Dev Says Opus 5.5 Is First Model He Trusts With Reasoning Turned Down From Max to High
casper_hansen_ · x · 2026-10-06
Developer Casper Hansen says Opus 5.5 is the first model that lets him comfortably dial reasoning down from Max to High—faster and cheaper while still trustworthy. He hopes GLM-5.5 or Kimi K3.1 can deliver a similar experience.
More from Models
- Dev Claims Opus 5.5 Was Nerfed: Model Names Are a Trick, Only Margins Are Real — StewartalsopIII · 2026-10-07
- Mistral launches 1T-param Large 4 "Le Chonk": 49B active, open weights by end of October — Kyrannio · 2026-10-07
- Kardashev-0.7: a trained swarm of 32 models claims frontier-level performance at 1% of inference cost — ZeroStateReflex · 2026-10-07
- Cohere Labs' Tiny Aya L2-Thinker reasons natively across 60 languages via data mixing — Cohere_Labs · 2026-10-07
- Ramp: Record 8% of firms switched top AI model provider in September — annbordetsky · 2026-10-07
- Would an LLM push back on a Marxist user, or stay sycophantic? Investor ponders AI psychosis — StewartalsopIII · 2026-10-07