yminsky 谈如何为智能体改造代码库
so many gems and great tips in this talk from @yminsky about how to improve your codebase for agents
lauren 分享了 yminsky 关于如何为 AI 智能体改进代码库的演讲要点：类型是最佳反馈来源之一，用类型让非法状态不可表示可在全代码库强制全局规则；此外还有基于属性的测试、fuzzing、全系统确定性模拟测试和 expect tests。演讲提到形式化方法过去成本极高，seL4 约 8,700 行 C 代码耗时约 25 人年、每行 C 代码对应 23 行证明，但智能体改变了投入产出比。
正文
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
https://t.co/0zDb5euxhr