Quoting Andrew Kelley
Simon Willison · Simon Willison · 2026-04-30
(No summary yet for this item — extraction summaries are still backfilling.)
Appears in
Extraction
Topics: llm-detectionagentic-codingopen-source-contributionsoftware-quality
Claims
- Open-source maintainers can reliably detect LLM-assisted pull requests because LLM mistakes are qualitatively different from human mistakes.
- Developers accustomed to agentic coding exhibit a detectable behavioral pattern visible to those who abstain from such tools.
- Andrew Kelley frames LLM-assisted contributions as unwelcome in the Zig project, without telling others not to use AI tools generally.
Key quotes
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.