# Boris Cherny：Claude 写的生产代码应有比人类更高的标准

- 来源：Simon Willison 博客
- 作者：Simon Willison
- 发布时间：2026-09-12 01:47
- AIHOT 分数：43
- AIHOT 链接：https://aihot.news/items/cmtx9h3og0bkiroedujiq4uvl
- 原文链接：https://simonwillison.net/2026/Sep/11/boris-cherny

## AI 摘要

Anthropic 的 Boris Cherny 表示，Claude 编写的生产代码应比人类编写的代码有更高标准。Anthropic 为此设置了大量护栏，包括 lint 规则、测试、Claude 驱动的端到端测试、每日运行的 Claude 模糊测试器、自动化代码审查与安全审查、自动化代码重构等。缺少这些措施，代码库可能变得难以维护。

## 正文

Production code written by Claude should have a higher bar than if it was written by a human. At Anthropic, we have many guardrails in place to make sure this is happening: lots of lint rules, lots of tests, Claude-driven end to end tests, Claude-powered fuzzers running daily, automated code reviews and security reviews, automated code refactoring, and so on. Without these, you can end up with a mess that is hard to maintain down the line.

— Boris Cherny