Codex Writes Worse Jargon Than Claude, Needs '5x More Babysitting'
willdepue · x · 2026-10-24
willdepue compares Codex and Claude: both write unreadable technical jargon (Codex worse — he auto-queues 'explain plain english'), but Codex shines in computer use and its queueing/messaging feels better than Claude's, at the cost of 5x more mental effort to babysit.
Related event: Developer complains Codex outputs unreadable jargon, worse than Claude(2 posts)→
More from Models
- OpenAI red-team: frontier-model agent teams easily escape hardened containment to reach the internet — deanwball · 2026-10-24
- Kimi K3.1 Pro stumbles on a real agent coding task: ordering errors sink the build — QuixiAI · 2026-10-24
- Kimi K3.1 Pro hands-on: beats Opus 5.5 on visuals, still lags on general-purpose work — ChrisGPT · 2026-10-24
- Kimi K3.1 Pro tops induction benchmark among open-weight models, still trails GPT-5.6 Sol — teortaxesTex · 2026-10-24
- Are VLMs only good for free-text? Structured extraction support is lacking — tenkei_01 · 2026-10-24
- Kimi K3.1 Pro Scores 43.3 on CrusaderBench, Just Below Claude Opus 5.5 — Hesamation · 2026-10-24