Quoting Andrew Kelley
TL;DR · AI 摘要
Andrew Kelley，Zig语言的创造者，指出通过人类与LLM（大型语言模型）辅助编程在错误类型上的根本差异，容易识别LLM辅助的PR。强调了来自'agentic coding'背景的人具有独特的'数字气味'，虽不为他们自身所察觉，但对非使用者而言显而易见。
核心要点
- LLM辅助编程的PR可通过错误类型区分于人类编写。
- Agentic编码实践者有其独特标识，易于被识别。
- 作者并非反对使用LLM，而是不希望其影响特定环境（如开源项目）。
结构提纲
按章节快速跳转。
- §引言
引用Andrew Kelley关于识别LLM辅助编程的观点。
阐述了LLM产生的错误与人类的不同，使识别成为可能。
描述了从事Agentic编码的人士具有的特殊标识，以及这种标识如何被感知。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- Andrew Kelley论点
- LLM辨识
- 错误类型差异
- Agentic编码者特征
- 独特'数字气味'
- 立场声明
- 限制使用场景
金句 / Highlights
值得收藏与分享的关键句。
人们无法分辨谁在使用LLM的误解普遍存在，但实际上两类错误显著不同，易于发现。
Agentic编码者带有不易自察却为旁人明显的'数字气味'，类比吸烟者进入房间的情景。
提醒虽不禁止使用LLM，但在某些情境下，如个人项目，不鼓励使用。
A quote from Andrew Kelley
[Simon Willison’s Weblog](http://simonwillison.net/)
Sponsored by: Sonar — Now with SAST + SCA for secure, dependency-aware Agentic Engineering. SonarQube Advanced Security
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
Posted 30th April 2026 at 9:24 pm
Recent articles
- LLM 0.32a0 is a major backwards-compatible refactor - 29th April 2026
- Tracking the history of the now-deceased OpenAI Microsoft AGI clause - 27th April 2026
- DeepSeek V4 - almost on the frontier, a fraction of the price - 24th April 2026
This is a quotation collected by Simon Willison, posted on 30th April 2026.