Autoresearch on an old research idea(ykumar.me)
408 points by ykumards | 90 comments
Blog post describing running Karpathy's Autoresearch with Claude Code on the author's old eClip research codebase to see what an AI agent could improve.
#karpathy on Hacker News
7 stories tagged karpathy, newest first.
US Job Market Visualizer(karpathy.ai)
425 points by andygcook | 318 comments
Interactive treemap visualizing 342 BLS occupations covering 143M US jobs, colored by outlook, pay, education, or LLM-scored AI exposure.
Microgpt(karpathy.github.io)
1807 points by tambourine_man | 302 comments
Andrej Karpathy's blog post introducing microgpt, a dependency-free 200-line Python file that trains and runs inference on a GPT.
Reproducing GPT-2 in llm.c(github.com)
578 points by tosh | 109 comments
A GitHub discussion in Andrej Karpathy's llm.c repository about reproducing GPT-2 training from scratch in C/CUDA.
Llm.c – LLM training in simple, pure C/CUDA(github.com)
810 points by tosh | 134 comments
GitHub repository for llm.c, Andrej Karpathy's project for training LLMs like GPT-2 in simple, raw C/CUDA.
Beyond self-attention: How a small language model predicts the next token(shyam.blog)
411 points by tplrbv | 72 comments
A long blog post analyzing how a small ~10M parameter transformer trained from Karpathy's tutorial turns attention outputs into next-token predictions.
Llama2.c: Inference llama 2 in one file of pure C(github.com)
659 points by anjneymidha | 158 comments
GitHub repository by Andrej Karpathy for llama2.c, a minimal implementation for running Llama 2 model inference in a single file of pure C.