Chirag Taneja
hey! i am a final year robotics and ai major. i like to tinker with large language models, deep learning architectures and agentic systems.
hey! i am a final year robotics and ai major. i like to tinker with large language models, deep learning architectures and agentic systems.
A simulated Unitree G1 humanoid learns the opening of "Runaway" with reinforcement learning: 43 of 44 notes on time.
124M parameters, pretrained on 9.99B FineWeb-Edu tokens.
Local Python execution, made inspectable: what happens between a command and its result.
Teaching Qwen3-8B to paint watercolours with code: 20 RL updates took valid paintings from 10 to 23 of 24.
Twelve ML papers implemented from scratch, from an autograd engine to a diffusion pipeline: the equation, the code, the result.
Practice high-stakes conversations with an AI or live with other people, then review a debrief tied to your own words.
No-limit hold'em from first principles: Socratic lessons, animated explainers, and timed practice drills.
Supervisor-worker agents that turn a vague question into a sourced report.
Routes between chat, retrieval, and sandboxed code, and asks before it acts.
revamped the whole site
oct 19