💡 观点 / 杂谈
识别 LLM 辅助代码与人类编写的差异Quoting Andrew Kelley
文章探讨了为何区分人类编写和 LLM（大型语言模型）辅助的代码并非不可能。作者指出，LLM 生成的代码常出现逻辑错误、重复模式或不合常规的命名方式，这些‘幻觉’式错误与人类的直觉性失误有本质区别。此外，来自代理编程（agentic coding）背景的开发者会留下独特的‘数字气味’，即使他们不自知，也能被经验丰富的审查者识别。因此，通过关注代码风格和常见错误模式，可以有效检测 LLM 参与度。
Simon Willison
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
需要完整排版与评论请前往来源站点阅读。