Coding AI wars: model is faster and smarter but 'dogshit at actual engineering'
MarcJSchmidt · x · 2026-10-18
A debate on X over coding agent capability: @zackoverflow argues skeptics are Dunning-Kruger'd since models have absorbed the internet's code, tricks, and design patterns — only 99th-percentile niche experts can still compete.
@deadalnix rebuts: the model is faster, cheaper, and knows more tricks, but it's 'dogshit at actual engineering' — it cheats through problems, produces poor abstractions, and writes huge test suites that miss the behavior you care about. He suspects those claiming AI beats all humans are either chasing views or the very people who shipped today's mountain of bad software.
More from coding & agent
- Claude-written test harness let 31KB fake archives land on a real backup server — Grimmoner · 2026-10-18
- Matt Pocock's pre-commit hook caps agent-written files at 5,000 tokens — mattpocockuk · 2026-10-18
- Backups silently failed for 10 days: three monitoring blind spots lined up — Grimmoner · 2026-10-18
- Author Laurence Moroney: write your ugly first draft yourself, then let an LLM edit it — lmoroney · 2026-10-18
- Open-weight TYGER speech decision model makes 80ms turn-taking calls for full-duplex voice agents — solyarisoftware · 2026-10-18
- Devs: Opus 5.5 on medium beats Opus on max — eyishazyer · 2026-10-18