karpathy/autoresearch: AI agents running research on single-GPU nanochat training automatically ·
github.com · 1,189 words · saved by 6 readers
AI agents running research on single-GPU nanochat training automatically
One day, frontier AI research used to be done by meat computers in between eating, sleeping, having other fun, and synchronizing once in a while using sound wave interconnect in the ritual of "group meeting". That era is long gone. Research is now entirely the domain of autonomous swarms of AI agents running across compute cluster megastructures in the skies. The agents claim that we are now in the 10,205th generation of the code base, in any case no one could tell if that's right or wrong as the "code" is now a self-modifying binary that has grown beyond human comprehension. This repo is…
saved by
related reading
- GitHub - karpathy/nanochat: The best ChatGPT that $100 can buy.github.com
- microgptkarpathy.github.io
- Automated Weak-to-Strong Researcheralignment.anthropic.com
- GitHub - karpathy/nanoGPT: The simplest, fastest repository for training/finetuning medium-sized GPTs. · GitHubgithub.com
- Training a Specialist Code Search Agent with turbopufferappliedcompute.com
- Let's build GPT: from scratch, in code, spelled out.youtube.com
- Towards self-driving codebases · Cursorcursor.com
- Autoresearch Is Not About Training Models. It Is About What Happens When Agents Get a Scoreboard | by Krish | AI Sutraaisutra.com
- Evidence on AI R&D Progress from NanoGPT - METRmetr.org
- [Jan 7 2026] nanochat miniseries v1 · karpathy nanochat · Discussion #420github.com
- Introducing nanocode: The best Claude Code that $200 can buy. · salmanmohammadi nanocode · Discussion #1github.com
- GitHub - rasbt/LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by stepgithub.com