The idea: give an AI agent a small but real LLM training setup and let it experiment autonomously overnight. It modifies the code, trains for 5 minutes, checks if the result improved, keeps or discards, and repeats. You wake up in the morning to a log of experiments and (hopefully) a better model. The training code here is a simplified single-GPU implementation of nanochat. The core idea is that you're not touching any of the Python files like you normally would as a researcher. Instead, you are programming the program.md Markdown files that provide context to the AI agents and set up your autonomous research org. The default program.md in this repo is intentionally kept as a bare bones baseline, though it's obvious how one would iterate on it over time to find the "research org code" that achieves the fastest research progress, how you'd add more agents to the mix, etc. A bit more context on this project is here in this tweet.
当AI开始发展自己的语言和文化，我们面对的已经不只是工具，而是一种正在萌芽的数字文明。
，详情可参考PDF资料
Ранее сообщалось, что Россия и Китай выступили в пользу реформы ООН. По словам российского президента Владимира Путина, в Совет Безопасности ООН необходимо включить представителей государств Азии, Африки и Латинской Америки.
Врач посоветовала некоторым людям с осторожностью есть помидоры17:33
。业内人士推荐新收录的资料作为进阶阅读
Медведев вышел в финал турнира в Дубае17:59，这一点在新收录的资料中也有详细论述
Loading of code