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.
asks about the numbers on June 27,
В США забеспокоились из-за передачи Россией Ирану разведданных14:07。业内人士推荐新收录的资料作为进阶阅读
The Track Radio Corporation is understood to have been granted a licence by Ofcom last week, with Goldsmith and his brother Ben, a financier and environmentalist, the major investors.
。业内人士推荐新收录的资料作为进阶阅读
Раскрыты подробности похищения ребенка в Смоленске09:27
Уточняется, что в общей сложности могло быть эвакуировано 150 человек, включая семьи дипломатических работников. Причиной решения покинуть ближневосточную страну называются угрозы со стороны Израиля.，更多细节参见新收录的资料