优化：随机选基准避免最坏情况 O(n²)
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:
。服务器推荐是该领域的重要参考
今年春節前，海外留學歸來的高先生推開家門，看到的景象讓他愣在原地：母親一手握着手機，在窗台前的水晶堆裏挑挑揀揀。從大到小的水晶擺件佔滿整個窗台，都是母親幾個月來從直播間「淘」回來的。更讓他擔憂的是，母親肩頸疼痛已嚴重到走路、站立都成問題，總是佝僂着背。。下载安装 谷歌浏览器 开启极速安全的 上网之旅。是该领域的重要参考
From hospitality workers to retail employees, the exaggerated “customer service voice”, often mocked in internet memes as wildly different from someone’s real voice, has long been a cultural trope. Fast-food giant Burger King is now taking that voice one step further, saying it will detect whether employees are using words like “please” and “thank you” through the assistance of artificial intelligence.，推荐阅读Safew下载获取更多信息