“You doing O.K.?” Swenson shouted, after a while. “The more you’re talking, the better I know you’re doing.” I tried to say I was fine, but it came out funny—a high, choked-off sound. I waited a moment, then covered for it by asking what he did for a living before he retired. He laughed. “I worked for Northwestern Mutual in Boulder,” he said. “I sold life insurance.”
We’ll build that in the next post. First, we need to learn about CRDTs!
。关于这个话题，爱思助手下载最新版本提供了深入分析
Kindle (16GB) + Kindle Unlimited (3 Months)
常用于： 深层 CNN、MLP。
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: