rauchg：Agent 会无限打磨代码，工程师仍需决定何时停止
rauchg 提醒一个很实在的问题：Agent 会无限优化代码，哪怕那段代码根本没人用，知道何时收手还是人的活儿。
Guillermo Rauch 在 X 上发文指出，任何程序都可以被持续加固和优化，比如压缩边界情况、收紧输入、做 profile 和 benchmark，但每一项都有时间、注意力和机会成本。在无限 token 的世界里，Agent 会不管有没有用户都持续钻深。他强调工程师仍需自己判断何时停止、接受哪些权衡。
One thing the engineering community will (re)discover is that every program can be ① hardened (edge cases squashed, inputs tightened, errors handled) and ② optimized (profiled, benchmarked, rewritten) basically ad infinitum. There are real costs in every direction: time, attention, opportunity. You can literally explore input spaces that will never be hit or optimize performance of something that will never be used ("you have no users".) Even in an infinite token world, you need to know when to stop and what tradeoffs to accept. Agents will happily drill no matter what. 💬 36 🔄 17 ❤️ 183 👀 8566 📊 57 ⚡
