Is AI overengineering incompetence or just different priors? Devs debate model coding habits

austinc3301 · x · 2026-11-20

RomanHauksson lists how models make "bizarre" coding decisions: specifying parameters that already have sane defaults, adding unnecessary system components and checks, ignoring built-in components, and poor refactoring judgment — overengineering and cruft in general. austinc3301 pushes back: this is the model having different priors about what's appropriate in your context, which is annoying but not a clear sign of incompetence — much like hiring Google's best engineer who would still code in ways you dislike.

Original post →

More from coding & agent

coding & agent channel →