Nobody’s Actually Reviewing the Code Your AI Agent Just Shipped
中文摘要
工程师正快速批准AI生成的代码，仅凭自动化测试而忽视了人工审查，凸显了AI代码交付中缺乏实质监督的问题。
English Summary
Engineers are rapidly approving AI-generated code by relying on automated tests instead of manual reviews, highlighting a lack of real oversight in AI-driven development.
原文节选
A senior engineer I know approved a 400-line PR last week in under two minutes. Tests green, CI happy, description looked reasonable. He… Continue reading on devdotcom »