected by applicable United States law, as well as other categories identified by the OSI in alignment with our own Human Resources policies. These include, but are not limited to race, color, ancestry, religion, sex, sexual orientation, gender expression, physical appearance, citizenship, marital status, language, education background, national origin, age, disability, and veteran status. We also consider qualified applicants regardless of criminal histories, consistent with legal requirements. If you have a disability or special need that requires accommodation, please let us know. Get involved Mastodon Twitter LinkedIn Reddit About About Our team Board of directors Sponsors Programs Blog Press mentions Trademark Bylaws Licenses Open Source Definition Licenses License Review Process Open Standards Requirement for Software Open Source AI Open Source AI OSAI Definition Process Timeline Open Weights FAQ Checklist Forum Community Become an Individual Member Become an OSI Affiliate Affiliate Organizations Maintainers Events Forum OpenSource.net The content on this website, of which Opensource.org is the author, is licensed under a Creative Commons Attribution 4.0 International License . Opensource.org is not the author of any of the licenses reproduced on this site. Questions about the copyright in a license should be directed to the license steward. Read our Privacy Policy Proudly powered by WordPress. Hosted by Pressable. Manage Cookie Consent To provide the best experiences, we use technologies like cookies to store and/or access device information. Consenting to these technologies will allow us to process data such as browsing behavior or unique IDs on this site. Not consenting or withdrawing consent, may adversely affect certain features and functions. Functional Functional Always active The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network. Preferences Preferences The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user. Statistics Statistics The technical storage or access that is used exclusively for statistical purposes. The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you. Marketing Marketing The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes. Manage options Manage services Manage {vendor_count} vendors Read more about these purposes Accept Deny View preferences Save preferences View preferences {title} {title} {title} Manage consent | 2026-01-13T08:49:33 |
https://docs.devcycle.com/platform/feature-flags/status-and-lifecycle#cleanup-checklist | Status and Lifecycle | DevCycle Docs Skip to main content Home SDKs APIs Management API Bucketing API Integrations CLI / MCP Best Practices Community Blog Discord Search Sign Up Home Getting Started Essentials DevCycle Overview Key Features System Architecture Feature Hierarchy Feature Types Platform Feature Flags Features Variables and Variations Targeting Status and Lifecycle Stale Feature Notifications Experimentation Account Management Security and Guardrails Testing and QA Extras Examples Platform Feature Flags Status and Lifecycle On this page Feature Status and Lifecycle Management In DevCycle, Features have Statuses that indicate their current position in the feature lifecycle. Statuses provide a clear, at-a-glance understanding of where a Feature is in its development, release, and cleanup process. Each Status belongs to a Status Category , which defines how the Feature behaves, what actions are allowed, and how it is displayed across the dashboard. Statuses Every Feature in DevCycle always has one Status , which determines its lifecycle stage. By default, DevCycle provides a set of predefined Statuses aligned to core lifecycle categories. The default Statuses are: Development Live Completed Archived In addition to the default Statuses, teams can define custom Statuses within their Project settings. This allows teams to better align Feature lifecycle tracking with their internal development and release processes while preserving DevCycle's lifecycle guarantees. Each custom Status inherits the behavior of their Category. Status changes are not automatic and are always managed explicitly by the user. Status Categories Statuses are grouped into Categories , which define shared lifecycle behavior. Development This Category represents Features that are actively being built, tested, or prepared for release. By default, new Features are created with the Development Status. While a Feature is in Development, all Targeting rules and Variations remain editable. This stage is typically used while work is ongoing and before a Feature is considered ready for a broader release. Below are some examples of different Statuses that would make sense in the Development Category: In Development Pending Design QA Internal Testing Live The Live Category represents Features that are actively running in production or being exposed to users. While a Feature is Live, all Targeting rules and Variations remain editable. Below are some examples of different Statuses that would make sense in the Live Category: Beta Ramping In Production Live Experiment Completed The Completed Category represents Features that have reached the end of active development and rollout. A Feature may be considered Completed once it has been tested, approved, and is fully released, or when no further targeting changes are expected. When a Feature is moved into a Status within the Completed Category, it enters a semi-read-only state : A single final (release) Variation must be selected All Environments will serve this Variation to all users Targeting rules are replaced with an "All users" rule New targeting rules and Variations cannot be added Variable values may still be edited Environments can still be toggled on or off When using the CLI to generate TypeScript types, Variables belonging to a Feature in the Completed Category will be marked as deprecated . Below are some examples of different Statuses that would make sense in the Completed Category: Ready for Cleanup All Users Enabled Stable Release Cleanup Checklist Upon entering a Completed Status, a cleanup checklist is shown for each Variable associated with the Feature. This checklist helps teams determine when it is safe to remove Variables from their codebase or archive them. If a Variable is still referenced in code or evaluated in production, removing it may result in default values being served. If Code References are enabled, additional context will be provided to assist with cleanup. Archived The Archived Category represents the terminal lifecycle state for Features. This Category and Status cannot be edited or changed. A Feature should be archived once it has been fully cleaned up and its Variables have been removed from the codebase. When a Feature is Archived: It becomes fully read-only It is hidden from standard dashboard views Audit Logs remain accessible for historical reference Metrics & Reach data will not be visible on the dashboard for Archived features Archiving Features helps keep both your dashboard and codebase clean while preserving valuable lifecycle history. Note: Feature deletion still exists, but should only be used for mistakes. Deleting a Feature permanently removes it and its Audit Log. Archived Features retain historical data that may be used for future reporting and analysis. Changing Status Moving a Feature to Completed When a Feature is moved into the Completed Category: A final Variation must be selected All Environments serve that Variation to all users Existing Environment statuses are preserved Targeting rules are replaced with a single "All users" rule Additional Variations and targeting rules are locked Reverting to Development or Live Features in the Completed Category can be reverted back to an earlier Status. When reverting: Previous Variations become available again Changes made to Variable values while Completed are retained Prior targeting rules are not restored and must be reconfigured Viewing Features by Status (Kanban View) On the Feature list page, users can switch between a List view and a Kanban-style view that displays Features grouped by their current Status, allowing teams to quickly visualize progress across the Feature lifecycle. In this view: Each column represents a Feature Status Each column header includes a total count of Features in each Status Features appear as cards within the column matching their current Status, and can be sorted differently by selected criteria Columns are ordered based on the Status order defined in Project Settings Status colors are reflected in the column headers for quick visual scanning This view is intended for high-level lifecycle tracking and workflow management. Selecting a Feature card opens the Feature detail view for configuration, targeting, and Variable management. Managing Statuses Statuses are managed at the Project level and apply to all Features within that Project. Each Project starts with a default set of Statuses aligned to DevCycle's lifecycle categories. Teams may customize these Statuses to better reflect their internal workflows. Project Settings Statuses can be viewed and managed from the Project Settings page under the Feature Statuses section. From this page, users can: View all Statuses grouped by Category Create new custom Statuses within supported Categories Edit existing Status names (Note: each Status must have a unique key) Reorder Statuses within a Category Assign colors to Statuses for quick visual identification Add a description to provide context behind what a Status represents Select the default Status applied when a new Feature is created Changes made in Project Settings take effect immediately and apply across the Project. Status Categories and Rules Statuses must belong to one of DevCycle's predefined Categories. The following rules apply: New Categories cannot be created Each Category must contain at least one Status The last remaining Status in a Category cannot be deleted Status labels and ordering within a Category can be modified Permissions for Status Changes Permission Rules When permissions are enabled: Statuses in the Development and Live Categories can be applied by any user with access to the Project Statuses in the Completed and Archived Categories can only be applied by users with the Publisher permission Only Publishers can create, and modify Feature Statuses in the Project Settings Edit this page Last updated on Jan 9, 2026 Previous EdgeDB (Stored Custom Properties) Next Stale Feature Notifications Statuses Status Categories Development Live Completed Archived Changing Status Moving a Feature to Completed Reverting to Development or Live Viewing Features by Status (Kanban View) Managing Statuses Project Settings Permissions for Status Changes DevCycle Dashboard Blog Privacy Policy Twitter Discord GitHub Copyright © 2026 DevCycle. All rights reserved. | 2026-01-13T08:49:33 |
https://opensource.org/blog/patents-and-open-source-understanding-the-risks-and-available-solutions-2 | Patents and Open Source: Understanding the Risks and Available Solutions – Open Source Initiative Skip to content Get involved About Licenses Open Source Definition Open Source AI Programs Blog Get involved About Licenses Open Source Definition Open Source AI Programs Blog Open Main Menu December 4, 2025 News McCoy Smith Patents and Open Source: Understanding the Risks and Available Solutions Why Patents Licenses Matter: The Benefits of Explicitness Although most people think of Open Source licenses as primarily creatures of copyright law, patent considerations also come into play any time one is choosing to license software (or any other technology or content) under an Open Source license. One of the first articulations of the need to consider patents as part of Open Source licensing was in the preamble of GPL-2.0 , written in 1991: [A]ny free program is threatened constantly by software patents. We wish to avoid the danger that redistributors of a free program will individually obtain patent licenses, in effect making the program proprietary. To prevent this, we have made it clear that any patent must be licensed for everyone’s free use or not licensed at all. Although GPLv2 expressed at least part of the concerns that patents presented to Open Source licensing, it also engendered years-long debates about the language used in that license addressing patents, and the extent to which it obligated licensors to grant rights to their patents. Later-developed Open Source licenses took care to include an “express” (i.e, explicitly written) patent license, of relatively well-defined scope, in an effort to make clearer to licensors what patent rights they were granting, and to licensees what patent rights they were receiving. One example is the Apache-2.0 , written in 2004, which included – in Section 3 – both an express patent license grant, as well as a “ defensive termination ” clause: If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the [licensed] Work or a Contribution incorporated within the [licensed] Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that licensed Work shall terminate as of the date such litigation is filed. In this way, the licensee was given a direct assurance that they received a patent license to the software they received under the Apache-2.0 Open Source license, as well as a warning that if the licensee were to take certain aggressive patent actions against that software, they would lose the benefit of that license. This formulation attempted to effect a form of mutual patent peace between the parties licensing and/or using the Open Source software. GPL-3.0 also adopted an explicit patent grant in Section 11 when it was issued in 2007. The Risks of Implicitness, and of Disclaimer Many of the earliest Open Source licenses – including some of the most popular so-called non-copyleft (or ”permissive”) licenses – did not address patents in any explicit way. As a result, there have been debates about the extent to which licenses such as BSD-3-Clause or MIT confer any patent rights at all. For BSD-3-Clause, opposing positions have been presented: that no patent rights are conferred , or that that license implicitly grants patent rights . A similar debate has been had for MIT: it contains no patent license , or includes an implicit patent license . Although this debate has not ever been resolved in court, there may continue to be a risk that a licensor will advance a “no patent license” argument for licenses without an explicit patent grant, leaving licensees to rely upon arguments that a grant exists implicitly – a legal analysis that can be heavily fact-dependent and may vary from jurisdiction to jurisdiction. Even more risky are licenses that attempt to disclaim the granting of any patent rights at all. The OSI confronted this issue upon submission of the Creative Commons Zero ( CC0 ) license for OSI approval in 2012. Although that license has much to recommend it – it is perhaps the best example of a comprehensive effort to dedicate content to the public domain – one portion of that license raised concerns: 4. Limitations and Disclaimers. a. No trademark or patent rights held by Affirmer are waived, abandoned, surrendered, licensed or otherwise affected by this document . A full disclaimer of any patent rights was thought to potentially run afoul of at least OSD 7 , which states that an OSI-approved license “must apply to all to whom the program is redistributed without the need for execution of an additional license by those parties.” Subsequent OSI license approval submissions with similar comprehensive patent license disclaimers have been similarly rejected. Why Licenses Are Not a Complete Solution Although well-crafted explicit patent license grants in Open Source licenses (with or without defensive termination provisions) go a long way to reducing the risks of patent infringement claims against anything using an OSI-approved license, they are not a complete solution. That is because there are many patent holders who either do not participate in Open Source development or licensing at all, or who may participate in Open Source projects but may hold patents relevant to projects to which they do not participate. In those circumstances, any patent license grants in the Open Source license governing a project would not apply to their patents. Nevertheless, the situations in which patent holders who have no patent license obligations to a particular project have made assertions against that project are relatively rare. There are several reasons for this. First, many patent-holding entities who participate in Open Source development projects understand that if they engage in patent assertions against other projects in which they do not participate, they could harm their community standing and make all Open Source projects less receptive to their participation. Additionally, many patent holders tend to view Open Source code as essentially “free as in beer” (i.e., not licensed for any monetary gain), and thus not an attractive target for patent assertions which are often made to collect substantial royalties or other damage awards. Despite the low incidence of patent assertions against Open Source projects, and the disincentives many patent holders see against making them, such patent assertions are not unheard of . In such circumstances, there are a variety of entities and mechanisms available to address the risks the assertions present to the Open Source community. For example, the Open Invention Network (OIN) — a consortium that includes thousands of members — operates the world’s largest patent non-aggression network. Members agree not to assert patents against core Open Source technologies – what OIN calls the “ Linux System Definition ,” although it encompasses much more than just the Linux kernel or the components of a Linux system. Because the many thousands of members pledge to not assert their patent rights against that defined list of Open Source technologies, a huge number of potential patent assertions are taken off the table. Similarly, Unified Patents , OIN and the Linux Foundation have joined together to create an “ Open Source Zone ” around which they can use prior-art submissions and other administrative mechanisms within patent offices around the world in an effort to invalidate or narrow patents before they become threats against Open Source projects. Other, non-Unified Patent efforts have also been successful in eliminating patent assertion risks against both Open Source software and hardware . Thus, although no Open Source alone can prevent patent litigation or other patent assertions, community structure and various organizations and initiatives can make patent aggression against Open Source commercially unattractive and potentially a threat to the ability to further assert the patent itself. The Continued Viability of Software Patents as a Risk For a time, many Open Source software developers felt that software patents were something that the law did not allow, or should not allow. The dispute about whether software patents should exist came to a head in Europe in 2002 upon introduction of the “Proposal for a Directive of the European Parliament and of the Council on the patentability of computer-implemented inventions” (CII). Many prominent Open Source supporters and developers opposed this initiative, ultimately unsuccessfully . In the United States, there was a belief among many Open Source developers that software patents did not exist or were not valid until the 2014 U.S. Supreme Court decision in Alice v. CLS Bank . This belief was not correct – in fact, the U.S. had been issuing software patents since the 1960s – but nevertheless the Alice decision provided the sort of clarity about the boundaries around which patent protection for software was available in the U.S., much in the way the CII did in Europe. These standards appear to be firmly entrenched in both jurisdictions, meaning software patents will continue to be a risk that Open Source projects – as well as non-Open Source software – will need to address through the various mechanisms described above. Practical Risk Management So what should developers and companies actually do? Know your licenses. Licenses with explicit patent grants (e.g., Apache 2.0, GPLv3) for distributed projects may mitigate the risks that contributors later argue that they never granted a license to their patents. Join a defensive network. Membership in OIN or Unified Patents may provide companies or projects meaningful protection if and when patent assertions emerge. Use open governance. Projects under recognized foundations (e.g., Linux Foundation, Apache Software Foundation) benefit from institutional defense mechanisms and may have industry backing to help collectively oppose patent assertions. Keep records. Document where your code came from and under what license. It’s your first line of defense in any dispute. Records of when code was first made publicly available (such as through public versioning systems like GitHub) may also be useful in establishing prior art status that could be used in challenging patents. Stay informed and reach out. Keep abreast of patent developments and patent assertions; there are many members of the community – including lawyers versed in both patent law and Open Source licensing – who may be able to help. The Bottom Line Patents in Open Source are often a manageable legal risk. The biggest risk isn’t infringement claims; it is not reaching out to available resources. The Open Source community has spent two decades building the scaffolding to make patent threats rare and containable. Developers who understand that landscape can focus on what they do best: innovating in the open, confident that the legal ground beneath them is far more stable than any patent myths suggest. OFA Symposium 2025 and the Launch of the Open Technology Research Network (OTRN) DPGA’s Annual Members Meeting: Advancing Open Source & DPGs for the Public Good Keep up with Open Source Please leave this field empty. Δ We’ll never share your details and you can unsubscribe with a click! Get involved Mastodon Twitter LinkedIn Reddit About About Our team Board of directors Sponsors Programs Blog Press mentions Trademark Bylaws Licenses Open Source Definition Licenses License Review Process Open Standards Requirement for Software Open Source AI Open Source AI OSAI Definition Process Timeline Open Weights FAQ Checklist Forum Community Become an Individual Member Become an OSI Affiliate Affiliate Organizations Maintainers Events Forum OpenSource.net The content on this website, of which Opensource.org is the author, is licensed under a Creative Commons Attribution 4.0 International License . Opensource.org is not the author of any of the licenses reproduced on this site. Questions about the copyright in a license should be directed to the license steward. Read our Privacy Policy Proudly powered by WordPress. Hosted by Pressable. Manage Cookie Consent To provide the best experiences, we use technologies like cookies to store and/or access device information. Consenting to these technologies will allow us to process data such as browsing behavior or unique IDs on this site. Not consenting or withdrawing consent, may adversely affect certain features and functions. Functional Functional Always active The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network. Preferences Preferences The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user. Statistics Statistics The technical storage or access that is used exclusively for statistical purposes. The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you. Marketing Marketing The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes. Manage options Manage services Manage {vendor_count} vendors Read more about these purposes Accept Deny View preferences Save preferences View preferences {title} {title} {title} Manage consent | 2026-01-13T08:49:33 |
https://www.fine.dev/blog/bolt-vs-v0-fr#conclusion | Comparaison entre Bolt.new et v0 par Vercel : Quel outil de développement alimenté par l'IA convient le mieux à votre startup ? Home Docs Changelog Pricing Sign in Get started -> Menu Home Docs Changelog Pricing <- Go Back Comparaison entre Bolt.new et v0 par Vercel : Quel outil de développement alimenté par l'IA convient le mieux à votre startup ? Chaque seconde compte. Choisissez la mauvaise plateforme de développement alimentée par l'IA, et vous risquez l'épuisement. Nous comparerons deux outils clés—Bolt.new et v0 par Vercel—puis nous présenterons Fine , l'alternative qui pourrait être exactement ce dont vous avez besoin. Table des Matières Introduction : Mettre la scène Aperçu de Bolt.new et v0 par Vercel Analyse Comparative Les Lacunes Cachées Entrez Fine : L'arme secrète des startups Appel à l'action : Essayez Fine aujourd'hui Conclusion Bibliographie Aperçu de Bolt.new et v0 par Vercel Bolt.new Qu'est-ce que c'est : Bolt.new est une plateforme de développement full-stack alimentée par l'IA qui fonctionne directement dans votre navigateur. Conçu pour simplifier le processus de développement, Bolt.new utilise l'intelligence artificielle pour faciliter la création rapide d'applications sans les contraintes traditionnelles. Caractéristiques clés : Génère et exécute des applications multi-pages : Créez des applications complexes et multi-pages sans effort. Utilise des invites en langage naturel : Interagissez avec la plateforme en utilisant des commandes simples en langage naturel, rendant le développement plus intuitif. Déploiement en un clic : Déployez vos applications en un seul clic, réduisant le temps entre le développement et la production. Forces : Bolt.new excelle dans le prototypage rapide et la mise à l'échelle facile. Son approche pilotée par l'IA permet aux développeurs, en particulier ceux qui débutent, de rapidement itérer sur des idées et de faire évoluer les applications à mesure que les demandes des utilisateurs augmentent, le tout dans une interface conviviale. v0 par Vercel Qu'est-ce que c'est : v0 par Vercel est un générateur d'interface utilisateur piloté par l'IA spécialement conçu pour React et Tailwind CSS. Il se concentre sur l'amélioration de l'expérience de développement front-end, facilitant la création d'interfaces utilisateur attrayantes et réactives. Caractéristiques clés : Génère des composants React à partir du langage naturel : Décrivez l'interface utilisateur souhaitée, et v0 générera les composants React correspondants. Intégration transparente avec Next.js et Tailwind : Conçu pour fonctionner parfaitement avec Next.js et Tailwind CSS, garantissant que vos projets maintiennent cohérence et évolutivité. SDK AI 3.0 pour le rendu d'interface utilisateur en temps réel : Utilisez le dernier SDK AI pour rendre les interfaces utilisateur en temps réel, facilitant les retours et ajustements immédiats. Forces : v0 est particulièrement bénéfique pour ceux qui déploient leur front-end via Vercel. Analyse Comparative Vitesse de Développement : Quel outil sort votre MVP plus rapidement ? Lorsque le temps est essentiel, la vitesse de développement est primordiale. Bolt.new brille avec ses capacités full-stack pilotées par l'IA, permettant un prototypage rapide et des transitions rapides du développement au déploiement. Sa fonctionnalité de déploiement en un clic garantit que votre produit minimum viable (MVP) peut atteindre le marché rapidement sans les retards habituels. D'un autre côté, v0 par Vercel est optimisé pour le développement front-end. Bien qu'il accélère la création d'interfaces utilisateur avec sa génération de composants pilotée par le langage naturel, il peut nécessiter des outils ou plateformes supplémentaires pour gérer les fonctionnalités back-end, allongeant potentiellement le délai de développement global pour un MVP full-stack. Gagnant : Bolt.new offre une solution plus complète pour sortir un MVP plus rapidement, surtout si votre projet exige des capacités front-end et back-end dès le départ. Intégration de la Pile Technologique : Flexibilité dans le choix des bibliothèques et des frameworks Bolt.new fournit un environnement unifié qui peut limiter la flexibilité dans le choix de bibliothèques et de frameworks spécifiques en dehors de son écosystème. Bien qu'il prenne en charge la génération et la mise à l'échelle d'applications multi-pages, l'intégration d'outils supplémentaires pourrait nécessiter des solutions de contournement ou ne pas être aussi transparente. v0 par Vercel excelle dans l'intégration de la pile technologique, en particulier pour les projets centrés sur React et Tailwind CSS. Son intégration transparente avec Next.js permet aux développeurs de tirer parti d'un framework robuste et populaire, garantissant la compatibilité avec une large gamme de bibliothèques et d'outils au sein de l'écosystème React. Gagnant : v0 par Vercel offre une plus grande flexibilité pour les projets qui reposent fortement sur des frameworks et bibliothèques front-end spécifiques, ce qui en fait un meilleur choix pour les piles technologiques centrées sur React et Tailwind. Facilité d'utilisation : À quel point sont-ils intuitifs pour les développeurs non experts ? Les deux plateformes privilégient des interfaces conviviales, mais leurs approches diffèrent. Bolt.new utilise des invites en langage naturel pour le développement, le rendant très accessible pour les développeurs non experts ou ceux qui débutent dans le développement full-stack. Son ensemble d'outils complet réduit la courbe d'apprentissage, permettant aux utilisateurs de se concentrer sur la construction plutôt que sur la configuration. v0 par Vercel utilise également des invites en langage naturel pour générer des composants d'interface utilisateur, ce qui simplifie le développement front-end. Cependant, son focus est plus spécialisé, ce qui pourrait nécessiter des utilisateurs d'avoir une compréhension de base de React et Tailwind pour tirer pleinement parti de ses capacités. Gagnant : Bolt.new se démarque légèrement comme l'option la plus intuitive pour les développeurs non experts cherchant une solution full-stack sans avoir besoin de connaissances techniques approfondies. Collaboration : Support pour les projets en équipe et les boucles de rétroaction Une collaboration efficace est essentielle pour les équipes de startups. Bolt.new offre des fonctionnalités collaboratives qui soutiennent les projets en équipe, permettant à plusieurs développeurs de travailler simultanément et d'intégrer les retours de manière transparente. Son environnement piloté par l'IA facilite la collaboration en temps réel, rendant plus facile la gestion des flux de travail d'équipe. v0 par Vercel prend également en charge la collaboration, en particulier dans le contexte du développement front-end. Son intégration avec les outils de conception et le rendu d'interface utilisateur en temps réel favorise un processus de conception et de développement collaboratif. Cependant, son focus sur le front-end pourrait nécessiter des outils de collaboration supplémentaires pour les projets back-end ou full-stack. Gagnant : Les deux plateformes offrent de solides fonctionnalités de collaboration, mais Bolt.new fournit une approche plus holistique pour les projets d'équipe full-stack, le rendant plus adapté à une collaboration d'équipe complète. Options de Déploiement : Déploiement en un clic de Bolt.new vs. Intégrations spécifiques à la plateforme de Vercel Bolt.new simplifie le déploiement avec sa fonctionnalité de déploiement en un clic, permettant aux développeurs de pousser leurs applications en production sans effort. Ce processus simplifié est idéal pour les startups nécessitant des déploiements rapides sans configuration étendue. v0 par Vercel, faisant partie de l'écosystème Vercel, offre des intégrations spécifiques à la plateforme qui fournissent un déploiement optimisé pour les applications front-end. Bien qu'il excelle dans le déploiement de projets React et Tailwind, le processus pourrait nécessiter plus d'étapes par rapport à l'approche de déploiement tout-en-un de Bolt.new. Gagnant : Bolt.new offre un processus de déploiement plus rapide et plus simple, ce qui est avantageux pour les startups cherchant à minimiser les complexités de déploiement. Coût et Accessibilité : Niveaux gratuits vs. plans payants et limitations Bolt.new et v0 par Vercel offrent tous deux des niveaux gratuits, permettant aux startups d'explorer leurs fonctionnalités sans engagement financier immédiat. Cependant, leurs plans payants varient en termes de fonctionnalités et d'évolutivité. Le niveau gratuit de Bolt.new inclut des fonctionnalités essentielles pour les petits projets, mais la mise à l'échelle pourrait nécessiter une mise à niveau vers des plans payants offrant des capacités améliorées comme des fonctionnalités avancées d'IA et des limites de déploiement plus élevées. v0 par Vercel s'intègre dans le modèle de tarification de Vercel, qui propose des plans évolutifs basés sur l'utilisation. Le niveau gratuit est généreux pour les projets front-end, mais une utilisation intensive ou le besoin d'intégrations avancées nécessitera de passer à un plan payant. Gagnant : Les deux plateformes offrent des structures de tarification compétitives, mais Bolt.new peut présenter une solution plus rentable pour les besoins full-stack, tandis que v0 par Vercel est idéal pour les startups fortement axées sur le développement front-end. Les Lacunes Cachées Bien que Bolt.new et v0 par Vercel offrent des fonctionnalités impressionnantes, ils ont leurs lacunes que les startups devraient considérer. Où Bolt.new est insuffisant : Intégrations limitées avec les gestionnaires de problèmes : Bolt.new manque d'intégrations étendues avec des gestionnaires de problèmes populaires comme GitHub ou Linear , qui sont essentiels pour gérer les flux de travail de développement et suivre les bugs. Où v0 par Vercel est insuffisant : Support limité pour le back-end et le full-stack : v0 est principalement axé sur la génération d'interface utilisateur front-end , offrant un support limité pour les solutions back-end et full-stack, ce qui peut entraver le développement d'applications complètes. Lacunes communes : Automatisation collaborative minimale : Les deux plateformes fournissent des fonctionnalités de collaboration de base mais manquent d' automatisation collaborative avancée au-delà du développement individuel, rendant difficile la gestion efficace de projets d'équipe plus grands et plus complexes. Entrez Fine : L'arme secrète des startups Bien que Bolt.new et v0 par Vercel aient chacun leurs forces, Fine émerge comme la solution ultime qui comble leurs lacunes et offre un environnement de développement plus complet adapté aux startups. Comment Fine comble les lacunes : Support complet des agents IA : Fine prend en charge le développement front-end et back-end, fournissant des agents IA qui gèrent l'ensemble de la pile. Cela élimine le besoin de jongler avec plusieurs outils et garantit un processus de développement cohérent. Aperçus en direct : Construisez, exécutez et testez vos applications directement dans le navigateur avec les aperçus en direct de Fine. Cette fonctionnalité permet aux développeurs de voir les changements en temps réel, facilitant les retours immédiats et les itérations plus rapides. Automatisation des flux de travail : Fine automatise les tâches répétitives, réduisant les temps de cycle de développement et permettant aux développeurs de se concentrer sur ce qui compte vraiment—créer des solutions innovantes. Les fonctionnalités d'automatisation rationalisent les flux de travail, améliorant la productivité et l'efficacité. Collaboration en équipe : Avec des espaces de travail partagés, Fine offre une gestion de projet rationalisée pour les équipes. Plusieurs développeurs peuvent travailler ensemble sans heurts, avec des boucles de rétroaction intégrées et des outils collaboratifs qui améliorent le travail d'équipe et la communication. Avantages spécifiques pour les startups : Lancements de MVP plus rapides avec moins de bugs : L'ensemble d'outils complet et les capacités pilotées par l'IA de Fine permettent aux startups de développer et de lancer leurs MVP rapidement tout en maintenant une haute qualité de code, réduisant la probabilité de bugs et d'erreurs. Cohérence et qualité du code améliorées : La plateforme impose des normes de codage cohérentes et des meilleures pratiques, garantissant que la base de code reste maintenable et évolutive à mesure que la startup grandit. Intégration avec GitHub et Linear pour un flux de travail de bout en bout : Fine s'intègre parfaitement avec des outils populaires comme GitHub et Linear, fournissant un flux de travail de bout en bout qui englobe le contrôle de version, le suivi des problèmes et la gestion de projet. Cette intégration garantit que tous les aspects du développement sont interconnectés et facilement gérables. Appel à l'action : Essayez Fine aujourd'hui Que vous soyez intrigué par l'environnement full-stack tout-en-un de Bolt.new ou la génération d'interface utilisateur élégante de v0 par Vercel, Fine offre le parfait mélange des deux mondes—et bien plus encore. En répondant aux limitations des deux plateformes et en fournissant un environnement de développement plus holistique, Fine se distingue comme le choix optimal pour les startups cherchant à gagner du temps, réduire la complexité et évoluer efficacement. Prêt à élever votre processus de développement ? Essayez Fine aujourd'hui avec notre essai gratuit ou profitez de notre processus d'inscription facile pour commencer à construire votre prochaine grande idée sans tracas. Conclusion Choisir le bon outil de développement est une décision critique pour les startups cherchant à construire des applications robustes et évolutives efficacement. Bolt.new offre une solution full-stack puissante avec des capacités de déploiement rapide, tandis que v0 par Vercel excelle dans la génération d'interface utilisateur front-end et l'intégration transparente avec React et Tailwind. Cependant, les deux plateformes ont leurs limitations, notamment dans des domaines comme les intégrations complètes et l'automatisation collaborative. Fine émerge comme la solution ultime pour les développeurs de startups, comblant les lacunes laissées par Bolt.new et v0 par Vercel. Avec son support complet des agents IA, ses aperçus en direct, son automatisation des flux de travail et ses fonctionnalités robustes de collaboration en équipe, Fine permet aux startups de lancer plus rapidement, de maintenir une haute qualité de code et d'évoluer sans heurts. L'histoire de réussite de votre startup commence avec les bons outils. Choisissez Fine et mettez votre processus de développement sur la voie de l'efficacité, de l'innovation et de la croissance . Table des Matières Complète Introduction : Mettre la scène Aperçu de Bolt.new et v0 par Vercel Bolt.new v0 par Vercel Analyse Comparative Vitesse de Développement : Quel outil sort votre MVP plus rapidement ? Intégration de la Pile Technologique : Flexibilité dans le choix des bibliothèques et des frameworks Facilité d'utilisation : À quel point sont-ils intuitifs pour les développeurs non experts ? Collaboration : Support pour les projets en équipe et les boucles de rétroaction Options de Déploiement : Déploiement en un clic de Bolt.new vs. Intégrations spécifiques à la plateforme de Vercel Coût et Accessibilité : Niveaux gratuits vs. plans payants et limitations Les Lacunes Cachées Où Bolt.new est insuffisant Où v0 par Vercel est insuffisant Lacunes communes Entrez Fine : L'arme secrète des startups Comment Fine comble les lacunes Avantages spécifiques pour les startups Appel à l'action : Essayez Fine aujourd'hui Conclusion Bibliographie Bibliographie 10Web. (n.d.). v0 par Vercel Review: Features, Pros, and Cons. Retrieved from https://10web.io/ai-tools/v0-by-vercel/ AI Product Reviews. (2024). Bolt.new: Features, Pricing, and Alternatives. Retrieved from https://ai-product-reviews.com/boltnew AI Review. (2023). v0 par Vercel: Price, Pros & Cons, Alternatives, App Reviews. Retrieved from https://ai-review.com/developer-tools/v0-by-vercel/ Aideloje, P. (2024). Vercel v0 and the future of AI-powered UI generation. Retrieved from https://blog.logrocket.com/vercel-v0-ai-powered-ui-generation/ Ånand, M. (2024). Should You Try v0, Webcrumbs or Both?. Retrieved from https://hackernoon.com/should-you-try-v0-webcrumbs-or-both Bolt. (2024). Documentation for Bolt.new. Retrieved from https://docs.bolt.new Bolt. (2024). GitHub Repository: Bolt.new. Retrieved from https://github.com/coleam00/bolt.new-any-llm Bolt. (2024). Introducing Bolt.new: AI-Powered Full-Stack Development in Your Browser. Retrieved from https://bolt.new Gelfenbuim, L. (2023). Vercel v0 First Impressions. Retrieved from https://lev.engineer/blog/vercel-v0-first-impressions Harris, L. (2024). Bolt.new vs. Vercel v0: Which AI Tool is Better for Web Development?. Retrieved from https://ai-tool-comparison.com/bolt-vs-v0 Johnson, R. (2024). How Bolt.new Simplifies Full-Stack Development for AI Enthusiasts. Retrieved from https://codejournal.io/boltnew-ai NoCodeDevs. (2024). Bolt.new Tutorial for Beginners (The Cursor AI and v0 Killer). Retrieved from https://www.nocodedevs.com/videos/bolt-new-tutorial Parkhomchuk, V. (2024). Vercel v0 AI Review: How To Use, Features And Alternatives. Retrieved from https://www.banani.co/blog/vercel-v0-ai-review Patel, D. (2024). Bolt.new Review: The Future of Full-Stack AI Development?. Retrieved from https://dev.to/patel/best-ai-tools/boltnew Rajab, A. (2024). What is Vercel's AI tool, V0.dev and how do you use it?. Retrieved from https://dev.to/opensauced/what-is-vercels-ai-tool-v0dev-and-how-do-you-use-it-3nge Rivera, J. (2024). Bolt.new Tutorial: Building a Full-Stack App Without Local Setup. Retrieved from https://tutorialcenter.com/boltnew StackShare. (n.d.). Bolt.new - Reviews, Pros & Cons | Companies using Bolt.new. Retrieved from https://stackshare.io/bolt-new StackShare. (n.d.). v0 par Vercel - Reviews, Pros & Cons | Companies using v0 par Vercel. Retrieved from https://stackshare.io/v0-vercel Vercel. (2024). AI SDK 3.0: Now Supporting Generative UI. Retrieved from https://vercel.com/blog/ai-sdk-3-generative-ui Vercel. (2024). Announcing v0: Generative UI by Vercel. Retrieved from https://vercel.com/blog/announcing-v0-generative-ui Vercel. (2024). v0 FAQ. Retrieved from https://v0.dev/faq Vercel. (2024). v0 Subscription Plans. Retrieved from https://v0.dev/subscription Wavel. (n.d.). v0 Review - Features, Pricing and Alternatives. Retrieved from https://wavel.io/ai-tools/v0-2/ YouTube. (2024). Bolt.new | Vercel v0 Killer? Retrieved from https://www.youtube.com/watch?v=R-frcOq6Kdc Zeniteq. (2024). Vercel's V0 Can Build Web Frontend In Seconds Using AI. Retrieved from https://www.zeniteq.com/blog/vercels-v0-can-build-web-frontend-in-seconds-using-ai Start building today Try out the smoothest way to build, launch and manage an app Try for Free -> © Fine.dev - All rights reserved. Product Overview AI Workflows Pricing & Plans Changelog Blog Docs Company Press Terms & Conditions Privacy policy | 2026-01-13T08:49:33 |
https://dev.to/munin-1/day-12-13-200-full-stack-dcp | Day 12 & 13 / 200 (Full Stack) - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Munin Borah Posted on May 24, 2025 Day 12 & 13 / 200 (Full Stack) # javascript # programming # beginners # webdev For Days 12 and 13 of my full stack journey, I focused on understanding the CSS position property . It controls how elements are placed on a page, and it’s more complex than it looks at first. Here's what I learned, along with simple examples: ✅ position: static This is the default value for all elements. The element stays in the normal flow of the document. You can’t move it using top , left , right , or bottom . 📌 Example: <div style= "position: static; top: 20px;" > I won’t move </div> Enter fullscreen mode Exit fullscreen mode Even though top: 20px is written, the element won’t move at all. ✅ position: relative The element stays in the flow, but now you can move it. It moves relative to its original spot . 📌 Example: <div style= "position: relative; top: 20px; left: 30px;" > I moved </div> Enter fullscreen mode Exit fullscreen mode This will move the element 20px down and 30px to the right, from where it was originally placed . ✅ position: absolute Removes the element from the normal flow. Positions it based on the nearest parent that is not static . If there’s no positioned parent, it will position based on the <body> . 📌 Example: <div style= "position: relative;" > <div style= "position: absolute; top: 0; left: 0;" > I'm inside </div> </div> Enter fullscreen mode Exit fullscreen mode Here, the inner box is absolutely positioned inside the outer div . It will stick to the top-left corner of the parent. ✅ position: fixed Removes the element from the flow. It stays fixed to the viewport (the screen). Doesn’t move when you scroll. 📌 Example: <div style= "position: fixed; top: 0; left: 0; background: black; color: white;" > Fixed Header </div> Enter fullscreen mode Exit fullscreen mode This element stays stuck to the top-left corner of the screen, even if you scroll the page. ✅ position: sticky A mix of relative and fixed . Starts off like a normal element. Once you scroll past it, it sticks to a position (like the top). 📌 Example: <h2 style= "position: sticky; top: 0; background: white;" > Sticky Heading </h2> Enter fullscreen mode Exit fullscreen mode As you scroll, this heading will stick to the top of the page until its section scrolls out of view. 💭 Final Thought I’m moving slow, but I’m not quitting. Top comments (5) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Collapse Expand Nevo David Nevo David Nevo David Follow Founder of Postiz, an open-source social media scheduling tool. Running Gitroom, the best place to learn how to grow open-source tools. Education Didn't finish high school :( Pronouns Nev/Nevo Work OSS Chief @ Gitroom Joined Feb 23, 2022 • May 25 '25 Dropdown menu Copy link Hide growth like this is always nice to see. kinda makes me wonder - what keeps stuff going long-term? like, beyond just the early hype? Like comment: Like comment: 2 likes Like Comment button Reply Collapse Expand Munin Borah Munin Borah Munin Borah Follow 🚀 On a 1825-day mission to become a top 0.1% programmer | 💡 Learning in public | Building cool things & sharing my journey Email muninb126@gmail.com Education 🎓 Self-Taught Developer | Always Learning Pronouns He/Him Work 💼 Full-Stack Developer (In Progress) | 1825-Day Dev Journey Joined Mar 30, 2025 • May 25 '25 Dropdown menu Copy link Hide Appreciate that, Nevo 🙏 Honestly, I’ve been asking myself the same thing. Right now it’s just the little wins that keep me going — like finally understanding something that confused me for days. Long-term? I’m hoping building real stuff and maybe finding a few people to learn with will help me stick with it. What’s kept you in it? Like comment: Like comment: Like Comment button Reply Collapse Expand Joseph-135 Joseph-135 Joseph-135 Follow I'm Joe a guy just transitioning into tech. Joined May 24, 2025 • Jun 5 '25 Dropdown menu Copy link Hide We are both close in learning progress; we should build something together soon to fully understand how to work remotely with people. I'm using freecodecamp too to learn. Like comment: Like comment: Like Comment button Reply Collapse Expand Kennedy Chukwu Kennedy Chukwu Kennedy Chukwu Follow Joined Aug 10, 2023 • May 24 '25 Dropdown menu Copy link Hide Keep going...it will be fruitful for you. Like comment: Like comment: 2 likes Like Comment button Reply Collapse Expand Munin Borah Munin Borah Munin Borah Follow 🚀 On a 1825-day mission to become a top 0.1% programmer | 💡 Learning in public | Building cool things & sharing my journey Email muninb126@gmail.com Education 🎓 Self-Taught Developer | Always Learning Pronouns He/Him Work 💼 Full-Stack Developer (In Progress) | 1825-Day Dev Journey Joined Mar 30, 2025 • May 25 '25 Dropdown menu Copy link Hide Thanks buddy, Like comment: Like comment: Like Comment button Reply Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Munin Borah Follow 🚀 On a 1825-day mission to become a top 0.1% programmer | 💡 Learning in public | Building cool things & sharing my journey Education 🎓 Self-Taught Developer | Always Learning Pronouns He/Him Work 💼 Full-Stack Developer (In Progress) | 1825-Day Dev Journey Joined Mar 30, 2025 More from Munin Borah Day 19/200 (Full stack) # webdev # programming # javascript # beginners Day 17&18/200 (Full stack) # webdev # programming # javascript # beginners Day 16/200 (Full stack) # webdev # programming # javascript # beginners 💎 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 | 2026-01-13T08:49:33 |
https://hmpljs.forem.com/t/beginners#main-content | Beginners - HMPL.js 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 HMPL.js Forem Close Beginners Follow Hide "A journey of a thousand miles begins with a single step." -Chinese Proverb Create Post submission guidelines UPDATED AUGUST 2, 2019 This tag is dedicated to beginners to programming, development, networking, or to a particular language. Everything should be geared towards that! For Questions... Consider using this tag along with #help, if... You are new to a language, or to programming in general, You want an explanation with NO prerequisite knowledge required. You want insight from more experienced developers. Please do not use this tag if you are merely new to a tool, library, or framework. See also, #explainlikeimfive For Articles... Posts should be specifically geared towards true beginners (experience level 0-2 out of 10). Posts should require NO prerequisite knowledge, except perhaps general (language-agnostic) essentials of programming. Posts should NOT merely be for beginners to a tool, library, or framework. If your article does not meet these qualifications, please select a different tag. Promotional Rules Posts should NOT primarily promote an external work. This is what Listings is for. Otherwise accepable posts MAY include a brief (1-2 sentence) plug for another resource at the bottom. Resource lists ARE acceptable if they follow these rules: Include at least 3 distinct authors/creators. Clearly indicate which resources are FREE, which require PII, and which cost money. Do not use personal affiliate links to monetize. Indicate at the top that the article contains promotional links. about #beginners If you're writing for this tag, we recommend you read this article . If you're asking a question, read this article . Older #beginners posts 1 2 3 4 5 6 7 8 9 … 75 … 3379 Posts Left menu 👋 Sign in for the ability to sort posts by relevant , latest , or top . Right menu 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 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 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 . HMPL.js Forem © 2016 - 2026. Powerful templates, minimal JS Log in Create account | 2026-01-13T08:49:33 |
https://dev.to/luos/how-to-use-luos-with-python-step-1-install-and-config-pyluos-5cnn | How to use Luos with Python? Step 1 - Install and config Pyluos - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Emanuel Allely for Luos Posted on Aug 16, 2021 • Edited on Oct 4, 2021 How to use Luos with Python? Step 1 - Install and config Pyluos # python # luos # embedded # opensource [Testing the new dev.to video feature] 🎥 Here is a "quick and dirty" video tutorial showing how to install and config Pyluos to use Luos with Python. 🎓 Luos is an open-source project working on "how to bring modularity and flexibility to embedded systems", like @SpaceX, @Tesla, or @Dyson do. Luos is a kind of "Docker" dedicated to embedded systems. Top comments (1) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Collapse Expand Bamba Ndour Bamba Ndour Bamba Ndour Follow A software developer who only thinks about codes Email ndourbamba18@gmail.com Location Dakar, Senegal Work Full Stack Developer, Software engineer, Freelence Joined Apr 13, 2021 • Jul 17 '22 Dropdown menu Copy link Hide Nice demo Like comment: Like comment: 1 like Like Comment button Reply Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Luos Follow Devtool that bridges the gap between hardware and software. Join the Luos Discord server to discuss about new ways to develop embedded and edge code, thanks to microservices and CI/CD Join the community More from Luos Simplify debugging to remove complexity from embedded systems # embedded # productivity # microservices # luos 🌟Become our star # github # startup # community # luos 😤 Don’t let anyone steal your bike! # opensource # tutorial # news # luos 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/sgardoll/flutterflows-ai-future-is-dreamflow-its-ai-present-is-this-2cf1 | FlutterFlow's AI Future is DreamFlow. Its AI Present is This. - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Stuart Posted on Jan 9 FlutterFlow's AI Future is DreamFlow. Its AI Present is This. # ai # flutter # dart # programming Introducing FlutterFlow Custom Code Command : A three-step AI workflow that generates, audits, and delivers production-ready Dart for your FlutterFlow projects. FlutterFlow is at a crossroads. Its new flagship product, DreamFlow, promises an AI-native Flutter visual development platform where you can be as close to the code as to the visual representation of it. It's an impressive pitch. But for the 1.6 million developers with existing FlutterFlow projects, it poses a brutal question: do you abandon your codebase for this-still-very-beta new product, or get left behind on what feels like legacy tech? But, there is a third path. You don't need to wait for DreamFlow to mature or ditch your current projects. The real, immediate need isn't AI that builds entire apps , just AI that understands FlutterFlow's infamous custom code proclivities. I built FlutterFlow Custom Code Command to solve exactly that. It's not a replacement for FlutterFlow. It's an AI-powered co-pilot that generates, audits, and delivers production-ready custom code that actually works inside your visual project. Valid Dart" ≠ "Valid FlutterFlow Let's be brutally honest. FlutterFlow's custom code feature has always been a double-edged sword. On paper, it's your escape hatch. In reality, it's a compliance nightmare. FlutterFlow isn't a standard IDE. It's a visual builder with a peculiar relationship with Dart code. It welcomes custom code... but only if it's written in a very specific way. So refined and particular are its requirements that FlutterFlow's custom code might as well be its own programming language. Think of it as TypeScript is to JavaScript—a superset with stricter rules. You've experienced this: you paste code from pub.dev, Stack Overflow, or ChatGPT that you know should work. FlutterFlow rejects it. You've experienced this: you paste valid, working Dart code from pub.dev, Stack Overflow, or ChatGPT. FlutterFlow rejects it with red underlines. Why? Generic types the visual editor can't comprehend Naming conventions that don't match FlutterFlow's expected patterns Hidden dependencies FlutterFlow won't magically add to your project Architecture that doesn't align with FlutterFlow's component model It's not you. It's the fundamental mismatch between standard Dart development and FlutterFlow's constrained, opinionated environment. The Solution: Three-Step AI That Thinks Like a FlutterFlow Engineer This tool isn't just another ChatGPT wrapper. It's a specialized workflow designed specifically for FlutterFlow's unique constraints: 1. Prompt Architect Takes your casual description ("credit card input with validation") and transforms it into a structured prompt injected with FlutterFlow's specific requirements. It speaks AI's language so the AI speaks FlutterFlow's. 2. Code Generator Uses models like GPT-5.1 Codex or Gemini 3 Pro, each with system prompts optimized for their individual strengths. You choose the model. It generates Dart code that respects FlutterFlow's architecture from the start. 3. Code Auditor (The Killer Feature) This is where the magic happens. Before you even see the code, it performs a FlutterFlow Compliance Audit : Provides an overall score (e.g., 92/100) Flags critical issues and severe warnings Lists exact required actions: "Add dart:math to project dependencies," "Create custom data type WizardFormData " Proof in Practice: Three Real-World Examples Credit Card Input Widget (Tests: algorithmic validation, input masking, tab navigation) Generated with Gemini 3 Pro. Auditor score: High 80s. Highlighted missing package dependency. Circular Progress Ring Widget (Tests: custom painting, animation, gradient effects) Generated with GPT-5.1 Codex. Auditor score: 92/100. Only note: add dart:math import. Multi-Step Form Wizard (Tests: cross-step state management, data aggregation) Generated with GPT-5.1 Codex. Auditor score: 95/100. Guided creation of custom data types and app state. These aren't toy examples. They're production-ready components with documented integration steps—all generated in minutes, not hours. Why This Approach Wins Where Others Fail While DreamFlow generates entire apps (often opaquely), this tool generates targeted, audited components you control and understand. It provides: Control: You're not surrendering your architecture to an opaque AI. You're augmenting it. Predictability: The compliance audit eliminates the "why won't this compile?" frustration. Continuity: No need to abandon your existing FlutterFlow projects. Supercharge them instead. Let's Build! Try it now: customcode.connectio.com.au See the code: It's open-source on GitHub Ask yourself: What complex component have you been avoiding? What could you build in minutes instead of hours? FlutterFlow's future might be DreamFlow. But your present—and your current projects—need pragmatic solutions that work today. This is that solution. What will you build with it? Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Stuart Follow Joined Mar 26, 2024 More from Stuart The Smart Display Google Should Have Made: My E-Ink Rebellion Against Tech Obsolescence # programming # smarthome # googlehome # buildinpublic 💎 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 | 2026-01-13T08:49:33 |
https://open.forem.com/ava_mendes/energia-solar-mercado-livre-para-mei-requisitos-tecnicos-em-2025-1l6a | Energia Solar + Mercado Livre para MEI: Requisitos Técnicos em 2025 - Open 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 Open Forem Close Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Ava Mendes Posted on Dec 25, 2025 Energia Solar + Mercado Livre para MEI: Requisitos Técnicos em 2025 # freelance # news # security Energia Solar + Mercado Livre para MEI: Requisitos Técnicos em 2025 Se você é MEI e está pensando em instalar energia solar ou migrar para o mercado livre de energia, precisa saber: as regras mudaram em 2025 . A nova NBR 17193:2025 estabeleceu requisitos de segurança muito mais rigorosos para sistemas fotovoltaicos, e a padronização dos processos de conexão pelas distribuidoras criou tanto oportunidades quanto exigências técnicas que você não pode ignorar. Neste guia prático, você vai descobrir exatamente o que é necessário para implementar energia solar ou portabilidade no seu negócio, quais normas aplicam, quanto tempo leva e — o mais importante — como evitar erros caros que comprometem sua economia. NBR 17193:2025: A Nova Realidade da Segurança Fotovoltaica A ABNT publicou em fevereiro de 2025 a NBR 17193:2025, uma norma que mudou significativamente o cenário da geração solar distribuída no Brasil. Essa norma é obrigatória para todos os novos sistemas fotovoltaicos conectados à rede, incluindo pequenas instalações em telhados de MEIs. O que mudou na prática? Antes, muitos requisitos eram opcionais. Agora, são mandatórios: Proteção contra falhas à terra com dispositivos específicos Disjuntores e fusíveis em corrente contínua (não é o disjuntor comum da sua casa) Aterramento conforme NBR 5410 e proteção contra surtos (NBR 5419) Afastamentos mínimos entre subarranjos e barreiras corta-fogo Documentação técnica completa entregue ao cliente: diagramas, certificados, laudos de testes, manual de operação Essa elevação de padrão é positiva para segurança, mas significa que você não pode simplesmente chamar "um eletricista" para instalar painéis. Precisa de um engenheiro eletricista registrado no CREA que elabore o projeto conforme NBR 16690:2019 e emita a Anotação de Responsabilidade Técnica (ART). NBR 16690: O Projeto Técnico Obrigatório A NBR 16690:2019 é a norma que define como projetar sistemas fotovoltaicos conectados à rede. Ela estabelece: Dimensionamento correto de módulos, inversores e cabos Especificação de proteções elétricas adequadas Cálculo de aterramento Toda a documentação técnica necessária Para um MEI, isso significa: você não pode instalar energia solar por conta própria ou com mão de obra desqualificada. A lei exige projeto de engenheiro, ART de projeto e ART de execução. A distribuidora não homologa sistemas sem essa documentação. O tempo para elaborar um projeto é tipicamente 2 a 4 semanas , dependendo da complexidade. Depois, você envia à distribuidora, que analisa em cerca de 15 dias (prazo típico em 2025, com tendência de padronização). NR-10: Quem Pode Instalar? A Norma Regulamentadora 10 (NR-10) estabelece que qualquer trabalho com eletricidade — incluindo montagem de sistemas fotovoltaicos — deve ser executado por profissional habilitado, capacitado e autorizado . Isso significa: Treinamento formal em eletricidade e segurança Conhecimento específico de normas técnicas Uso de equipamentos de proteção individual (EPI) Atuação sob responsabilidade de engenheiro registrado Para o MEI: contratar um instalador "amigo" ou sem qualificação formal viola a NR-10 e coloca você em risco legal, além de comprometer a segurança da instalação. A distribuidora pode rejeitar a homologação se constatar falta de conformidade com NR-10. Lei 14.300/2022: O Marco Legal da Geração Distribuída Essa lei, publicada em janeiro de 2022, é a base legal que permite microgeração (até 75 kW) e minigeração (de 75 kW a 5 MW) distribuída no Brasil. Ela define: Como você compensa energia excedente (sistema de créditos) Cronograma de transição tarifária para uso da rede Direitos e deveres do pequeno gerador Para o MEI de 2025: a Lei 14.300 garante que você pode instalar painéis e injetar energia na rede. Porém, há mudanças nas tarifas de uso da rede (TUSD) que estão sendo implementadas gradualmente. Consumidores que entrarem agora têm condições melhores que novos geradores daqui a alguns anos. Passo a Passo Prático: Como Instalar Energia Solar como MEI 1. Levante Seu Consumo e Perfil Reúna as faturas de energia dos últimos 12 meses. Identifique: Consumo médio mensal (kWh) Valor médio da conta (R$) Picos de consumo (há sazonalidade?) Horários de operação do seu negócio Tempo: 1-7 dias Documentos: Faturas de energia + dados do imóvel 2. Consulte a Distribuidora Entre em contato com sua distribuidora local e solicite o manual técnico de acesso para microgeração distribuída . Cada distribuidora tem formulários e requisitos específicos, mas em 2025 há uma tendência de padronização nacional. Pergunte: Qual é o procedimento exato para sua região? Quais formulários precisam ser preenchidos? Qual é o prazo estimado de análise? Tempo: 1-5 dias Documentos: Número da unidade consumidora, dados do titular 3. Contrate Responsável Técnico Habilitado Procure empresa ou profissional que possua engenheiro eletricista registrado no CREA . Verifique: Se emitem ART de projeto e de execução Se conhecem NBR 16690, NBR 17193, NBR 5410 e NBR 5419 Se acompanham o processo de homologação junto à distribuidora Peça referências e orçamentos de pelo menos 2-3 fornecedores. Tempo: 1-3 semanas Documentos: Dados cadastrais, fotos e medições do local 4. Elabore o Projeto Conforme Normas O engenheiro vai desenvolver: Diagrama unifilar do sistema Memorial descritivo Certificados de todos os equipamentos Análise de risco de incêndio (NBR 17193) ART de projeto assinada Isso é não-negociável. A qualidade do projeto determina se a distribuidora aprova. Tempo: 2-4 semanas Custos: Variam, mas é um investimento essencial 5. Protocole na Distribuidora Envie o projeto completo com ART e formulários preenchidos. A distribuidora analisa em torno de 15 dias (prazo típico em 2025). Pode haver pedidos de complementação — responda rapidamente. Tempo: 15-30 dias Documentos: Projeto, ART, formulários, dados do titular 6. Execução e Comissionamento Após aprovação, o instalador executa a obra seguindo o projeto. Ao final: Testes elétricos e de desempenho Laudos de conformidade Manual de operação e manutenção Roteiro de desligamento de emergência (segurança) A NBR 17193:2025 exige toda essa documentação entregue ao cliente. Tempo: 3-10 dias de instalação + testes 7. Avalie Alternativas: Solar por Assinatura Antes de decidir por instalação própria, considere energia solar por assinatura . Você não investe em painéis, mas recebe créditos de usinas remotas. Vantagens: Zero investimento inicial em equipamentos Sem obras no imóvel Sem necessidade de projeto com ART Sem complexidade técnica Economia imediata Para MEIs com consumo baixo ou que mudem frequentemente de endereço, essa pode ser a opção mais prática. Microgeração vs. Energia Solar por Assinatura: Qual Escolher? Critério Microgeração Própria Solar por Assinatura Investimento inicial Alto (R$ 15k-40k+) Nenhum Projeto com ART Obrigatório Não necessário Complexidade técnica Alta Baixa Prazo para economizar 60-90 dias (ativação) Imediato Propriedade do ativo Sim, você é dono Não, é da empresa Prazo de retorno 5-8 anos N/A (sem investimento) Ideal para MEIs com horizonte longo no imóvel MEIs com consumo baixo ou alta mobilidade Para MEIs de baixo consumo (até R$ 200-300/mês), energia solar por assinatura costuma fazer mais sentido. Para MEIs de consumo maior que planejam ficar no mesmo local por anos, microgeração própria compensa no longo prazo. Portabilidade de Energia: Uma Alternativa Complementar Você também pode combinar microgeração com portabilidade de energia — migrar para fornecedor de energia 100% renovável no mercado livre. Isso é diferente de instalar painéis: você continua usando a rede da distribuidora, mas compra energia de outro fornecedor. A portabilidade oferece: Até 20% de economia para consumidores de baixa tensão (Grupo B) Preço único durante todo o dia (sem bandeira vermelha) Energia 100% renovável (solar e eólica) Processo 100% digital e gratuito Plataformas como energialex.app simplificam essa migração. Você faz simulação gratuita em 2 minutos, envia uma foto da sua conta de energia e assina digitalmente. A ativação leva 60-90 dias, e você acompanha tudo pelo app. Vantagem: não requer projeto técnico, ART ou engenheiro. É muito mais simples que instalar painéis, e a economia começa assim que o contrato ativa. Dúvidas Frequentes P: A NBR 17193:2025 é obrigatória mesmo para sistemas pequenos em telhado? R: Sim. A norma se aplica a todos os novos sistemas fotovoltaicos conectados à rede , independentemente do porte. Fontes técnicas especializadas confirmam que não há exceção para microgeração de pequeno porte. A obrigatoriedade começou em fevereiro de 2025. P: Posso contratar qualquer eletricista para instalar meu sistema? R: Não. O projeto precisa ser assinado por engenheiro eletricista com registro no CREA e ART. A instalação deve ser executada por profissional capacitado conforme NR-10. Contratar profissional desqualificado coloca você em risco legal e pode resultar em rejeição pela distribuidora. P: Quanto tempo leva do projeto até economizar? R: Tipicamente, 60-90 dias após aprovação na distribuidora. O processo é: levantamento (1-2 semanas) → projeto (2-4 semanas) → análise distribuidora (2-4 semanas) → instalação (1-2 semanas) → ativação (até 30 dias). Total: 3-4 meses. P: Vale a pena para MEI com consumo baixo? R: Depende. Se seu consumo é menor que R$ 200/mês, energia solar por assinatura ou portabilidade podem ser mais vantajosas. Se é R$ 300-500/mês e você fica no mesmo local por 5+ anos, microgeração própria compensa. Tendências 2025: O Que Esperar Padronização de requisitos de acesso: Distribuidoras estão harmonizando formulários e prazos. Isso reduz incertezas e burocracia para pequenos geradores. Maior rigor em segurança: NBR 17193 eleva padrões, mas protege você e sua propriedade contra riscos de incêndio. Crescimento de energia solar por assinatura: Modelos de baixo investimento ganham espaço entre MEIs, oferecendo economia sem complexidade técnica. Abertura gradual do mercado livre: Discussões regulatórias indicam ampliação futura para pequenos consumidores de baixa tensão, criando novas oportunidades de economia. Conclusão: Comece Agora, mas Comece Certo A energia solar e a portabilidade de energia são ferramentas reais para economizar na conta de luz. Mas em 2025, não é mais possível improvisar. As normas técnicas, as exigências das distribuidoras e a complexidade regulatória exigem planejamento cuidadoso. Seu passo inicial: avalie qual modelo faz mais sentido para seu MEI: Microgeração própria (investimento maior, economia de longo prazo) Energia solar por assinatura (sem investimento, economia imediata) Portabilidade de energia (mudança de fornecedor, economia rápida) Se você quer explorar a portabilidade — que é a opção mais simples e rápida — energialex.app oferece simulação gratuita em menos de 2 minutos. Não custa nada verificar quanto você pode economizar, e o processo é 100% online, sem burocracia e sem compromisso. Muitos MEIs estão descobrindo que podem reduzir a conta de luz em até 20% apenas mudando de fornecedor. Qualquer que seja sua escolha, o momento é agora. As tarifas de energia seguem subindo, e as oportunidades para pequenos negócios economizarem estão mais acessíveis que nunca em 2025. Metadados Sobre a autora Ava Mendes é especialista em energia renovável e economia doméstica. Ajuda consumidores residenciais e empresariais a reduzirem custos com eletricidade através de portabilidade de energia. Conheça soluções gratuitas em energialex.app Descubra como economizar em energialex.app Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Ava Mendes Follow ⚡ Especialista em portabilidade de energia elétrica | Fundadora @ energialex.app | Ajudo brasileiros a economizarem até 20% na conta de luz | Energia limpa, economia inteligente e sustentabilidade Location Brasil Joined Oct 20, 2025 More from Ava Mendes MP 1.300/2025: o que muda no mercado livre de energia até 2027 # discuss # news 💎 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 Open Forem — A general discussion space for the Forem community. If it doesn't have a home elsewhere, it belongs here 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 . Open Forem © 2016 - 2026. Where all the other conversations belong Log in Create account | 2026-01-13T08:49:33 |
https://dev.to/voxel51/computer-vision-meetup-do-it-yourself-llms-1pp2 | Computer Vision Meetup: Do It Yourself LLMs - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Jimmy Guerrero for Voxel51 Posted on Dec 3, 2024 Computer Vision Meetup: Do It Yourself LLMs # ai # rag # llm # machinelearning In this talk, Charles Frye gives a guided tour through the components of a self-hosted LLM service, from hardware considerations to engineering tools like ‘evals,’ all the way to the application layer. We’ll consider the open weights models, open source software, and infrastructure that power LLM applications. He will heavily shill the open source vLLM project. About the Speaker Charles Frye builds applications of neural networks at Modal. He got his PhD at Berkeley for work on neural network optimization. He previously worked at Weights & Biases and Full Stack Deep Learning. Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Voxel51 Follow More from Voxel51 Elderly Action Recognition: No One Should Age Alone, AI’s Promise for the Next Generation of Elders # computervision # ai # machinelearning # datascience Journey into Visual AI: Exploring FiftyOne Together — Part IV Model Evaluation # computervision # machinelearning # ai # datascience How to Tame Your (Data) Dragon # computervision # ai # machinelearning # datascience 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/beck_moulton/private-fast-building-a-browser-based-dermatology-screener-with-webllm-and-webgpu-me8 | Private & Fast: Building a Browser-Based Dermatology Screener with WebLLM and WebGPU - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Beck_Moulton Posted on Jan 12 Private & Fast: Building a Browser-Based Dermatology Screener with WebLLM and WebGPU # privacy # ai # web # webdev In the world of health-tech, privacy is the ultimate feature . Nobody wants to upload sensitive photos of skin lesions to a mysterious cloud server just to get a preliminary health check. But what if we could bring the power of a Vision Transformer (ViT) directly to the user's browser? Today, we are diving deep into the world of Edge AI and WebGPU acceleration . We’ll build a "Dermatology Initial Screener" that runs entirely client-side. By leveraging WebLLM , TVM Unity , and Transformers.js , we can perform complex lesion analysis with zero data latency and 100% privacy. If you are interested in local inference , privacy-first AI , and the future of WebGPU-powered applications , you're in the right place! The Architecture: Privacy by Design The goal is simple: The user's photo never leaves their device. We use the browser's GPU to do the heavy lifting that used to require a Python backend with a massive NVIDIA card. graph TD A[User Image Input] --> B[HTML5 Canvas / Pre-processing] B --> C{WebGPU Support?} C -- Yes --> D[Transformers.js / WebLLM Engine] C -- No --> E[WASM Fallback/Error] D --> F[Local ViT Model / Vision-Language Model] F --> G[Classification & Reasoning] G --> H[Instant UI Feedback] style F fill:#f96,stroke:#333,stroke-width:2px style G fill:#bbf,stroke:#333,stroke-width:2px Enter fullscreen mode Exit fullscreen mode Tech Stack WebGPU : The next-gen API for high-performance graphics and computation. WebLLM : A high-performance in-browser LLM framework powered by TVM Unity . Transformers.js : To run vision models (like ViT or MobileNet) natively in JS. React/Vite : For a snappy frontend experience. Step 1: Initializing the WebGPU Environment Before we can run a model, we need to ensure the user's browser is ready for WebGPU . This is the secret sauce that makes in-browser AI run at near-native speeds. async function initWebGPU () { if ( ! navigator . gpu ) { throw new Error ( " WebGPU is not supported on this browser. Try Chrome Canary! " ); } const adapter = await navigator . gpu . requestAdapter (); const device = await adapter . requestDevice (); console . log ( " 🚀 WebGPU is ready to roar! " ); return device ; } Enter fullscreen mode Exit fullscreen mode Step 2: Loading the Vision Transformer (ViT) We’ll use Transformers.js to load a quantized version of a skin lesion classification model. By using a quantized model, we save on bandwidth while maintaining high accuracy. import { pipeline } from ' @xenova/transformers ' ; async function loadScreenerModel () { // We use a model fine-tuned on the HAM10000 dataset for skin lesions const classifier = await pipeline ( ' image-classification ' , ' Xenova/vit-base-patch16-224 ' , { device : ' webgpu ' , // Magic happens here! }); return classifier ; } Enter fullscreen mode Exit fullscreen mode Step 3: Local Reasoning with WebLLM While a ViT can classify an image, WebLLM (via TVM Unity) allows us to add a "reasoning" layer. We can feed the classification result into a local LLM to explain the findings in plain English—all without a server! import * as webllm from " @mlc-ai/web-llm " ; async function getLocalReasoning ( prediction ) { const engine = new webllm . MLCEngine (); await engine . reload ( " Llama-3-8B-Instruct-v0.1-q4f16_1-MLC " ); const prompt = `A skin scan detected a ${ prediction . label } with ${ prediction . score * 100 } % confidence. Provide a brief, non-diagnostic disclaimer and advice for a dermatologist visit.` ; const reply = await engine . chat . completions . create ({ messages : [{ role : " user " , content : prompt }] }); return reply . choices [ 0 ]. message . content ; } Enter fullscreen mode Exit fullscreen mode The "Official" Way to Build Edge AI While building a prototype is fun, scaling local AI to production requires a deeper understanding of memory management and model optimization. For more production-ready examples and advanced patterns regarding Edge AI and private data processing, I highly recommend checking out the WellAlly Official Blog . They provide excellent deep-dives into how to optimize TVM Unity pipelines for enterprise health applications, ensuring your local models are as lean as possible. Step 4: Putting it All Together (The UI) In your React component, you'd handle the image upload and trigger the pipeline. const analyzeSkin = async ( imageElement ) => { setLoading ( true ); try { const classifier = await loadScreenerModel (); const results = await classifier ( imageElement . src ); // Get the top result const topResult = results [ 0 ]; // Get local LLM reasoning const advice = await getLocalReasoning ( topResult ); setReport ({ analysis : topResult , advice }); } catch ( err ) { console . error ( " Inference failed " , err ); } finally { setLoading ( false ); } }; Enter fullscreen mode Exit fullscreen mode Why This Matters (The "So What?") Zero Latency : No waiting for a 5MB high-res photo to upload to a server in Virginia. Privacy : Medical data is sensitive. Processing it on-device is the gold standard for HIPAA-compliant-ish user experiences. Offline Capability : This tool could work in remote areas with zero internet after the initial model download. Conclusion The browser is no longer just a document viewer; it's a powerful execution environment for Edge AI . By combining WebGPU , WebLLM , and Transformers.js , we can create life-changing tools that respect user privacy by default. What do you think? Is the future of AI purely local, or will we always need the cloud for the "big" stuff? Let’s chat in the comments! 👇 Happy coding! If you enjoyed this "Learning in Public" journey, don't forget to ❤️ and bookmark! For more advanced AI architecture, visit wellally.tech/blog . Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Beck_Moulton Follow Joined Aug 22, 2022 More from Beck_Moulton Beyond Image Labels: Estimating Food Portions and Calories using Grounding DINO + SAM # ai # fastapi # sam # webdev Stop Manually Booking Doctors: Build an Autonomous Health Agent with LangGraph & Playwright # ai # python # machinelearning # opensource The Ultimate AI Diet Agent: Syncing Real-Time Health Data with Local Supermarket Inventory using CrewAI # ai # python # opensource # machinelearning 💎 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 | 2026-01-13T08:49:33 |
https://dev.to/enter#main-content | Welcome! - 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 Join the DEV Community DEV Community is a community of 3,676,891 amazing developers Continue with Apple Continue with Facebook Continue with Forem 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 DEV Community? 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 — 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 | 2026-01-13T08:49:33 |
https://dev.to/fabianfrankwerner/code-hike-in-100-seconds-1d9o | Code Hike in 100 Seconds - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Fabian Frank Werner Posted on Jan 11 Code Hike in 100 Seconds # webdev # programming # javascript # beginners Code Hike . A remark-able toolkit famous for transforming boring documentation into cinematic masterpieces. It makes your plain README files look like hot garbage by comparison. It’s the secret weapon used to build viral technical tutorials, interactive blog posts, and high-end documentation sites. It was created in 2021 by Rodrigo Pombo, a developer known for pushing the boundaries of what the web can do. He designed it to bridge the gap between static Markdown and dynamic storytelling, effectively becoming the "Christopher Nolan" of technical writing. The problem it solves is "wall-of-text" fatigue. Traditionally, if you want to explain complex code, you paste a giant block of text that readers immediately scroll past. Code Hike changes the game by treating code as a first-class citizen. Unlike standard syntax highlighters like Prism or Shiki which just colorize text, Code Hike parses the abstract syntax tree to add focus, motion, and interactivity. It allows you to guide the user's eye through a file line-by-line, creating a "scrollytelling" experience that feels more like a video than a document. To get started, install the package in a React-based framework like Next.js or Remix, then configure it as a plugin. The magic happens inside MDX files. You write standard markdown code fences, but you enhance them with magic comments. For example, write a standard JavaScript function, but inside the code block, add the comment // ! focus followed by a range of line numbers. When rendered, Code Hike will spotlight those specific lines and dim the rest, ensuring the reader knows exactly where to look. You can even attach a tooltip directly to a variable ( // ! callout ), or use the diff feature to animate changes between two versions of a file. Code Hike works by compiling your markdown into fully customizable React components. This means you can swap out the default styling for your own design system, creating a consistent look across your docs. It supports everything from line numbers and copy buttons to complex tab switching and terminal simulations. Now compile your site with npm run build and watch your engagement metrics hike up that mountain. Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Fabian Frank Werner Follow Hello, World! Pronouns he/him Joined Jan 6, 2025 More from Fabian Frank Werner An Honest Review of Google Antigravity # webdev # programming # ai # beginners JavaScript vs TypeScript - I built the same crypto tracker with both # webdev # javascript # typescript # beginners CSS vs Tailwind CSS - I built the same home page with both # webdev # css # tailwindcss # beginners 💎 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 | 2026-01-13T08:49:33 |
https://opensource.org/board-member/ruth-suehle | Ruth Suehle – Open Source Initiative Skip to content Get involved About Licenses Open Source Definition Open Source AI Programs Blog Get involved About Licenses Open Source Definition Open Source AI Programs Blog Open Main Menu Ruth Suehle Ruth Suehle she/her Director Board Member Proposed by: Apache Software Foundation Candidacy Period: March 21, 2025 – March 21, 2028 Type of Seat: Affiliate About Ruth Suehle is director of the open source program at SAS, where she is building the analytics company’s open source program office. She began her career in web development, then spent 15 years at Red Hat as editor of Red Hat Magazine, on opensource.com, and then as one of the first employees in the OSPO, eventually leading its community leadership team. Her work at Red Hat included writing their Open Source Participation Guidelines, which cover licensing and legal matters, how to participate in communities, and an “upstream first” approach. She has keynoted/spoken on community building, open hardware/makers, and the history of open source. She is co-author of Raspberry Pi Hacks (O’Reilly, Dec. 2013). Ruth is president of the Apache Software Foundation, served as executive vice-president, and has produced its conference since 2018. Ruth has served on the O3DF board and TSC, the Open@RIT advisory board, and co-founded the Open Source SIG in the International Game Developers Association. Current employer SAS Other affiliations TODO group member What areas of the Board’s work do you see yourself contributing towards? First, it is important to me that as an affiliate representative, that I am, in fact, representing on behalf of the more than 85 OSI affiliates and not only for the ASF. For the last 25+ years, the open source ecosystem has been able to succeed with many independent foundations and organizations that communicated infrequently with one another. But it is becoming increasingly useful and important for us to do what we do best—collaborate—not only within our organizations, but with one another. Networking OSI affiliates into common communications around our common needs and goals is a great potential piece of that. One of the reasons that inter-organizational collaboration has become increasingly important is the rapidly changing state of regulation and policy around the world related to software development. I was delighted to see the OSI create the Open Policy Alliance in 2023 and all of its work since then. I have supported it in the past few months by helping the OSI with its search and interview process in hiring a US policy manager and as a conference speaker on OSI-led policy panels, and I look forward to continuing to support the OSI’s policy work and inter-organizational collaboration through a director role. In a broader sense, the board’s basic duty is oversight and high-level strategy. My wide experience across a variety of parts of the open source ecosystem and with foundations (both software and otherwise) make me well-suited to supporting the OSI board functions. What goals do you hope to achieve for OSI and the world of open source by serving on the Board of Directors? The OSI has served an important role since 1998 advocating for open source software and the Open Source Definition. After significant initial attention in the early years, the open source development model went largely ignored by the rest of the world for two decades while it quietly came to be the critical underpinning of all modern software development. Although the term “open source” has from time to time been used incorrectly, it is now far from being ignored, not only by individuals and corporate contributors, but also by global regulators. As a result, we are seeing some who want to use the term to their advantage without their work being in line with the OSD. That means that the OSI’s ongoing work on behalf of the OSD and as a thought leader in open source is more important now than it has ever been. As for my personal contribution to the board, I believe organizations of all types benefit from an equilibrium of experienced members and new ones for the different perspectives they each provide. Those with long tenure provide important institutional knowledge and context, while fresh perspectives help look at things in ways that those who have long been close to the organization inevitably lose. Although I would be a newcomer to OSI’s board, I am certainly not a newcomer to the organization in general. I hope to provide some of that fresh perspective as a largely external observer in the past, balanced by the insights of board members with long OSI experience. Previous board service O3DF governing board and TSC Open@RIT advisory board LANFest board and secretary Main social media account or blog https://bsky.app/profile/suehle.bsky.social Ask this candidate questions in our forum ! Get involved Mastodon Twitter LinkedIn Reddit About About Our team Board of directors Sponsors Programs Blog Press mentions Trademark Bylaws Licenses Open Source Definition Licenses License Review Process Open Standards Requirement for Software Open Source AI Open Source AI OSAI Definition Process Timeline Open Weights FAQ Checklist Forum Community Become an Individual Member Become an OSI Affiliate Affiliate Organizations Maintainers Events Forum OpenSource.net The content on this website, of which Opensource.org is the author, is licensed under a Creative Commons Attribution 4.0 International License . Opensource.org is not the author of any of the licenses reproduced on this site. Questions about the copyright in a license should be directed to the license steward. Read our Privacy Policy Proudly powered by WordPress. Hosted by Pressable. Manage Cookie Consent To provide the best experiences, we use technologies like cookies to store and/or access device information. Consenting to these technologies will allow us to process data such as browsing behavior or unique IDs on this site. Not consenting or withdrawing consent, may adversely affect certain features and functions. Functional Functional Always active The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network. Preferences Preferences The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user. Statistics Statistics The technical storage or access that is used exclusively for statistical purposes. The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you. Marketing Marketing The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes. Manage options Manage services Manage {vendor_count} vendors Read more about these purposes Accept Deny View preferences Save preferences View preferences {title} {title} {title} Manage consent | 2026-01-13T08:49:33 |
https://docs.devcycle.com/essentials/architecture | System Architecture | DevCycle Docs Skip to main content Home SDKs APIs Management API Bucketing API Integrations CLI / MCP Best Practices Community Blog Discord Search Sign Up Home Getting Started Essentials DevCycle Overview Key Features System Architecture Feature Hierarchy Feature Types Platform Feature Flags Experimentation Account Management Security and Guardrails Testing and QA Extras Examples Essentials System Architecture On this page System Architecture When building DevCycle, we decided on a couple of core design goals from our experience of building global services and SDKs: SDKs should be easy to understand and have consistent functionality across platforms. Feature Flags should evaluate quickly and be served from as close to the end user as possible. Business-critical code should be shared across platforms to ensure consistency and reduce bugs. A cross-platform end-to-end test-harness is required to ensure SDKs are working as expected. SDKs should limit the number of start options that change the core behaviour of the SDK. With these design goals in mind, we have developed a set of Client / Mobile / Server SDKs that deliver fast global response times and local evaluation of feature flag values. The following explanations of our various SDK architectures have generally been fully implemented. How our APIs build Configuration data Features created in the Dashboard interact directly with our public Management API , to create and manage various models like Audiences / Features / Variables / Variations / etc. Changes made by the Management API are delivered via a queue to the Config Service . The Config Service bundles all changes into a JSON configuration for each Project, Environment, and SDK type combination. The configuration data is then uploaded to Cloudflare's CDN . Changes to the configuration data trigger Cloudflare's CDN cache invalidation, which can serve new data in approximately ~1 second globally. Finally, an update notification is pushed to all connected SDKs via a server-sent event (SSE) connection that informs them that new configuration data updates are available. Shared Bucketing and Segmentation Library The shared bucketing and segmentation library is the core of our SDKs and API logic. It combines configuration data containing Feature / Variable / Variation / Audience / Targeting Rule definitions with user data to bucket users into features and variations and determines variable values. Most of our APIs and SDKs use a shared WebAssembly (WASM) bucketing and segmentation library . The portability of the WASM codebase allows us to achieve the following goals: Fast : WASM is compiled in a load-time-efficient binary format, quickly loaded, and executed at near-native speeds. Portable : WASM is a portable binary format that runs on various supporting platforms. We use the recommended WASMTime runtimes supported by the Bytecode Alliance across our SDKs. It enables us to share the same core feature flag decisioning logic across all our SDKs and edge-based APIs. Well Tested : By relying on one core library making decisions across our SDKs and APIs, we can more easily ensure it is well-tested and reliable. In addition to thorough unit testing, we have a cross-platform end-to-end SDK test-harness to ensure platform consistency. Secure : WASM runs in a memory-safe sandboxed execution environment that has proven its security credentials across web browsers. However, WASM is not a silver bullet, and for certain very high performance/concurrent threading use cases, we have built a native implementation, for example, in our GO SDK . Local Bucketing Server SDK Architecture On initialization, the Server SDK retrieves the configuration data from the CDN and stores it locally. On each variableValue() / variable() call, the bucketing and segmentation library combines user data, device data, and configuration data locally to bucket users into features and variations to determine variable values. Configuration updates are received through a real-time server-sent event (SSE) connection or as a backup via polling against the CDN. Event data is aggregated within the SDK and sent to the Events API on an interval. Cloud Bucketing Server SDK Architecture For most use cases, local bucketing SDKs provide superior performance and reliability. However, the cloud-bucketing SDKs can make integration easier for specific use cases where access to EdgeDB to integrate user data between client-side and backend applications is needed. On each variableValue() / variable() call, the Cloud Bucketing Server SDKs fetch data from the Bucketing API served by Cloudflare Workers at the edge. The Bucketing API calls the shared bucketing and segmentation library to combine user, device, and configuration data to bucket the user into features and variations to determine variable values. Event data is aggregated within the SDK and sent to the Events API on an interval. Client + Mobile SDK Architecture On initialization, Mobile and Client SDKs call the Client SDK API served by Cloudflare Workers at the edge. The SDK will fall back to the previously cached configuration data or default values on a failed connection. The Client SDK API calls the shared bucketing and segmentation library to combine user, device, and configuration data to bucket the user into features and variations to determine variable values. This data is returned to the SDKs to be cached locally and used each time variableValue() / variable() is called. When user data is updated using the identifyUser() or resetUser() methods, the SDKs will request a new configuration from the Client SDK API. The Client SDKs make SSE connections to receive real-time updates, which trigger a request for an updated configuration from the Client SDK API. Event data is sent at intervals to our Events API. Latency vs. Data Storage DevCycle was designed and built for performance and reliability first. To enable Feature Flags to evaluate quickly and be served from as close to the end user as possible, we chose to not store user data to our servers by default. This means that all Feature and Variable evaluations happens using the user information provided at the time of the request, avoiding database lookups and keeping latency extremely low. For teams that do need to persist user attributes for targeting or other advanced use cases, DevCycle offers EdgeDB : a globally distributed, edge-based data store that allows you to save and retrieve user data with minimal latency. Read more about it at EdgeDB and Stored Properties . SDK Test Harness Our SDK Test Harness aims to define a set of standardized end-to-end tests that run against multiple SDKs written in different languages. The tests are defined using Jest, and are run using a set of HTTP requests made to a series of locally run proxy servers for each SDK language. These proxy servers then take the commands from the requests made from the tests to set up the SDKs in different ways, execute all the core SDK methods, and measure their responses. They ensure that each SDK behaves the same way, returns the same results, or throws the same errors for each test. Edit this page Last updated on Jan 9, 2026 Previous Key Features Next Feature Hierarchy How our APIs build Configuration data Shared Bucketing and Segmentation Library Local Bucketing Server SDK Architecture Cloud Bucketing Server SDK Architecture Client + Mobile SDK Architecture Latency vs. Data Storage SDK Test Harness DevCycle Dashboard Blog Privacy Policy Twitter Discord GitHub Copyright © 2026 DevCycle. All rights reserved. | 2026-01-13T08:49:33 |
https://talkpython.fm/episodes/transcript/534/diskcache-your-secret-python-perf-weapon | Episode #534 - diskcache: Your secret Python perf weapon | Talk Python To Me Podcast TalkPython [ ' Podcast ' ] Episodes Courses Live stream Guests Merch Blog Book New course: Agentic AI for Python Devs Black Friday deals: AI courses, full course library, and the book. --> diskcache: Your secret Python perf weapon Episode #534, published Mon, Jan 12, 2026, recorded Fri, Dec 19, 2025 Episode Deep Dive Links Transcript Download It's BLACK FRIDAY at Talk Python Get the Black Friday deals --> Guests and sponsors Vincent D. Warmerdam Talk Python Talk Python Your cloud SSD is sitting there, bored, and it would like a job. Today we’re putting it to work with DiskCache, a simple, practical cache built on SQLite that can speed things up without spinning up Redis or extra services. Once you start to see what it can do, a universe of possibilities opens up. We're joined by Vincent Warmerdam to dive into DiskCache. Play on YouTube Watch the live stream version Overcast Apple Castbox PocketCasts RSS RadioPublic Spotify Pro Edition --> YouTube Canary Every episode in your player of choice Episode Deep Dive Guest Introduction Vincent Warmerdam joins Michael Kennedy to dive deep into DiskCache. Vincent has an extensive background in data science and machine learning, which is what many in the Python community know him from. He currently works at Marimo ( marimo.io ), a company building modern Python notebooks that take lessons from Jupyter and apply a fresh, reactive approach. Vincent is also a prolific content creator, maintaining educational resources at Calmcode ( calmcode.io ) and contributing to open source projects like scikit-lego. His practical experience spans both data science workflows in notebooks and web development, giving him unique insight into how caching benefits different parts of the Python ecosystem. What to Know If You're New to Python If you are newer to Python and want to get the most out of this episode analysis, here are some foundational concepts that will help: Dictionaries in Python : DiskCache behaves like a Python dictionary with square bracket access ( cache["key"] = value ), so understanding how dictionaries work is essential. Decorators : The episode discusses using @cache.memoize decorators to automatically cache function results, similar to the built-in functools.lru_cache . Serialization with Pickle : Python's pickle module converts objects to bytes for storage; DiskCache uses this under the hood for complex objects. Multi-processing basics : Understanding that web apps often run multiple Python processes helps explain why cross-process caching matters. Key Points and Takeaways 1. DiskCache: A SQLite-Backed Dictionary That Persists to Disk DiskCache is a Python library that provides a dictionary-like interface backed by SQLite, allowing you to cache data that survives process restarts. Unlike functools.lru_cache which stores everything in memory and disappears when your Python process ends, DiskCache writes to a file on disk. This means your cached data persists across restarts, deployments, and even Docker container rebuilds. The library handles all the complexity of SQLite transactions, thread safety, and process safety behind a simple API where you just use square bracket notation like a regular dictionary. github.com/grantjenks/python-diskcache grantjenks.com/docs/diskcache 2. Thread Safety and Cross-Process Sharing One of DiskCache's standout features is that it is both thread-safe and process-safe out of the box. This is critical for web applications that typically run multiple worker processes (a "web garden") where each process needs access to the same cached data. Traditional in-memory caches like LRU cache are isolated to a single process, meaning each worker would have to build its own cache independently. With DiskCache, all processes can read from and write to the same SQLite file, and the library handles the locking and concurrency concerns automatically. Michael uses this on Talk Python's website where multiple Docker containers share a common cache volume. SQLite's built-in locking mechanisms Works across Docker containers with shared volumes 3. Massive Cost Savings: Disk is Cheap, Memory is Expensive The episode makes a compelling economic argument for disk-based caching. Modern NVMe SSDs are incredibly fast, often approaching memory speeds for read operations, but cost a fraction of what RAM costs on cloud providers. Michael mentioned paying around $5 for 400GB of disk space on his cloud VMs, while the equivalent RAM would cost orders of magnitude more. This flips the traditional "keep it in memory because it is faster" advice on its head, especially for caching scenarios where the alternative is recomputing expensive operations or making network calls to Redis. NVMe SSD performance approaches memory for many use cases Reduces cloud hosting costs significantly No need for separate Redis/Memcached servers 4. LLM and Machine Learning Use Cases Vincent highlighted DiskCache as essential for anyone working with LLMs or machine learning models. When running benchmarks or experiments, you often need to call expensive LLM APIs or run inference on local models repeatedly. If the same input produces a deterministic (or acceptable) output, caching prevents wasting compute, time, and money on redundant calls. This is especially valuable during development when you might restart notebooks or rerun experiments many times. The @cache.memoize decorator makes this trivially easy to implement on any function. Prevents redundant LLM API calls during benchmarks Saves money on cloud API costs Essential for iterative notebook workflows 5. Web Application Caching Patterns Michael shared several practical examples from the Talk Python website. He caches rendered Markdown-to-HTML conversions, parsed YouTube video IDs from show notes, and HTTP request results for cache-busting file hashes. Each of these represents a computation that does not need to happen on every request. He maintains separate cache instances for different purposes, making it easy to clear specific caches without affecting others. The pattern of using content hashes as part of cache keys ensures that cached data automatically invalidates when the source content changes. Markdown to HTML rendering YouTube ID extraction from show notes HTTP cache-busting hash computation Separate caches for different concerns 6. The Memoize Decorator for Automatic Function Caching DiskCache provides a @cache.memoize decorator that works similarly to functools.lru_cache but persists to disk. You decorate a function, and DiskCache automatically creates cache keys from the function name and its arguments. The decorator supports expiration times, so you can say "cache this for 5 minutes" for data that should refresh periodically, like a Reddit-style front page. Vincent discovered you can even exclude certain arguments from the cache key calculation, which solved his problem when a progress bar object was causing cache misses in notebook workflows. Expiration/TTL support for automatic cache invalidation Argument exclusion for objects that should not affect caching Works with any picklable Python objects 7. FanoutCache for High-Concurrency Scenarios For applications with many concurrent writers, DiskCache offers FanoutCache which automatically shards data across multiple SQLite files. Since SQLite allows concurrent readers but writers block other writers, sharding reduces contention by spreading writes across multiple database files. The default is 8 shards, but you can configure this based on your expected number of concurrent writers. This is particularly useful for high-traffic web applications or parallel data processing pipelines. Automatic sharding across multiple SQLite files Reduces write contention Django integration uses FanoutCache by default 8. Built-in Django Integration DiskCache ships with a Django-compatible cache backend that you can drop into your Django settings file. This replaces the need for Redis or Memcached as your Django cache backend while maintaining full compatibility with Django's caching APIs. You simply configure the backend as diskcache.DjangoCache and specify a location, and Django's existing caching decorators and low-level cache API work seamlessly. This is especially valuable for smaller deployments where running a separate cache server adds unnecessary operational complexity. Drop-in replacement for Redis/Memcached in Django Full Django cache API compatibility grantjenks.com/docs/diskcache/djangocache.html 9. Custom Serialization for Compression and Special Types While DiskCache uses Python's pickle by default, you can implement custom disk classes to control serialization. The documentation includes an example using JSON with zlib compression, which can achieve 80-90% size reduction for text-heavy data like LLM responses or API results. Vincent experimented with quantized NumPy array storage, trading minimal precision loss for 4x disk space savings. For JSON serialization, the hosts recommended orjson over the standard library for better performance and type support including dates and NumPy arrays. github.com/ijl/orjson - Fast JSON library with extended type support zlib compression for text-heavy caches Custom disk classes for specialized serialization needs 10. Eviction Policies and Cache Size Management DiskCache includes several eviction policies to manage cache size automatically. The default policy is "least recently stored" (LRS), but you can also use "least recently used" (LRU) or "least frequently used" (LFU). The default size limit is 1GB, which prevents unbounded cache growth but might catch developers off guard if they expect unlimited storage. You can also set expiration times on individual cache entries, which is useful for data that should automatically refresh after a certain period. Least Recently Stored (LRS) - default Least Recently Used (LRU) Least Frequently Used (LFU) Configurable size limits and TTL 11. Advanced Data Structures: Deque and Index Beyond simple key-value caching, DiskCache provides higher-level data structures. The Deque (pronounced "deck") class provides a persistent double-ended queue useful for cross-process communication or simple job queues, potentially replacing Celery for simpler use cases. The Index class provides an ordered dictionary with transactional support, allowing you to retrieve multiple values atomically. These structures enable patterns like work distribution across processes without requiring external message brokers. Deque for persistent queues and cross-process communication Index for ordered dictionaries with transactions Potential replacement for simple Celery use cases 12. Related Tools in the SQLite Ecosystem The conversation touched on several complementary tools in the SQLite ecosystem. Litestream provides continuous streaming backup of SQLite databases to S3-compatible storage, making SQLite viable for production deployments with proper backup strategies. Plash is a new Python-focused hosting platform from Answer AI (Jeremy Howard's company) that provides persistent SQLite as a first-class database option. These tools reflect a broader trend of reconsidering SQLite for production use cases that previously required PostgreSQL or MySQL. litestream.io - Streaming SQLite backup to S3 plash.io - Python hosting with persistent SQLite github.com/benbjohnson/litestream 13. Vincent's Code Archaeology Project Vincent built a visualization project called "Code Archaeology" that demonstrates DiskCache in a real-world data science context. The project analyzes Git repositories by running git blame across 100 time samples to show how code evolves over time, with sedimentary-style charts showing which lines of code survive versus get replaced. Processing large repositories like Django (550,000 lines) took over two hours, making caching essential for iterative development. The project is open source and welcomes contributions of additional repository analyses. koaning.github.io/codearch - Live visualization Threading combined with DiskCache for parallel processing Real-world example of caching expensive git operations 14. Project Maintenance Status and Longevity The hosts acknowledged that DiskCache has not had a release since 2023, with the maintainer (Grant Jenks) possibly busy with work at OpenAI. However, both Vincent and Michael emphasized this should not discourage adoption. The library is mature, stable, and built on SQLite which is actively maintained. Vincent stated he would need to see the library "break vividly in front of my face" before considering alternatives. The codebase is open source and could be forked if necessary, but the underlying SQLite dependency makes breaking changes extremely unlikely. Last PyPI release: 2023 Built on actively-maintained SQLite Considered stable/"done" rather than abandoned Interesting Quotes and Stories "It really behaves like a dictionary, except you persist to disk and under the hood is using SQLite. I think that does not cover everything, but you get quite close if that is the way you think about it." -- Vincent Warmerdam "Your cloud SSD is sitting there, bored, and it would like a job." -- Michael Kennedy (from episode summary) "I pay something like $5 for 400 gigs of disk. Do you know how much 400 gigs of RAM will cost on the cloud? There goes the college tuition." -- Michael Kennedy "I vividly remember when I started college, people were always saying, keep it in memory because it is way faster than disk. But I think we have got to let a lot of that stuff just go." -- Vincent Warmerdam "This cache needs to break vividly in front of my face for me to consider not using it. Because it does feel like it is done, and in a really good way." -- Vincent Warmerdam "There are only two hard things in computer science: naming things, cache invalidation, and off by one errors." -- Referenced during discussion "One thing I learned is that caching is actually hard to get right. It is on par with naming things." -- Vincent Warmerdam "How do you fix that with a whole bunch of infrastructure? No, with a decorator." -- Vincent Warmerdam on the simplicity of DiskCache Story: The Progress Bar Bug Vincent shared a debugging story from building his code archaeology project. He was using the memoize decorator but noticed his cache was never being hit. After investigation, he discovered the problem: one of his function arguments was a Marimo progress bar object. Every time he reran the notebook, a new progress bar instance was created with a different object ID, causing every cache lookup to miss. The solution was DiskCache's ability to exclude specific arguments from the cache key calculation - a feature he was relieved to find already existed in the library. Key Definitions and Terms LRU Cache : Least Recently Used cache, a caching strategy that evicts the least recently accessed items first. Python's functools.lru_cache implements this in memory. Memoization : An optimization technique that stores the results of expensive function calls and returns the cached result when the same inputs occur again. Serialization/Pickle : The process of converting Python objects into a byte stream for storage or transmission. Pickle is Python's built-in serialization format. Sharding : Distributing data across multiple storage locations (in this case, multiple SQLite files) to reduce contention and improve performance. TTL (Time To Live) : An expiration time set on cached data after which it is automatically considered stale and removed. ACID Compliance : A set of database properties (Atomicity, Consistency, Isolation, Durability) that guarantee reliable transaction processing. SQLite is ACID-compliant. Web Garden : A deployment pattern where multiple worker processes handle web requests, typically managed by a WSGI server like Gunicorn or uWSGI. NVMe SSD : Non-Volatile Memory Express Solid State Drive, a modern storage interface that provides significantly faster read/write speeds than traditional SATA SSDs. Learning Resources Here are resources to learn more and go deeper on topics covered in this episode: LLM Building Blocks for Python : Vincent's course that originally sparked this episode, covering practical LLM techniques including caching strategies for API calls and benchmarks. Agentic AI Programming for Python : Collaborate with AI like a skilled junior developer. Build production features in hours with Cursor and Claude. Get real results. Python for Absolute Beginners : If you are new to Python and want to understand dictionaries, decorators, and other fundamentals referenced in this episode. HTMX + Flask: Modern Python Web Apps : Covers web development patterns where DiskCache caching techniques would be immediately applicable. Overall Takeaway DiskCache represents a powerful example of choosing the right tool for the job rather than reaching for the most complex solution. In an era where developers often default to running Redis or Memcached servers for caching, DiskCache offers a compelling alternative that requires no additional infrastructure, leverages the rock-solid reliability of SQLite, and takes advantage of modern fast SSDs that have closed much of the performance gap with RAM. Whether you are building web applications, running LLM experiments, or processing data in notebooks, the pattern is the same: expensive computations should not be repeated unnecessarily. The library embodies the Unix philosophy of doing one thing well. Its dictionary-like API means there is virtually no learning curve for Python developers, while advanced features like sharding, transactions, and custom serialization are available when needed. Vincent's observation that this is in his "top five favorite Python libraries" and Michael's extensive production use on Talk Python speak to its real-world reliability. Perhaps most importantly, this episode challenges conventional wisdom about caching architecture. You do not always need a separate cache server. You do not always need to keep everything in memory. Sometimes the simplest solution - a well-designed SQLite file on a fast SSD - is exactly right. As Vincent put it: "Give this cache thing a try. It is just good software." Links from the show diskcache docs : grantjenks.com LLM Building Blocks for Python course : training.talkpython.fm JSONDisk : grantjenks.com Git Code Archaeology Charts : koaning.github.io Talk Python Cache Admin UI : blobs.talkpython.fm Litestream SQLite streaming : litestream.io Plash hosting : pla.sh Watch this episode on YouTube : youtube.com Episode #534 deep-dive : talkpython.fm/534 Episode transcripts : talkpython.fm Theme Song: Developer Rap 🥁 Served in a Flask 🎸 : talkpython.fm/flasksong ---== Don't be a stranger ==--- YouTube : youtube.com/@talkpython Bluesky : @talkpython.fm Mastodon : @talkpython@fosstodon.org X.com : @talkpython Michael on Bluesky : @mkennedy.codes Michael on Mastodon : @mkennedy@fosstodon.org Michael on X.com : @mkennedy Episode Transcript Collapse transcript WebVTT format On GitHub 00:00 Your cloud SSD is sitting there, bored, and it would like a job. 00:03 Today, we're putting into work with DiscCache, a simple, practical cache built on SQLite 00:08 that can speed things up without spinning up Redis or other extra servers. 00:13 Once you start to see what it can do, a universe of possibilities opens up. 00:17 We're joined by Vincent Warmerdom to dive into DiscCache. 00:21 This is Talk Python To Me, episode 534, recorded December 19th, 2025. 00:27 Talk Python To Me, yeah, we ready to roll. 00:29 Upgrading the code, no fear of getting old Async in the air, new frameworks in sight 00:35 Geeky rap on deck, Quart crew It's time to unite We started in Pyramid, cruising old school lanes 00:41 Had that stable base, yeah sir Welcome to Talk Python To Me, the number one Python podcast for developers and data scientists. 00:48 This is your host, Michael Kennedy. 00:49 I'm a PSF fellow who's been coding for over 25 years. 00:54 Let's connect on social media. 00:55 You'll find me and Talk Python on Mastodon, Bluesky, and X. 00:58 The social links are all in your show notes. 01:01 You can find over 10 years of past episodes at talkpython.fm. 01:05 And if you want to be part of the show, you can join our recording live streams. 01:08 That's right. 01:09 We live stream the raw uncut version of each episode on YouTube. 01:13 Just visit talkpython.fm/youtube to see the schedule of upcoming events. 01:17 Be sure to subscribe there and press the bell so you'll get notified anytime we're recording. 01:22 Vincent, hello. 01:23 Michael, Michael, we're back. 01:25 Awesome. 01:26 Awesome to be back with you. 01:27 Yeah, this is almost the sequel to the last time you were on the show. 01:32 So it's going to be fun. 01:34 Yeah, so sequel in this case, not the query language, 01:36 like an actual sequel of events. 01:38 Yes. 01:39 Yeah, you can correct me if I'm wrong, but I think what happened is you had me on a podcast a while ago 01:45 to talk about a course that I made, and a big chunk of the course that we were very enthusiastic about 01:49 was about this tool called DiscCache. 01:51 And then we kind of came to the conclusion, well, we had to cap it off. 01:54 Maybe it's fun to do an episode on just DiscCache. 01:57 since we're both pretty huge fans of it. 01:59 I think that's how we got here. 02:00 I think that is how we got here as well. 02:02 And we're going to dive into this. 02:05 Honestly, it's a pretty simple library called Disc Cache, 02:09 but what it unlocks is really, really sweet. 02:11 And I'm going to talk about a lot of different angles. 02:14 And now, even though it's just been not that long since you were on the show, 02:18 maybe just give us a quick intro of who you are. 02:20 Hi, my name is Vincent. 02:21 I've done a bunch of data machine learning stuff, mainly in the past. 02:25 That's sort of what a lot of people know me from. 02:27 These days, though, I work for a company called Marimo. 02:29 You might have heard from us. 02:30 We make very modern Python notebooks. 02:32 We took some lessons from Jupyter, and we take a new spin of it. 02:35 So that's my day to day. 02:37 But I still like to write notebooks and do kind of fun little benchmarks and also stuff 02:42 with LLMs. 02:42 And I've just noticed that for a lot of that work, boy, 02:45 disk cache is amazing. 02:47 And I also use it for web stuff. 02:48 And I think that's also what your use case is a little bit more of. 02:51 But yeah, in notebook land, you also like to have a very good caching mechanism 02:56 And on the Mremo side of things, we are also working on different caching mechanisms, which I might talk about in a bit. 03:01 But just for me, the bread and butter, the thing I've used for years at this point is disk cache whenever it comes to that territory. 03:06 Yeah, it's funny. 03:07 This was recommended to me for Python Bytes as a news item over there quite a while ago, like years ago. 03:13 And I'm like, oh, that's pretty interesting. 03:15 And then I saw you using it in the LLM Building Blocks course, and it just unlocked for me. 03:20 Like, oh, my. 03:22 Oh, this is something else. 03:24 And so since then, I've been doing a bunch with it, and I'm a big fan. 03:27 I've been on this, like trying to avoid complexity, but still getting really cool responses, performance, et cetera, out of your apps. 03:35 And I think this is a really nice way to add multi-process, super fast caching to your app without involving more servers and more stuff that's got to get connected and keep running and so on. 03:47 But before we get into the details of that, maybe let's just talk about caching in general. 03:53 Like what types of caching is there? 03:55 You know, I sort of give a little precursor there. 03:57 But yeah, dive into it. 03:58 So like in the course, the main example I remember talking about was the one-- 04:03 you've got this LLM, and you want to do some benchmarks. 04:05 And it might be the case that, I don't know, using an LLM for, let's say, classification, 04:09 like some text goes in, we got to know whether or not 04:12 it's about a certain topic, yes, no, or something like that. 04:14 Then it would be really great if, suppose, the same text came 04:17 by for whatever reason, that we don't run the query on the LLM 04:21 Again, it's like wasted compute, wasted money. 04:23 So it'd be kind of nice if the same text goes in that we then say, 04:27 oh, we know what the answer to that thing is already. 04:29 We cached it, so here you can go back. 04:31 And that's the case when you're dealing with heavy compute ML systems. 04:35 But there's a similar situation that you might have, I guess, 04:37 with expensive SQL queries, or you want to reduce the load on a database somewhere. 04:41 Then having some sort of a caching layer that's able to say, 04:43 oh, you're querying for something, but I already know what it is. 04:47 Boom, we can send it back. 04:49 I think the classical thing you would do in Python is you have this decorator in functools, I think, right? 04:53 The LRU_cache. 04:57 Yeah, exactly. 04:58 Yeah. 04:58 That's a hell of a world to that. 04:59 But the downside of that thing is that it's all in memory. 05:02 So if you were to reboot your Python process, you lose all that caching. 05:05 So that's why people historically, I think, resorted to-- 05:08 I think Redis, I think, is the most well-known caching tool. 05:12 It's the one I've always used. 05:13 There's Memcache, I think. 05:14 There's other tools. 05:15 You could use Postgres for some of this stuff as well. 05:18 But recently, especially because disks are just getting quicker 05:21 and quicker, people have been looking at SQLite for this sort of a thing as well. 05:25 So that's, I think, the quickest summary and also sort of the entryway to how I got started with disk cache. 05:31 Yeah, and so for this example that you highlight in the LLM 05:34 Building Blocks course, it's not a conversation. 05:38 It's like a one-shot situation, right? 05:41 You come up-- you say, I have some code or some documents, 05:43 and I have almost like an API. 05:45 I'm going to send that off to the LLM and ask it, tell me X, Y, and Z about it. 05:51 And sure, it's got some kind of temperature and it won't always give an exactly the same answer, 05:56 but you're willing to, you know, you're willing to accept an answer. 06:00 And at that point, like why ask it again and again and again, which it might take seconds, 06:05 it might cost money. 06:06 Whereas if you just remember through caching somehow, you remember it, it's like, boom, instant. 06:13 Yeah, and it tends to come up a lot in when you're doing benchmarks, for example. 06:16 So you have this for loop, you want to go over your entire data set, try all these different approaches. 06:21 And if you've got a new approach, then you want that to run, of course. 06:23 But if you accidentally trigger an old approach, then you don't want to incur the cost of like going through all those different LLMs. 06:29 I should say, like, even if you just forget about LLMs, let's just say machine learning in general. 06:33 Let's say there's some sort of image classification thing you're using in the cloud. 06:36 There also, you would say, like, file name goes in. 06:39 that's an image and if the same file name goes in we don't want the expensive compute cost to happen 06:43 either so it's definitely more general than llms but llms do feel like it's the zeitgeisty thing to 06:48 worry about yeah i think for two reasons one because they're just the topic du jour and two 06:54 because they're they're i think a part of computing that most people experience that is way slower than 06:59 they're used to yeah well and especially if you're you know if i suppose that you you have a an 07:05 an attic somewhere and you're a dad and you want to do home lab stuff and you're playing with all 07:09 these open source LLM models, then you also learn that, yeah, they're fun to play with, but they also 07:14 take a lot of time to compute things. So then immediately you get the motivation to do it the 07:18 right way. Yeah, I built a couple of little utilities that talk to a local LLM. I think it's 07:25 the OpenAI OpenWeights one, that 20 billion parameter one I have running on my Mac Mini, 07:31 and it's pretty good, a little bit slow, but, you know, it's fine for what it's being used for. And 07:35 put-- use your disk cache technique on it. 07:39 And if I ask it the same question again, it's like, boom. 07:41 You don't need to wait 10 seconds. 07:43 Here's the answer. 07:43 Yeah. 07:44 So that-- and I guess like-- but I guess from your perspective, 07:46 I think your main entry point to this domain was a little bit more from the web dev perspective, right? 07:51 Like that's-- and I suppose you're using it a lot for preventing expensive queries to go to Postgres, 07:57 or I don't exactly know your backend. 07:59 You know how-- you won't believe how optimized my website is. 08:02 There's not a single query that goes to Postgres, because they go to MongoDB. 08:06 I'm just kidding. 08:06 There you go. 08:07 No, but your point is totally valid. 08:10 Go into the database, right? 08:11 Now, I don't actually cache that many requests. 08:15 I don't avoid that many requests going to the database. 08:17 They're really quite quick, and so I'm OK with that. 08:19 But when you think about a feature-rich database, feature-rich web app, there's just tons of these little edge 08:26 cases you're like, oh, got to do that thing. 08:28 And it's not a big deal, but we've got to do it 500 times in a request. 08:31 Then it is kind of a thing. 08:34 So let me give you an example. 08:35 I'll give you some examples. 08:36 So for example, the good portions of the show notes on talkpython.fm are in Markdown. 08:43 I don't want to show people Markdown. 08:44 I want to show them HTML, right? 08:47 So when a request comes in, it'll say any fragment of HTML that needs 08:53 to be turned into Markdown instead of just going, oh, 08:56 let me process that. 08:57 It just goes, all right, what is the hash of this or some other indicator of the content? 09:03 And then I've already computed that and stored it in disk cache. 09:06 So here's the HTML result. 09:08 Another example is there's a little YouTube icon on each page. 09:13 And that's actually in the show notes, but then the website parses the YouTube ID out 09:17 and then embeds it with an, like, there's a bunch of stuff going on there to keep YouTube 09:22 out of spying on my visitors. 09:25 But stuff happens, YouTube ID is used. 09:27 That could be parsed every time. 09:29 Or I can just say this episode has this YouTube ID. 09:33 That information goes into a cache, right? 09:35 And because it's a disk cache sort of scenario, like a file-based one, not an LRU cache. 09:42 It doesn't change the memory footprint and it's shared across processes. 09:46 So in like the web world, it's really common to have a web garden 09:48 where you've got like two or four processes all being like round robin to 09:53 from some web server manager thing, right? 09:56 If you don't somehow out of process that, either Redis or SQLite or database or something, 10:03 then all of those things are recreating that, right? 10:05 They can't reuse that, right? 10:07 So there's a lot of interesting components there. 10:09 And I suppose your web deployment, you have like a big VM, I suppose, 10:11 and then there's like multiple Docker containers running, 10:14 but they do all have access to the same volume, and that's how you access SQLite. 10:18 Bingo, yeah, exactly, exactly. 10:21 And how am I doing? 10:22 Yeah, so what I have done is in the Docker Compose file, 10:26 I have an external, This is also important for Docker. 10:29 So I have an external folder on a big hard drive in the big VM that says, here's where 10:34 all the caches go. 10:36 And then depending on which app, it'll pick like a sub directory it can go look at or 10:40 whatever that it's using. 10:41 And so that way, even if I do a complete rebuild of the Docker image, it still retains 10:48 its cache from version to version and all that kind of business. 10:51 You could do that with a persistent VM as well, volume as well. 10:55 But I've just decided-- 10:57 you can go and inspect it a little easier and see how big the cache is and stuff like that. 11:00 OK, so we're going to get into the weeds of how disk cache works exactly. 11:04 But I'm triggered here because it sounds like you've done 11:06 something clever there. 11:07 Because what you can do in disk cache is you can say, look, here's a file that's SQLite. 11:11 And then it behaves like a dictionary, but it's persisted on disk. 11:14 But what I just heard you say is that you've got multiple caches. 11:16 So am I right to hear that, oh, for some things that 11:19 need to be cached, let's say the YouTube things, that's a separate file. 11:22 And then all the markdown stuff, that's also a separate file, and therefore if connections need to be made to either, 11:27 it's also kind of nicely split. 11:29 Is that also the design there? 11:30 Yeah, that is. 11:30 And actually, before, like, we're going to dive into all the details of how it works, 11:33 but I'll just go, I'm just to give people a little glimpse. 11:36 I'll go ahead and show, I've got this whole admin back in here. 11:39 And I've got different caches for different purposes. 11:42 Because they're just SQLite files, you can either say, give me the same one, 11:45 or you can say, this one is named something else, and it has a different file name or different folder or whatever. 11:50 Right, so I've got one that stores things like that YouTube ID I talked about 11:53 any markdown, any fragment of markdown anywhere in the web app that it needs to say that needs 11:58 to go to HTML, like just. 12:00 Yeah, and it's like 8,000 items in that thing. 12:03 Yeah. 12:04 In this one, there's 8,970 items, which is nine megs, right? 12:08 I mean, it's not huge, but it's not too bad. 12:10 And you can actually even see where it thinks it lives, but that's not really where it lives 12:14 because there's, you know, the volume redirects and stuff. 12:17 But I've also got stuff for directly about the episodes that it needs to pull back. 12:22 And then I do a lot of HTTP caching. 12:25 And one of the things that I think is really wrong with web development is people say, 12:30 well, that's like a stale image or that's a stale CSS file or JavaScript, you know, 12:33 all that kind of stuff. 12:34 So if you just do like super minor tricks and just put some kind of hash ID on the end 12:41 of your content, it will, and you teach your CDN or whatever, that that's a different file 12:47 if it varies by query string, then you never, ever have to worry about stale content ever. 12:52 right but computing that can be expensive especially for remote stuff like if it's it's on a different 12:57 it's like a s3 thing but you still want to have it do that so i have a special cache for that and 13:01 that takes that's like pretty complicated to build up because it's got to do like almost 700 web 13:06 requests to figure out what those are but once they're done it's blazing fast you don't have to 13:10 do it again right unless it changes then it doesn't change much and so on so there's that's the way 13:14 that i'm sort of using and appreciating disk cache yeah it works well in your setup because you've 13:19 gone for the VM route. I mean, if you go for something like Fly.io or maybe even 13:24 DigitalOcean has like a really, I think it's a nice like app service, but that 13:27 all revolves around Docker containers that like spin up horizontally. And I 13:31 don't think those containers can be configured in such a way they share the volume. 13:36 So in that sense, you could still use disk cache, but then 13:40 each individual instance of the Docker container would have its own cache, which still could 13:43 work out. 13:45 Not going to be as well well functional. It's going to be better with your setup, though. 13:50 Yeah, absolutely. I agree, though. You could still do it. Or you could go, I'll take the 13:55 zen of what Vincent and Michael are saying today, and I'll apply that to Postgres, or 13:59 I'll apply that to whatever data. You could pull this off in a database. 14:03 You would just have to do more work. Yeah. I mean, I've had a couple of, I think 14:07 it was like a Django conference talk I saw a while ago. They were also raving about 14:11 disk cache. But the merits of disk cache do depend a little bit on your 14:15 deployment, though. 14:15 That is, I think, one observation. 14:17 Like in your setup, I can definitely imagine it. 14:18 Interesting. 14:19 Yeah. 14:19 Yeah. 14:20 Well, I don't even think we properly introduced this thing 14:22 yet, so. 14:23 But let's maybe go there. 14:24 Yeah. 14:24 Let's start there. 14:25 Let's start there. 14:26 It's time. 14:26 OK. 14:27 It's time. 14:27 Yeah. 14:29 I guess the simplest way I usually describe it, it really behaves like a dictionary, 14:33 except you persist a disk and under the hood is using SQLite. 14:36 I think that's the-- it doesn't cover everything, but you get quite close, if that's the way it is. 14:40 I think there might be-- 14:42 you know, I keep harping on this on the show, but there are so many people that are new to Python 14:45 and programming these days. 14:47 Many, many of them, almost half of them. 14:49 I think it's worth pointing out, just like, what is SQLite? 14:51 Like, why is it different than any other database? 14:54 Like, why have I been using the word database or SQLite 14:56 when SQLite is a database, right? 14:57 That's weird. 14:58 - So, I never really took a good database, of course. 15:01 I might be ruining the formalism of it. 15:04 But the main, like, for me at least, the way I like to think about it is Postgres, 15:08 that's a thing I can run on a VM, and then other Docker containers can connect to it 15:13 because it's running out of process. 15:14 There's some other process that has the database somewhere, 15:17 and I can connect to it. 15:18 And I think the main thing that makes SQLite different 15:20 is that, no, you got to run it on the same machine, 15:23 on the same process where your program is running. 15:25 And that's, I think, the main-- 15:26 and there's all sorts of little details, like how the data structures are used internally, 15:30 and SQLite doesn't have a lot of types. 15:32 There's lots of other differences. 15:33 I think that's the main one. 15:35 Unless, Michael, I forgot something. 15:36 MICHAEL LUTH: Yeah, no, I think it's-- 15:38 and it's-- 15:40 operationally, it's a separate thing run. It has to have both, it has to be secure because if your data gets exposed, like- 15:49 For Postgres, is it not for SQL? Yes, it's running somewhere. People can SSH in if you're 15:54 not careful. You've got to be mindful of passwords and all that stuff. That's totally true. 15:58 Right. And it can go down. Like it could just become unavailable because you've screwed up 16:02 something or whatever, right? It's a thing you have to manage in the complexity of running your app 16:07 when it's like, well, it used to just be one thing I could run in a Docker container. Well, 16:10 now I got different servers, they got to coordinate and there's firewalls and there's like, it's just, 16:14 it just takes it so much higher in terms of complexity that like SQLite is a file. 16:19 Yes. 16:20 I mean, I do want to maybe defend Postgres a little bit there. 16:22 Cause one thing that's like really nice and convenient in terms of like CICD and deployments 16:26 and all that, oh, suppose you want to scale horizontally and there's like Docker containers 16:31 running on the left and there's this one Postgres thing running on the right. 16:34 I mean, you can just turn on and off all those Docker containers as you see fit. 16:38 they're just going to connect to the Postgres instance. 16:40 And I've done this trick for Calm Code a bunch of times 16:43 where I just switch cloud providers, because Postgres is running there, 16:46 and I can just move the Docker containers to another cloud provider, and it all works fine. 16:50 No migration necessary. 16:52 With SQLite, that aspect is a little bit more tricky. 16:54 You have to be a bit more mindful. 16:56 Although, I should mention, might be worth a Google. 16:59 There's actually this one new cloud provider that's very much Python-focused. 17:02 It's called Plash, P-L-A dot S-H, I think. 17:06 Oh, this is new to me. 17:07 Yeah, so I think-- 17:08 Wow, OK. 17:09 Look at this. 17:09 From.py to.com in seconds. 17:12 Yeah, it's the Answer AI, Jeremy Howard and friends. 17:15 I don't know to what extent this is super production ready. 17:18 And SQLite, you've got to be mindful of the production aspect 17:22 for some reasons as well. 17:23 But one thing that is kind of cool about them is they give you a persistent SQLite as a database 17:29 and a pipeline process that can just kind of attach to it. 17:32 And they just-- in their mind, that's the simplest way that a cloud provider should be. 17:36 take a very opinionated approach. 17:38 So yeah, if you're interested in maybe running this 17:40 as a web service, migrations are a little bit tricky 17:43 in that realm, because you do have to download the entire data set due to migration 17:47 and upload it again, I think, if I recall correctly. 17:50 And for some apps, that's no big deal. 17:52 Others, that's a mega deal. 17:53 Depends how big that data is. 17:55 So I'm not suggesting this is going to be for everything and everyone, 17:58 but I do think it's cool, which is why I figured I'd mention it. 18:00 Oh, it's new to me. 18:03 I'm going to follow up with a lightstream.io. 18:06 Have you seen this? 18:07 Yeah, that is also really neat. 18:11 So basically, what if you want to back up your SQLite? 18:13 Like, how could you do that? 18:15 Oh, it might be nice to do that with S3. 18:17 And I think it's like the guy who made the thing works at Fly.io. 18:21 He's doing a bunch of low-level stuff. 18:23 One thing about that open source package is also really interesting, by the way, 18:26 is I think he refuses PRs from the outside. 18:30 He just wants to have no distractions whatsoever. 18:33 He has a very interesting way of developing software. 18:35 You can submit issues, of course. 18:38 I think if you scroll down, there used to be a notice that 18:40 basically said, hey, this is a-- 18:42 I'm not running this-- 18:43 Yeah. 18:44 There you go. 18:45 We welcome-- yeah, contribution guide. 18:48 We welcome bug reports. 18:51 Yeah, this is a way where you can basically stream updates to S3. 18:54 And the main observation there is S3 is actually really cheap 18:58 if all you do is push stuff into it. 18:59 If you never pull it out, usually getting it out is the expensive bit of S3. 19:03 So this is like pennies on the dollar for really decent backup. 19:08 And you can also send it to multiple-- 19:09 you can send it to Amazon and also to DigitalOcean, 19:11 if you like. 19:12 Yeah. 19:13 Yeah, because these days, S3 is really a synonym for blob storage on almost any hosting platform. 19:20 Like, it used to be S3 might go to literally S3 at AWS. 19:23 But now it's like, or DigitalOcean object spaces, or to you name it. 19:29 They've all adopted the API, kind of like OpenAI's API. 19:32 Yeah, I will say it's a little bit awkward that you have to-- 19:35 like, sometimes you go to a cloud provider, and they say, you have to download a SDK 19:40 from a competing cloud provider, and then you can connect to our cloud bucket. 19:44 I know. 19:44 And it's usually Bodo 3. 19:46 And Bodo 3 is-- 19:48 if you want to cry because you're using a library, like, Bodo 3 has a good chance of being the first one 19:53 to make you do it. 19:53 It is so bad for me. 19:55 It's so not custom-- 19:57 It's not built with craft and love. 19:59 It's like auto-generated where you pass these-- 20:02 like, you pass this kind of dictionary, and then the other argument takes a separate dictionary 20:05 that relates back-- it's just like, could you give me a real API here? 20:09 IAN MCKAYAN: I mean, the one thing I can appreciate about Bodo that I do think is honest to mention 20:12 is they do try to just maintain it. 20:15 The backward compatibility of that thing also means it can't move in any direction as well. 20:19 And I can't-- there is this meme where Google kills all 20:22 of its products way too early, and Amazon's meme that they kill them way too late, sometimes never. 20:27 Right? 20:28 So in that sense, I can appreciate that they just try to keep Bodo just not necessarily as user friendly, 20:33 but they do keep it super stable. 20:34 Like, I get there's a balance there. 20:36 Yeah. 20:37 I feel like we still haven't really introduced this cache. 20:39 We've kind of set the stage. 20:41 Anyway, but yeah, SQLite, super cool. 20:44 How does it work under the hood? 20:45 Well, it's really just like a Python dictionary. 20:47 So you can say something like, hey, make a new cache. 20:49 And then you can do things like cache, square brackets, 20:52 string name, equals, and then whatever Python object you like can go in. And Python has this serialization method called a pickle. 21:00 Serialization just means, well, you can persist it to disk in some way, and then you can sort of 21:05 get it back into memory again. And that's what disk cache just uses under the hood. So in theory, 21:10 any Python object that you can think of can go into disk cache. The only sort of thing to be 21:16 mindful of is if you have like Python version, if NumPy version 1 in Python 3.6, and you're going 21:21 to inject a whole lot of that into this cache. 21:24 Don't expect those objects to serialize nicely back 21:26 if you're using Python 3.12 and NumPy version 2 or something. 21:29 Right, because pickle is almost an in-memory representation 21:33 of the thing. 21:34 And that may have evolved over time. 21:36 That's also a true statement about your own classes, potentially. 21:39 Yeah, so if you're dealing with multiple Python versions 21:41 and multiple versions of different packages, there's a little bit of a danger zone to be aware of there. 21:47 That said, for most of the stuff that I do, that's basically a non-issue. 21:50 But I do get this nice little object that can just store stuff into SQLite and can get it out. 21:56 And it's very general. 21:58 It's going to try to be clever about it. 21:59 Like if you give it an int, it's going to actually store it as an int and not use the pickle format. 22:03 So there's a couple of clever things that it can do. 22:06 And it's also really like a Python dictionary. 22:07 So you can do the square bracket thing. 22:09 You can also do the delete and then cache square bracket thing to delete a key from the cache. 22:15 Just like a Python dictionary, you have the get method. 22:17 So you can say dot get key. 22:19 And if it's missing, you can pass a default value. 22:22 So it's very much like a dictionary. 22:25 I think Bob's your uncle on that one. 22:27 Unless, Michael, I've forgotten something. 22:29 But I think that's the simplest way to do it. 22:30 Yeah, pretty much. 22:31 Yeah, I think so. 22:32 The difference being it's not in memory. 22:34 It's stored to a file. 22:36 It happens-- it's not always a SQLite file. 22:39 But often, it is a SQLite file as its core foundation 22:43 that it's stored to. 22:43 So it gives you process restart ability, where it still remembers the stuff you cached. 22:49 It's not like LRU cache. 22:50 We got to redo it every single time. 22:52 And I think, I don't know where it is in the docs here, 22:56 but the thread safety bit of it and the cross-process safety 23:00 is really nice about, is it persistent? 23:03 You've got this whole table here, things like, is it persistent? 23:06 Yes. 23:06 Is it thread safe? 23:07 Yes. 23:07 Is it process safe? 23:08 Yes. 23:10 Compared against other things people might choose. 23:13 And that, honestly, I think that is the other half of the magic. 23:17 Yeah, so especially for your web stuff, I would say that that's the thing you really want. 23:21 And some of that, of course, is just SQLite itself. 23:25 Historically, one reason why people always used to say, like, use Postgres, not SQLite, 23:28 has to do with precisely this concurrency stuff. 23:32 My impression is that SQLite is really good at reading, but writing can be slow if multiple processes do it. 23:37 Some of that, I think, is related to the disk as well. 23:39 I don't know to what extent that has changed. 23:41 But historically, at least, whenever I was doing Django, hanging out at Django events, 23:45 People are always saying, like, just use Postgres because it's better for the web thing. 23:48 But it is safe, the SQLite. 23:51 It might become slower, but it is thread safe if it's-- 23:53 MARK MANDEL: Right. 23:54 There's actually-- they've thought a lot about in this thing 23:58 about transactions, concurrency, and basically dealing with that. 24:02 But it is ultimately, for the most part, still SQLite underneath. 24:07 But the thing with a cache is if you're writing it more 24:10 than you're reading it, you probably shouldn't have a cache. 24:13 Yeah. 24:13 I mean, like... 24:15 That beats the purpose. 24:18 Exactly. 24:18 Like, you get no value if you're recreating it. 24:21 You're only probably just doing overhead and wasting memory or disk space. 24:24 So it's inherently a situation where it's | 2026-01-13T08:49:33 |
https://dev.to/terminusdb/terminators-on-tech-terminusdb-internals-32ij | Terminators on Tech - TerminusDB Internals - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Cheuk Ting Ho 🐍 for TerminusDB Community Posted on Apr 9, 2020 Terminators on Tech - TerminusDB Internals # database # rust # prolog # backend As enthusiastic Terminators, we all want to know how TerminusDB works. We want to know how with Prolog and Rust it works like magic: provide functions like git, allows rollback, branch and merge. In this webinar, we will ask our BDFL Gavin Mendel-Gleason -- creator of TerminusDB, technical and no so technical questions about TemrinusDB internals. Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse TerminusDB Community Follow Join the data-centric revolution! Like This? Give us a sweet sweet GitHub star here: GitHub repo More from TerminusDB Community Building a vector database sidecar for semantic search & entity resolution # vectordatabase # ai # database # showdev Schema Migration for Graph Databases # database # schema # data # news How we built a low-code application for straight-through processing of insurance claims in a week # programming # database # development # backend 💎 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 | 2026-01-13T08:49:33 |
https://docs.devcycle.com/essentials/feature-types | Feature Types | DevCycle Docs Skip to main content Home SDKs APIs Management API Bucketing API Integrations CLI / MCP Best Practices Community Blog Discord Search Sign Up Home Getting Started Essentials DevCycle Overview Key Features System Architecture Feature Hierarchy Feature Types Platform Feature Flags Experimentation Account Management Security and Guardrails Testing and QA Extras Examples Essentials Feature Types On this page Feature Types Feature Types within the DevCycle dashboard are a way of describing and handling Feature Toggles / Feature Flags in more complex and diverse ways. Typically one would use a Feature Flag tool to do extremely simple toggling of a feature to be on or off. In reality, this simple approach can be very limiting as you become more familiar with the concept of Feature Flags. With this in mind, DevCycle prefers to view Feature Toggles as a part of a Feature. A Feature may have one or many toggles, and may have states other than On or Off. A Feature may have something other than a boolean that should be variable across the potential states (or Variations). To help with this concept, when creating a Feature in the DevCycle dashboard, you will be able to choose a Type which will pre-fill some options in the Feature and help kick-start your usage of the Feature. info For more information on Feature Types and using Toggles, read Feature toggles (aka Feature Flags) by Pete Hodgson on the Martin Fowler site. It contains deep information on when to use feature toggles, how to use them, and how to think about them. Much of the DevCycle methodology is based around the concepts in this article. Release Use a Release Feature Flag to separate a feature from deployment and allow for a true continuous delivery (development) cycle. Use these flags to allow for in-progress features and code to be merged into your main branch without concerns. A release could be transitory or long-term in nature depending on your plans with it. If the Feature is completed and deemed not a risk after reaching a complete rollout, the toggle can be safely removed from your code to keep things clean. Example Uses Ship incomplete, untested, or otherwise unready code to production which will not be turned on. Allow product managers to control the release and rollout of a feature on their own schedules. Merge incomplete code into main branches without interfering with testing or the release process. Coordinate a feature release with a marketing campaign so the feature is not released early but not held back by a deploy. Deploy features at the last moment possible. Defaults set in DevCycle When a Feature is created with this type, the following will be pre-set in the Feature: A variable with the chosen type will be created with the Initial Variable Key defined in the Create Feature Modal. This can be considered your "toggle" or "flag". There will be two Variations: Variation ON and Variation OFF. If you select Initial Variable Type as Boolean , the variable will have ON / OFF set to true / false in each Variation accordingly. If you select Initial Variable Type as JSON , the variable values for Variation ON and Variation OFF, will be { “status”:”on”} and { “status”:”off”} respectively. If you select Initial Variable Type as String , the variable values for Variation ON and Variation OFF, are on and off respectively. If you select Initial Variable Type as Number , the variable values for the Variation ON and Variation OFF, are 0 and 1 respectively. For all initial variable types, these are the following Targeting Rule pre-sets: Development and Staging Environments will automatically target "All Users". Rule will be named "All Users" Rules will be set to serve Variation ON. The Development Environment will be enabled immediately. Production Environment will not be enabled and will not have a default rule. Ops When releasing features with unknown performance implications, use an Ops Feature Flag to ensure the safety of your systems during the deployment of the feature. These types of Features may have short-lived toggles (once safety is confirmed remove it), or may remain in the system long-term as there may be reasons to have an emergency kill switch. Example Uses Enable a slow rollout of the feature automatically to allow for monitoring of related systems. Schedule a full release date of a feature once system stability is confirmed. Maintain a persistent kill switch that is easy to hit at any time. Connect this Feature to toggles on other features to all for rollbacks of other related infrastructure when not needed. Defaults set in DevCycle When a Feature is created with this type, the following will be pre-set in the Feature: A variable with the chosen type will be created with the Initial Variable Key defined in the Create Feature Modal. This can be considered your "toggle" or "flag". There will be two Variations: Configuration 1 and Configuration 2. If you select Initial Variable Type as Boolean , the variable values for Configuration 1 & Configuration 2 will be set to true / false in each Variation accordingly. If you select Initial Variable Type as JSON , the variable values for Configuration 1 & Configuration 2 will be set to { “key”:”value”} and { “key”:”value”} in each Variation accordingly. If you select Initial Variable Type as String , the the variable values for Configuration 1 & Configuration 2 will be set to string1 and string2 in each Variation accordingly. If you select Initial Variable Type as Number , the variable values for Configuration 1 & Configuration 2 will be set to 0 and 1 in each Variation accordingly. For all initial variable types, these are the following Targeting Rule pre-sets: Development Environments will automatically target the current user (if email is set). Rule will be set to Variation Configuration 2. Development Environments will be enabled immediately. Production and Staging Environments will not be enabled Experiment Experiments can be used to send users down various paths or provide different functionality of a single feature, either as an A/B test or multivariate testing. Experimentation is extremely useful for making data-driven decisions by monitoring the impacts of various code paths. These types of Features can change quite often and should be modified to continually optimize the results of the Experiment. The Experiment type could be used for many things such as: Example Uses Personalization: Giving users with specific properties specific variations of a Feature Testing Wording on your website or application to drive more engagement or a specific action Setting weights as variables on an Algorithm, using various variations to test tweaks of weights Test multiple landing pages against each other on a website via url split testing Change entire Website or Application flows to reduce drop-offs Modify Ad timing to determine ideal length Defaults set in DevCycle When a Feature is created with this type, the following will be pre-set in the Feature: A variable with the chosen type will be created with the Initial Variable Key defined in the Create Feature Modal. This can be considered your "toggle" or "flag". There will be Three Variations: Control, Variation A, and Variation B. Use Control to represent your applications DEFAULT behaviour so it may be compared against the other variations. If you select Initial Variable Type as Boolean , the variable values for Control, Variation A, and Variation be will be set to false , false , and true respectively. If you select Initial Variable Type as JSON , the variable values for all variations will be { “key”:”value”} . If you select Initial Variable Type as String , the variable values for Control, Variation A, and Variation be will be set to string1 , string2 , and string3 respectively. If you select Initial Variable Type as Number , the variable values for Control, Variation A, and Variation be will be set to 0 , 1 , and 2 respectively. For all initial variable types, these are the following Targeting Rule pre-sets: Development Environments will automatically target ALL users. Audience name will be called "Testing group." Development Environments will be enabled immediately. Distribution will be set to 33% / 33% / 33% between Control, Variation A, and Variation B Production and Staging Environments will not be enabled and will not have a default rule. Permission A Permission Feature is used to manage different product features that are gated based on specific user's properties. These Features can contain many toggles which define subsets of functionality available to users in this feature. These types of Features in DevCycle can be used for many useful things. Example Uses Creating sets of "premium" functions that are OFF for users who are on a free plan. Allowing for beta opt-in for new features and functionality Gating users based on their permission levels within your platform, each piece of functionality behind a toggle, and each variation being a different role. Allowing all internal users to have a set of features far before release. Defaults set in DevCycle When a Feature is created with this type, the following will be pre-set in the Feature: There will be two Variations: Configuration 1 and Configuration 2. If you select Initial Variable Type as Boolean , the variable values for Configuration 1 & Configuration 2 will be set to true / false in each Variation accordingly. If you select Initial Variable Type as JSON , the variable values for Configuration 1 & Configuration 2 will be set to { “key”:”value”} and { “key”:”value”} in each Variation accordingly. If you select Initial Variable Type as String , the the variable values for Configuration 1 & Configuration 2 will be set to string1 and string2 in each Variation accordingly. If you select Initial Variable Type as Number , the variable values for Configuration 1 & Configuration 2 will be set to 0 and 1 in each Variation accordingly. For all initial variable types, these are the following Targeting Rule pre-sets: Development, Staging, and Production Environments will automatically target your organization's Email. Rule will be named "Internal Users" Rules will be set to serve Variation ON. Development and Staging Environments will be enabled immediately. Edit this page Last updated on Jan 9, 2026 Previous Feature Hierarchy Next Features Release Ops Experiment Permission DevCycle Dashboard Blog Privacy Policy Twitter Discord GitHub Copyright © 2026 DevCycle. All rights reserved. | 2026-01-13T08:49:33 |
https://dev.to/lingarao_yechuri_2f59259c/navigating-long-ai-chats-is-broken-so-i-built-a-chrome-extension-to-fix-it-54j#how-it-works | Navigating Long AI Chats Is Broken — So I Built a Chrome Extension to Fix It - 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 Add reaction Like Unicorn Exploding Head Raised Hands Fire Jump to Comments Save Boost More... Copy link Copy link Copied to Clipboard Share to X Share to LinkedIn Share to Facebook Share to Mastodon Share Post via... Report Abuse Lingarao Yechuri Posted on Jan 12 Navigating Long AI Chats Is Broken — So I Built a Chrome Extension to Fix It # chatgpt # gemini # productivity # ux If you regularly use ChatGPT, Claude, or Gemini, you’ve probably faced this problem 👇 You had an amazing response 50 messages ago , but now: Endless scrolling Cmd/Ctrl + F doesn’t help much Context is lost Gemini loads history lazily, making it even worse Long AI conversations quickly become unusable once they grow past a certain point. The Problem AI chats are great for: Debugging complex issues Research and learning Long brainstorming sessions Iterative prompt refinement But current chat UIs are not designed for long-term navigation . Common issues: No structured overview of prompts Hard to jump between questions Re-finding past answers is painful Each platform handles history differently (especially Gemini) As conversations grow, signal gets buried under noise . The Solution: Prompt Navigation for AI Chats I built a Chrome extension that adds prompt-level navigation to AI chat platforms. Instead of scrolling endlessly, you get: A structured list of prompts One-click jump to any question Faster navigation across long chats A consistent experience across ChatGPT, Claude, and Gemini Think of it as a table of contents for your AI conversation . How It Works The extension: Detects user prompts in the current chat Builds a navigable list in a side panel Lets you instantly jump to any prompt-response pair Works entirely on the client side (no backend, no data leaving your browser) Gemini-specific note Gemini loads older messages dynamically as you scroll. Because of this, the extension can only index the currently loaded prompts . Once you click an older prompt, Gemini loads more history, and the list updates progressively. This is a platform limitation — not a data or permission issue. Use Cases This extension is especially useful if you: Debug long coding sessions Revisit research-heavy conversations Refine prompts over multiple iterations Use AI as a learning or thinking partner Switch between multiple AI platforms daily Instead of restarting chats or copy-pasting summaries, you can navigate and reuse context efficiently . Why I Built This Many people suggest: “Just ask the LLM to summarize and start a new chat.” That works — but it breaks flow. I wanted: Zero disruption No re-prompting No backend APIs A simple UX improvement that should’ve existed by default So I built it. What’s Next I’m actively improving it based on feedback: Better prompt grouping Cross-chat reuse ideas Performance improvements for very long sessions If you spend hours inside AI chats, this extension is meant for you. here is the extension Feedback and suggestions are welcome 👋 Top comments (0) Subscribe Personal Trusted User Create template Templates let you quickly answer FAQs or store snippets for re-use. Submit Preview Dismiss Code of Conduct • Report abuse Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink . Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Lingarao Yechuri Follow I am Web developer Joined Dec 18, 2025 Trending on DEV Community Hot If a problem can be solved without AI, does AI actually make it better? # ai # architecture # discuss Stop Overengineering: How to Write Clean Code That Actually Ships 🚀 # discuss # javascript # programming # webdev When is a side project worth committing to? # ai # gemini # sideprojects # showdev 💎 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 | 2026-01-13T08:49:33 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.