В нескольких микрорайонах Киева пропал свет14:16
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.
。新收录的资料对此有专业解读
The PRO X Superlight 2 builds on Logitech’s already popular Superlight formula with a 60-gram design, Lightforce hybrid switches, and the HERO 2 sensor. According to the specs, this mouse’s sensor can hit up to 44,000 DPI and track at over 888 IPS — built for competitive-level responsiveness and minimal drag.。新收录的资料是该领域的重要参考
会话状态、项目目录、历史等可持久化（如 SQLite），支持迁移与审计
Free plan Features