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.
people overlook in favor of Magit. I'm not saying it replaces Magit
，更多细节参见新收录的资料
Last year, Ford set a new industry record: It issued 152 safety recalls, almost twice the previous high set by General Motors back in 2014. More than 24 million vehicles were recalled in the US last year, and more than half—13 million—were either Fords or Lincolns. By contrast, Tesla issued 11 recalls, affecting just 745,000 vehicles.
专利诉讼和刑事案件的叠加，也使得海辰储能的法律风险逐渐升级。2025年7月，公司总裁办主任冯登科因涉嫌侵犯商业秘密，被警方依法采取强制措施，这一事件无疑加剧了市场对其资本化进程的担忧。