An interactive Street Fighter 3 demo against an RL-trained LLM in a sandboxed game engine.

Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs

Evaluate and improve models and agents using environments

A library for mechanistic interpretability of GPT-style language models

prime is a framework for efficient, globally distributed training of AI models over the internet.

The Company AI Command Center

Mechanistic Interpretability on Reasoning using Gemma-Scope for BlueDot Impact Course.

AI Crash Course to help busy builders catch up to the public frontier of AI research in 2 weeks

A script that helps generate a rich GitHub Contribution Graph for your account 🤖

The Abstraction and Reasoning Corpus

A list of open-source, affordable, less-known, or visionary robotics projects.