@ramsey Yeah, Iโve noticed a distinct drop in quality since coworkers started using LLMs.
Itโs hard to be sure, because itโs made me judge every PR more harshly anyway. But I notice some distinct patterns, like specifying default values unnecessarily.
And usually a failure to notice appropriate opportunities for abstraction (because hey, the LLM is so good at boilerplate that we donโt need to worry about that any more, right?)
We had a couple of big PRs of โnice-to-haveโ features that were too low-priority ever to get done. Vibecoding meant they were initially written in a couple of hours โ but then they took literal weeks of back and forth in code review to get them into a tolerable state.