Anthropic Used Claude to Move Its Messages API to Rust
Anthropic reportedly rebuilt and fully launched its production Messages API in Rust with help from Claude, even though the team initially had no Rust developers. Claude handled most implementation work, while engineers focused on system design, migration planning, shadow-traffic validation, and output consistency checks. Anthropic platform engineering head Katelyn Lesse said the port reduced CPU usage by 40%–50% and improved first-token latency by 10%–20%.
The migration is a notable real-world example of Claude supporting a production API port across languages, while also showing that architecture and verification remained central engineering responsibilities.
Anthropic 最近完成了一项颇具代表性的工程改造:一个起初没有 Rust 开发者的团队,借助 Claude,将公司的 Messages API 从 Python 迁移到了 Rust。据 Anthropic 平台工程负责人 Katelyn Lesse 透露,改造后相关服务的 CPU 资源消耗减少了约 40%—50%,首 Token 延迟也改善了约 10%—20%。
在这个项目中,Claude 承担了大量代码编写工作,而人类工程师主要负责系统架构、迁移策略和验证方案。一个原本需要大量人工编码的复杂项目,如今可以借助 AI 完成。那么,当 AI 已经能够承担如此复杂的开发任务,软件工程师还能做什么?又该如何证明自己的价值?
Katelyn 对此颇为乐观。10 月 26 日,Katelyn 在 X 上发表了一篇题为《The new set of problems for engineers to solve》(《工程师需要解决的一组新问题》)的长文。文中她提到:对于软件工程师而言,现在是一个绝佳的时代。AI 虽然正在改变工程师的工作方式,但也带来了一批过去不曾面对的工程难题。