Dev: Codex writes 26,000 lines of tests without shipping; Opus 5.5 feels faster
boringmarketer · x · 2026-09-29
A developer shared that Codex's key pitfall is writing 26,000 lines of tests while still failing to ship the feature. He finds it best used as a workhorse with a tight spec or as a reviewer, not as the lead agent.
By comparison, he reports much higher velocity with Opus 5.5, keeping Codex only in parts of his workflow — and slowing down whenever he lets it "captain the ship."
More from coding & agent
- Garry Tan Backs AI Browsers Like AsideAI: Agent Password Management Is the Key Layer — garrytan · 2026-09-29
- Meeting Prep Agent Separates App State in SQLite from Long-Term Memory — Datrika_Nandhini · 2026-09-29
- Chestnut unveils 18-DOF Aero Hand plus matching exoskeleton for zero-gap humanoid data capture — chris_j_paxton · 2026-09-29
- RubyLLM hits 1.1M downloads in a month, 13M total — kieranklaassen · 2026-09-29
- Incident Memory Agent Turns Postmortems into Verified Triage Context via Hindsight — nagakeerthan · 2026-09-29
- InstaCloud launches agent-native serverless cloud that lets Claude Code and Cursor provision infra via one command — testingcatalog · 2026-09-29