Trending storyPast story
Prompting agents to iteratively optimize Rust until it beats state-of-the-art libraries
1 report1 sourceupdated 7 days ago
What happened
Summary
Max Woolf 用了一年多时间验证一件事：给 AI 代理定一条硬规矩——每次改代码必须至少提速 5%，否则回滚——然后让它自己去迭代优化 Rust。从 Claude Opus 4.5 开始，这套玩法在 UMAP 等算法上拿到了 2 到 20 倍的加速，对比的是已经打磨多年的成熟库，而且全程没碰 unsafe 代码。文章把提示词和基准测试结果都贴出来...
Coverage
Follow the reports to see the story from different sides.
Sep 22
- Hacker News front pagePickPrompting agents to iteratively optimize Rust until it beats state-of-the-art libraries
Max Woolf spent over a year testing whether agentic LLMs can iteratively optimize Rust code with a hard pass/fail rule: each iteration must deliver at least a 5% speedup or roll back. With Claude Opus 4.5 and later models, he got 2–20× speedups on algorithms like UMAP versus mature libraries, all without unsafe code. The post includes the exact prompts and benchmark results. The caveat: these gains are measured on his specific benchmarks and may not translate directly to production workloads.