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.
Written and directed by Dave Boyle, this haunted house story centers on a pair of sisters who can commune with ghosts. Together, they traverse Japan, making a living by helping the dead pass on. There's just one catch: One sister is a ghost herself, only seen by her sibling Airi (Moeka Hoshi) in reflections. Yet even their powers combined might not be enough for their latest challenge — a long-empty hotel where a jawless ghost is stalking the new owner.。搜狗输入法对此有专业解读
Middle East live blog – latest updates，更多细节参见谷歌
# The Z80 experiment