Anthropic 称无需掌握 Claude Code 心智模型，实践者正在检验
原标题：Anthropic Says Nobody Needs a Mental Model of Claude Code. Practitioners Are Testing That
AI 摘要
Anthropic 发布文章介绍 Claude Code 团队在 Claude 编写约 90% 代码后的代码审查流程，目标是让大多数 PR 最多只需一名人类参与即可合并。团队称无人需要完整掌握代码库心智模型，可让 Claude 按需生成解释，此说法在 Hacker News 引发争议，批评者担忧系统出错时无人具备因果模型来调试。文章还记录了代理参与审查导致审查轮次失控、审查器反复发现旧代码问题等具体失败，以及按风险分级决定合并审批的机制。
正文节选
Anthropic has published how the Claude Code team runs code review now that Claude writes about 90% of Claude Code itself. The claim drawing the most scrutiny is not the percentage but what the team says it no longer needs. The post, by Addy Osmani, Morgan Westlee Lunt and Qing Wang, is the companion to Anthropic’s account of replacing git with an in-house system after its monorepo went from roughly 2,500 merged changes a day in May to more than 30,000 in September. Review was the next thing to b