lauren· @poteto · X·· 3 小时前AI 评分63
AI 导读
Yaron Minsky 在演讲中分享了改进代码库以适配 AI 智能体的多个要点，指出智能体非常依赖反馈，而类型系统是最好的反馈机制之一。演讲提到的要点还包括利用类型让非法状态无法被表示、使用基于属性的测试与模糊测试、采用期望测试使行为清晰可读，以及探讨智能体如何改变形式化方法的投入产出比。
正文 · 原文
so many gems and great tips in this talk from @yminsky about how to improve your codebase for agents
- agents thrive on feedback, and types are one of the best kinds
- make illegal states unrepresentable with types, and it enforces global rules across your codebase
- property based tests, fuzzing, and even full-system deterministic simulation testing
- expect tests: just print stuff out and capture it in the test. makes behavior legible. it's very similar to how compilers have fixture tests, it reduces the review surface area
- formal methods used to be very expensive: seL4 is about 8,700 lines of C and took around 25 person-years, with 23 lines of proof for every line of C code, but agents change the roi
来源：lauren · x.com