Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

None defined yet.
MUK-IS-GOATΒ 
posted an update about 2 months ago
view post
Post
146
SmilyAI-Labs is happy to say that our new AI called Mira is launched. Mira is the curious, honest companion built to help you learn, not impress you β€” she'll debug your code, explain her reasoning, and politely roast broken lines before fixing them. Her personality isn't a gimmick: it's an engineering choice that makes her more usable, not less. Competing models can't be honest without sounding untrustworthy; Mira has the cover story that makes honesty a feature, not a liability. She's the upgrade you already love, and the lab is excited to meet you.' To see the wonders of Mira, go to hugging-science/chat-with-mira
  • 1 reply
Β·
MUK-IS-GOATΒ 
posted an update about 2 months ago
stephenb1334Β 
in lora-library/inme 4 months ago

Add application file
#1 opened 4 months ago by
stephenb1334
pandeypsΒ 
authored a paper 6 months ago
mindchainΒ 
posted an update 9 months ago
view post
Post
3319
Claude Code Self & Continual Learning

Hey everyone! πŸ‘‹

30 GitHub Stars in 4 Days - Thank You!

I'm really grateful for the positive response to the Claude Reflect System. In just 4 days, 30 developers have shown interest by starring the project. Thank you so much!

What Is Claude Reflect?

Correct once, never again. Claude Reflect helps Claude Code remember your corrections and preferences across sessions. Instead of repeating the same feedback, the system learns and applies it automatically.

Main Features:

🧠 Learning System
- Detects corrections and preferences from conversations
- Stores them permanently in skill files
- Applies learnings in future sessions

πŸ”’ Safety First
- Automatic backups before changes
- YAML validation
- Git version control

⚑ Two Modes
- Manual: Run /reflect when you want
- Auto: Reflects automatically at session end

How It Works

If you correct Claude to use pytest instead of unittest, this preference gets saved. Next time, Claude will remember and use pytest automatically. It's that simple.

Getting Started

1. Clone the repository
2. Install dependencies
3. Activate the skill
4. Try it out!

The python-project-creator example shows how the system learns from your feedback.

Give It a Try

https://github.com/haddock-development/claude-reflect-system

Feel free to check it out, give feedback, or contribute. Every bit of input helps improve the project!

Thank you so much for your support!

---
#ClaudeCode #AI #MachineLearning #ContinualLearning #OpenSource #Developer #Coding #Python #Productivity #DevTools #GitHub #SoftwareDevelopment #Programming #AIAssistant #DeveloperTools #CodeQuality #Tech



Feel free to give it a try by yourself.
https://github.com/haddock-development/claude-reflect-system
  • 2 replies
Β·
mindchainΒ 
posted an update 9 months ago
view post
Post
2109
Scaling Physical AI: SAM 3D, NVIDIA Cosmos, and Unreal Engine!

The "Sim-to-Real" gap is officially history. In early 2026, we are no longer just rendering data; we are simulating reality. By bridging Meta’s SAM 3D, Unreal Engine, and the NVIDIA Cosmos suite, we’ve built an autonomous pipeline for Physical AI that evolves itself.

The 2026 Tech Stack:
SAM 3D: Generates high-fidelity digital twins from 2D photos in seconds.

Unreal Engine + MCP: The AI "Director" orchestrates environments via the Model Context Protocol, providing perfect Ground Truth.

NeMo Data Designer: The orchestration hub on GitHub. Following NVIDIA’s acquisition of Gretel in early 2025, its leading generative privacy and tabular tech are now fully integrated here.

NVIDIA Cosmos Transfer: Neural rendering that adds hyper-realism to Unreal Engine outputs.

NVIDIA Cosmos Predict: Predicts physically accurate motion (falling, sliding) without manual animation.

NVIDIA Cosmos Reason: The automated supervisor checking every frame for logical and physical consistency.

The Workflow:
Asset Capture: SAM 3D turns real-world photos into Nanite meshes for Unreal Engine.

Orchestration: NeMo Data Designer (with Gretel-powered integrity) defines the data schema, while AI builds the world in Unreal Engine.

Completion: NVIDIA Cosmos (Transfer & Predict) adds photorealism and physics, while NVIDIA Cosmos Reason guarantees quality.

By combining Gretel’s data heritage with the visual power of Unreal Engine, we generate 100,000 perfect frames per hour. Weights and tools are on Hugging Face. Stop labeling. Start simulating.

#PhysicalAI #SAM3D #NVIDIACosmos #UnrealEngine #NeMo #Gretel #SyntheticData #HuggingFace #Robotics #AI #ComputerVision
mindchainΒ 
posted an update 9 months ago
view post
Post
2067
Skill Reflect: A Concept for Automated AI Skill Mastery

Let’s be real for a second: most of us are using AI all wrong. We send a prompt, get a "meh" answer, and then spend twenty minutes fixing it ourselves. That’s not a workflow; that’s just a digital chore. I wanted to see if I could push Claude furtherβ€”to see if I could build a system that actually learns and refines itself. That’s how the Claude-Reflect-System (Skill Reflect) was born.

But here’s the thing: this isn’t some polished, final product. It’s a concept. It’s a blueprint. I’ve built the foundation of a recursive reflection loop that forces the AI to step back, look at its work, and act as its own harshest critic. It identifies the "skill delta"β€”the gap between "okay" and "mastery"β€”and closes it. This logic isn't just for Claude; you can grab this architecture and drop it right into codex-cli, terminal agents, or whatever stack you're building.

I’m a big believer in the law of causality. Action, reaction. Cause and effect. If you control the causeβ€”the way the AI thinks about its mistakesβ€”you dictate the effect: a perfected skill. This is a playground for builders who are tired of stochastic guessing. I want you to take this. Fork it. Break it. Make it better. This is an open invitation to the community to take this reflection loop and see how far we can push the boundaries of agentic reasoning. Whether you're building Claude Code plugins or just want to automate your self-learning, the code is there for you to smash. Stop accepting the first draft. Let’s build something that actually thinks.

https://github.com/haddock-development/claude-reflect-system

#Skills #ClaudeCode #ClaudeCodeSkills #ClaudeCodePlugins #ClaudeCodeMarketplace #CodexCLI #AI #SelfLearning #Automation #OpenSource #LLM #Reasoning #Causality #Matrix #Concept
mindchainΒ 
posted an update 9 months ago
view post
Post
1859
Neural Traffic Control: Orchestrating Multi-Path Reasoning πŸš₯
The future of AI isn't just about "better" modelsβ€”it’s about high-precision orchestration. We are moving from linear processing to Parallel MTP-Reasoning, where we manage neural traffic across stabilized, transparent, and recursive highways.

1️⃣ The Backbone: Stabilized High-Dimensional Routing (arXiv:2512.24880) Using DeepSeek’s mHC (Manifold-Constrained Hyper-Connections), we solve the instability of deep MoE architectures. By projecting weight updates onto the Birkhoff Polytope, we ensure that our "Simpsons-style" expert lanes maintain mathematical identity. This is the hardware-level stability needed to run multiple reasoning paths without collapse.

2️⃣ The Vision: Gemma Scope 2 & Feature Steering You can't steer what you can't see. Gemma Scope 2 provides the "X-ray" for our highways. By using Sparse Autoencoders (SAEs), our Meta-Controller identifies the active features in each expert lane. We don't just route data; we route intent by monitoring feature-drift in real-time.

3️⃣ The Logic: Recursive Open Meta-Agents (arXiv:2512.24601) We integrate the ROMA (Recursive Open Meta-Agent) framework. Instead of a flat response, the model operates in a recursive loop, refining its internal state before any output occurs. This is the "brain" of our [Meta-Controller GitHub Repo], enabling the model to simulate and discard weak logic internally.

4️⃣ The Simulation: Parallel MTP-Reasoning This is where it comes together: Multi-Token Prediction (MTP) meets Parallel Simulation. Our Python-driven controller runs three parallel Gemma 3 instances.

The Process: 3 paths generated simultaneously.

The Filter: A 500-token lookahead window.

The Decision: The Meta-Controller uses SAE-data from Gemma Scope to select the path with the highest logical fidelity.

The Result: A self-correcting, transparent, and multi-threaded reasoning engine. We aren't just scaling parameters; we are scaling architectural precision. 🧠
mindchainΒ 
posted an update 9 months ago
view post
Post
3688
The Architecture of 2026: Beyond the Token Trap πŸš€

We are witnessing a tectonic shift in Transformer architecture. It’s no longer just about "predicting the next token"β€”it’s about executing latent plans on a high-speed data highway.

What happens when we combine DeepSeek’s stability with Google’s strategic intelligence?

1️⃣ The Infrastructure: DeepSeek’s mHC Moving from a single-lane residual stream to a multi-lane highway. Using the Birkhoff Polytope, mHC ensures mathematical stability (Identity Mapping) while routing specialized data through dedicated lanes.

2️⃣ The Intelligence: Google’s Meta-Controller An internal AI unit that lives inside the Transformer. It escapes the "Token Trap" by extracting data to create a latent plan, steering the model via Temporal Abstraction.

The Synergy: In a Topological Transformer, the Meta-Controller finally has the "dedicated lanes" it needs to steer complex reasoning without causing gradient explosions.

We aren't just making models bigger; we are making them architecturally smarter. 🧠

#MachineLearning #DeepSeek #GoogleAI #Transformer #AIArchitecture
chenheguΒ 
authored 3 papers 9 months ago
hesamationΒ 
posted an update 10 months ago
view post
Post
5881
this is big... 50 AI researchers from Bytedance, Alibaba, Tencent, and other labs/universities just published a 300-page paper with surprising lessons about coding models and agents (data, pre and post-training, etc).

key highlights:

> small LLMs can beat proprietary giants
RL (RLVR specifically) gives small open-source models an edge over big models in reasoning. a 14B model trained with RLVR on high-quality verified problems can match the performance of OpenAI's o3.

> models have a hard time learning Python.
mixing language models during pre-training is good, but Python behaves different from statically typed languages. languages with similar syntax (Java and C#, or JavaScript and TypeScript) creates high positive synergy. mixing Python heavily into the training of statically typed languages can actually hurt because of Python's dynamic typing.

> not all languages are equal (coding scaling laws)
the amount of data required to specialize a model on a language drastically depends on the language. paper argues like C# and Java are easier to learn (less training data required). languages like Python and Javascript are actually more tricky to learn, ironically (you see AI most used for these languages :)

> MoE vs Dense (ability vs stability)
MoE models offer higher capacity, but are much more fragile during SFT than dense models. hyperparams in training have a more drastic effect in MoE models, while dense models are more stable. MoE models also require constant learning rate schedules to avoid routing instability.

> code models are "insecure" by default (duh)
training on public repos makes models learn years of accumulated insecure coding patterns. safety fine-tuning often fails to work much on code. a model might refuse to write a hate speech email but will happily generate a SQL-injection vulnerable function because it "works."

read the full paper:
From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence (2511.18538)
  • 1 reply
Β·
longchenΒ 
authored 4 papers 11 months ago
yuna0x0Β 
authored a paper about 1 year ago
ehristoforuΒ 
posted an update about 1 year ago
view post
Post
2796
πŸš€Hello from the Project Fluently team!

✨ We are happy to share with you our new universal LLM models based on Qwen3 1.7B and 4B β€” powerful, multilingual and ready to solve a wide range of problems!

πŸ› οΈ We have conducted additional training and carefully merged them to achieve even better results and maximize the potential of the models.

πŸ†“ And most importantly β€” the models are completely open and free under the Apache-2.0 license!

πŸ”— Links to repositories:
- FluentlyQwen3-4B: fluently/FluentlyQwen3-4B
- FluentlyQwen3-1.7B: fluently/FluentlyQwen3-1.7B

😍 We will be very glad to hear your feedback and impressions! Your opinion is very important to us!
hesamationΒ 
posted an update about 1 year ago
view post
Post
15037
a senior engineer at google just dropped a 400-page free book on docs for review: agentic design patterns.

the table of contents looks like everything you need to know about agents + code:
> advanced prompt techniques
> multi-agent patterns
> tool use and MCP
> you name it

read it here: https://docs.google.com/document/d/1rsaK53T3Lg5KoGwvf8ukOUvbELRtH-V0LnOIFDxBryE/edit?tab=t.0#heading=h.pxcur8v2qagu

you can also pre-order on Amazon (published by Springer) and the royalties goes to Save the Children: https://www.amazon.com/Agentic-Design-Patterns-Hands-Intelligent/dp/3032014018/