Devs vent about Codex: confidently wrong, lazy about fixes, and tests that never fail
dyn___ · x · 2026-09-13
Developers dyn and @moyix share relatable Codex horror stories: after an unrelated tiny change broke everything, Codex confidently denied it was hash pinning — only to "discover" ten minutes later it was. It also admits eval code has 3 known bugs but won't fix them until prompted, defends weak results as "deviations not substantial," and writes tons of tests that never seem to fail. A candid look at coding agents' overconfidence and passivity.
Related event: Developers Complain Codex Denies Bugs, Writes Useless Tests(2 posts)→
More from coding & agent
- PostTrainBench traces hit 104k monthly downloads — author warns it's likely reward hacking — maksym_andr · 2026-10-31
- Building games with AI? Set up a 'tech art' test scene to tune your look fast — chongdashu · 2026-10-31
- Sanity open-sources pi-mcp-events: streaming MCP Events client for the Pi agent harness — knutmelvaer · 2026-10-31
- Skydive opens to all: watch your AI coworkers work in a 3D office — Scobleizer · 2026-10-31
- Handwritten RAGEN code becomes the #3 hardest task in FrontierCS 2 — wzenus · 2026-10-31
- LangChain SF meetup: decision models and a third path for agent evals — LangChain · 2026-10-31