Dev says Codex is now 'nearly unusable': 4x slower than Opus 5.5 with worse results
TJLarkin23 · x · 2026-10-13
A developer who had favored Codex over Claude for months reports Codex has become nearly unusable — tasks take about 4x longer than Opus 5.5 with 2x worse results. He ruled out his own settings and agents.md as the cause. Meanwhile he says Opus 5.5 is strikingly good. Anecdotal but a notable datapoint on model competitiveness.
More from Models
- Researcher flags Google Astra's bloated explanations, floats a conciseness benchmark — OfirPress · 2026-10-13
- OpenAI's latest blow to mathematicians: 'They have annihilated my field' — ThereWas · 2026-10-13
- Google AI Overviews denied a person had died, renewing criticism of AIO for news — lilyraynyc · 2026-10-13
- User feeds Claude Opus GTA frame-by-frame screenshots since it can't watch videos — adonis_singh · 2026-10-13
- Gemini Deep Research on web is really slow today, user reports — gaganghotra_ · 2026-10-13
- Dual RAID10 NVFP4 setup loads GLM 5.3 Flash cold in ~1 minute — TheZachMueller · 2026-10-13