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.
That's a huge step up from VisiCalc's "all or nothing" approach to cell references. Put in a formula and copy it through to other cells. For every cell reference, in every copy of the formula, VisiCalc prompts the user for "relative or fixed?" It is a complete drag, and Woz help you the day that formula needs updating.，这一点在新收录的资料中也有详细论述
https://www.wired.com/story/openai-president-greg-brockman-political-donations-trump-humanity/。新收录的资料是该领域的重要参考
say_hi(); // hiCapturing Variables。新收录的资料对此有专业解读
美国电动汽车寒冬，Lucid 裁员 12%