Introducing Trackio A Lightweight Experiment Tracking Library from Hugging Face uv pip install trackio
CODE
-
Zero-Cost Model Serving: SFT vs RLHF Strategy
By
–
hypothetical situation – i am an AI company that's reduced the cost of transferring and storing models to zero. i can serve each user their own model with no overhead what do i do? directly SFT user-specific models on their data? or RLHF on the chat ratings? something else?
-
Self-Correcting RAG Agent for Automated Code Generation
By
–
LangGraph: Building a Self-Correcting RAG Agent for Code Generation Ready to level up your AI workflows? In our latest #LangGraph post, we built a self-correcting RAG agent that writes Python code with Hugging Face Diffusers, runs it, learns from errors, and iterates until
-
Space Invaders Clone Generated by 3-Bit MLX GLM-4.5 Air
By
–
Here's the Space Invaders clone my 2.5 year old laptop wrote itself using 3 bit MLX GLM-4.5 Air, from the single prompt "Write an HTML and JavaScript page implementing space invaders" https://t.co/DVDLcLnoTI pic.twitter.com/53ildnkObA
— Simon Willison (@simonw) 29 juillet 2025Here's the Space Invaders clone my 2.5 year old laptop wrote itself using 3 bit MLX GLM-4.5 Air, from the single prompt "Write an HTML and JavaScript page implementing space invaders" https://
tools.simonwillison.net/space-invaders
-GLM-4.5-Air-3bit
… -
MLX Builds for GLM-4.5 Air 3bit Quantization
By
–
Great work @ivanfioravanti on the MLX builds of GLM-4.5 Air – I used the 3bit one for this
-
Build a GPT-like Large Language Model from Scratch
By
–
Build a Large Language Model from scratch! This repository contains the code for developing, pretraining, and finetuning a GPT-like large language model. 100% Free & Open Source
-
Claude Uses ULMFiT Tokenization Technique from 2017
By
–
According to this research it sounds like Claude uses the same tokenization trick I invented for ULMFiT in 2017! 😀
-
ChatGPT Reaches Final in Elite Programming Competition
By
–
ChatGPT a surpassé presque tous les programmeurs d’élite (un seul a résisté). (C'est l'élu, il représente l'humanité ) Dans une compétition centrée sur les algorithmes d’optimisation, le modèle d’OpenAI a atteint la finale le 16 juillet, a pris la tête… avant d’être dépassé
-
Anthropic Implements Weekly Rate Limits for Claude Pro Users
By
–
Anthropic will add weekly rate limits for Pro and Max users due to “unprecedented demand” from Claude Code, saying the move will hit under 5% of current users.
— The Rundown AI (@TheRundownAI) 29 juillet 2025
The company also said Claude can now read and update Notion pages and Linear tickets via MCPpic.twitter.com/Ry580cK2TkAnthropic will add weekly rate limits for Pro and Max users due to “unprecedented demand” from Claude Code, saying the move will hit under 5% of current users. The company also said Claude can now read and update Notion pages and Linear tickets via MCP
-
GLM-4.5: Advanced AI Model for Reasoning and Coding
By
–
Explore the cutting-edge capabilities of http://
Z.ai’s GLM-4.5, a state-of-the-art AI model designed for advanced reasoning and efficient coding. Access detailed documentation and models here -> https://
shorturl.at/GKKHS Follow us @futurepedia_io for fresh AI tools