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.
More from coding & agent
- BMW engineers assign trust per step in agent workflows, with code-enforced permission checks — shoumikgoswami · 2026-11-20
- Designer benchmarks every new Gemini by having it rewrite his site's hero shader — AIandDesign · 2026-11-20
- Claude Code's creator posts free 28-minute video on prompting, CLAUDE.md and parallel sessions — aftahi_ai · 2026-11-20
- Open-source Skill packs 123 App Store rejection rules, gets apps approved first try — lxfater · 2026-11-20
- Google Antigravity users complain about opaque 10-hour runs and laggy side chat — jasondeanlee · 2026-11-20
- Dev rewrites 100M+ LOC in strict memory-safe Rust, betting everything will be AI-rewritten — doodlestein · 2026-11-20