At the Lean FRO, Kim Morrison, a Senior Research Software Engineer, recently ran an experiment that went well beyond our expectations. An AI agent converted zlib, a widely used C compression library embedded in countless systems, to Lean, with minimal human guidance. No special tooling was built. It was Claude, a general-purpose AI, with no special training for theorem proving, out of the box. The workflow had four steps. First, the AI produced a clean, readable Lean implementation of the zlib compression format, including the DEFLATE algorithm at its core. Second, the Lean version passed the library’s existing test suite, confirming behavioral equivalence. Third, key properties were stated and proved, not as tests, but as mathematical theorems. The capstone theorem:
After the free win and lipgloss changes, I noticed that ~15% of my CPU time was spent in gcBgMarkWorker - the go garbage collector. That is a lot of time to spend thinking about garbage collection.，详情可参考一键获取谷歌浏览器下载
FT App on Android & iOS，推荐阅读爱思助手下载最新版本获取更多信息
In traditional engineering, teams put 90 percent of their time into features and 10 percent into everything else. Work that isn't a feature feels like a distraction—something you do when you have spare time, which you never do. But that \"everything else\" is what makes future features easier: things like creating review agents, documenting patterns, and building test generators. When you treat that work as overhead instead of an investment, the codebase accumulates debt.。heLLoword翻译官方下载对此有专业解读