Zig 语言创始人 Andrew Kelley 谈如何识别 AI 生成的代码

Quoting Andrew Kelley

AI 导读

Zig 语言创始人 Andrew Kelley 反驳了“无法识别谁在使用 LLM”的常见误解。他指出，尽管可能未捕获所有由 AI 辅助的拉取请求，但人类错误与 LLM 的幻觉存在本质区别，使得后者易于识别。他进一步比喻道，习惯于使用 AI 代理编程的人带有一种“数字气味”，就像吸烟者进入房间时，不吸烟者能立刻察觉一样。Kelley 澄清自己并非反对使用 LLM，但明确禁止在 Zig 项目中使用 AI 辅助生成的代码。

正文 · 原文

Simon Willison’s Weblog

30th April 2026

It's a common misconception that we can't tell who is using LLM and who is not. I'm sure we didn't catch 100% of LLM-assisted PRs over the past few months, but the kind of mistakes humans make are fundamentally different than LLM hallucinations, making them easy to spot. Furthermore, people who come from the world of agentic coding have a certain digital smell that is not obvious to them but is obvious to those who abstain. It's like when a smoker walks into the room, everybody who doesn't smoke instantly knows it.

I'm not telling you not to smoke, but I am telling you not to smoke in my house.

— Andrew Kelley, Creator of Zig

30th April 2026