OpenAI将把伦敦打造成其美国以外最大的研究中心
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:
，推荐阅读下载安装 谷歌浏览器 开启极速安全的 上网之旅。获取更多信息
Temperatures fell to freezing, food and water were rationed. It was days before they limped back to the fringes of Earth's atmosphere. They climbed back aboard the Odyssey and prayed the heat shield had not been damaged.
「語言的一個有趣特點是，某種語言中 70% 的內容，其實是由幾百個常用詞組成的，」莫納漢說。「但真正難以在短時間達成的，是聽懂別人回你什麼，因為他們會不時使用那些較少見的詞彙。」