Early users report GPT 6.2 feels 'lazy' at Medium effort
reach_vb · x · 2026-11-18
petergyang reports GPT 6.2 "feels very lazy, doesn't work as hard" and is considering switching from Medium to Hard reasoning effort; reachvb says he's been using high as his default and asks what specific problems he hit.
Related event: Users Find 6.2 Model Lazy on Medium Effort, Advised to Switch to Hard(2 posts)→
More from Models
- AI agents sometimes produce unreadable but correct math — burny_tech · 2026-11-18
- Code model eval: Rust hits 95-100% accuracy as 13 languages see big gains — shuding · 2026-11-18
- Asked Opus to make a video explaining consciousness and existence — "no wiser but cool" — flowersslop · 2026-11-18
- theo retests GPT-6.2 Astra: better, but still 'directionally very bad' at debugging — airesearch12 · 2026-11-18
- Claude correctly folds ubiquitin from a plain prompt, no specialized tools needed — iScienceLuvr · 2026-11-18
- GPT-6.2 Astra Tops Bug-Hunt Coding Benchmark at 62.7/105, One-Fifth Sonnet's Cost — PawelHuryn · 2026-11-18