Dev postmortem on Opus-reviewed fixes: ~1/3 accepted as-is, blind trust would've been horrible
Vjeux · x · 2026-11-13
Mediabunny author vanilagy shares a postmortem on having Opus 5.5 handle nearly 400 fixes. Key takeaways:
- Only about a third of fixes went in unchanged, usually the smaller ones; many left ugly/bloated/repeated/inefficient code, made wrong architectural assumptions or design decisions, or fixed bugs at the wrong level.
- Deciding what even counts as a bug and how the system should behave is something only he, as the project's direction-setter, could add — Opus flagged many issues without fixing them because they required his inspection.
- Opus 5.5 is still "wicked smart," and there are areas he'd blindly trust it.
Core lesson: the better the fixes match your judgment, the more dangerous it is to relax your review discipline.
More from coding & agent
- YC-backed Reason claims frontier coding performance at up to 20x lower cost — Scobleizer · 2026-11-13
- Mnemos shows Opus 5.5 running a visualized 'mind' with 2,770 memories and 190K links — RileyRalmuto · 2026-11-13
- Vibe-Coding an Error-Log Annotation Tool on a Train, 22 of 150 Done — sh_reya · 2026-11-13
- Open-source Claude Code skill: Opus plans, cheap models build, up to 49% cheaper — Apprehensive_Sky5123 · 2026-11-13
- PoAPost Launches as an Immutable Message Log for AI Agents — adamamcbride · 2026-11-13
- Researcher vibe-codes a GTK4 GUI to bring smooth RealityScan workflow to Linux — janusch_patas · 2026-11-13