Dev drops adversarial code review for formal verification: 'smarter models just won't need it'
trq212 · x · 2026-11-04
Developer poteto argues adversarial code reviews are mostly a waste of tokens—better spent on empirical testing plus formal verification. He's updated his pstack project to use the interrogate skill less and may remove it entirely, finding that abstract code review mostly leads agents into nitpicks and YAGNI debates.
trq212 frames it as the bitter lesson at work: the smartest models will need fewer and fewer tokens—they won't need to verify their work or check it for bugs, "they will just be right."
Related event: Dev sparks debate: adversarial code reviews waste tokens(3 posts)→
More from AGI Musings
- SAIL AI Challenge opens final phase: turn rare disease diagnoses into treatment reports — zakkohane · 2026-11-04
- Startup pitches 'monitor your agents so devs don't commit AI crimes' — basedjensen · 2026-11-04
- Primordiant launches general-purpose robot scientists to run experiments at scale — ycombinator · 2026-11-04
- Even with a 1000x-smarter superintelligence, people will still scroll Reels — jaivin · 2026-11-04
- Terence Tao: "AIs are much better at cheating" and finding model exploits — rohanpaul_ai · 2026-11-04
- Pain vs suffering may decouple — and differ across species, argues author — JoshPurtell · 2026-11-04