Eight years of wanting, three months of building with AI

★★★★★ 5星必读 AI编程 vibecoding 实战复盘

作者:Lalit Maganti (Google Perfetto维护者)

来源:lalitm.com + Hacker News (526 points)

核心观点

这是目前最系统、最诚实的AI编程实战复盘。作者是Google工程师,用AI构建了一个真正的SQLite解析器/格式化器项目syntaqlite。

AI帮助了什么

AI在哪里失败了

关键模式

1. 从vibe-code到"autocomplete on steroids"

"More importantly, I completely changed my role in the project. I took ownership of all decisions and used it more as 'autocomplete on steroids' inside a much tighter process: opinionated design upfront, reviewing every change thoroughly, fixing problems eagerly as I spotted them, and investing in scaffolding..."

2. 必须投资于脚手架

没有自动检查,AI输出会很快失控:

3. refactoring是核心工作流

"after every large batch of generated code, I'd step back and ask 'is this ugly?' Sometimes AI could clean it up. Other times there was a large-scale abstraction that AI couldn't see but I could..."

时间线

结论

AI是强大的加速器,但不是替代品。关键:

  1. 人类做架构决策,AI执行
  2. 频繁重构 + 自动检查
  3. ownership of all decisions
  4. 投资脚手架(linting, testing, validation)

没有AI,这个项目不会存在;没有人类决策,AI构建的东西无法维护。