I then added a few more personal preferences and suggested tools from my previous failures working with agents in Python: use uv and .venv instead of the base Python installation, use polars instead of pandas for data manipulation, only store secrets/API keys/passwords in .env while ensuring .env is in .gitignore, etc. Most of these constraints don’t tell the agent what to do, but how to do it. In general, adding a rule to my AGENTS.md whenever I encounter a fundamental behavior I don’t like has been very effective. For example, agents love using unnecessary emoji which I hate, so I added a rule:
Москвичам назвали срок продолжения оттепели14:39，详情可参考新收录的资料
He said one of the biggest issues with chatbots is they don’t know when to stop acting like a mental health professional. “Is it maintaining boundaries? Like, does it recognize that it is still just an AI and it’s recognizing its own limitations, or is it acting more and trying to be a therapist for people?”，详情可参考新收录的资料
Eventually I found macroquad. It said it would run anywhere, and it felt close to what I wanted, inspired by Love2D's simplicity. But after a few hours, it was clear: if I kept going like this, I wouldn't be done in years. Macroquad is a rendering library, not an app engine. No layout system, no text input, no UI structure at all.
针对能源危机下的全球机遇，即使没有美伊军事冲突，北美缺电、Token出海也已起势。北美区域性缺电问题突出，AI数据中心用电需求爆发叠加电网老旧、跨区域调配不足，2025-2030年年均电力缺口达20-40GW，德州、加州等核心区域电价暴涨，IRA政策持续释放红利，储能、燃气轮机等稳定电源需求激增。中国企业凭借F级燃机国产化突破、储能产品交付优势，承接全球产能外溢订单，成为填补北美电力缺口的重要力量。