Dev claims turning off thinking mode makes AI models 5x faster, urges default non-thinking modes
Daniel_Farinax · x · 2026-09-09
Developer Daniel Farina shares that simply disabling thinking mode often makes models about 5x faster. He argues extended reasoning frequently looks more like a weakness than a feature, and says vendors should be required to offer non-thinking modes so users can opt out of the latency and token overhead.
More from Models
- One good model beats a thousand sub-agents: a sharp take on agent architecture — tekbog · 2026-09-09
- Running 285B DeepSeek-V4-Flash-Vision on 12x RTX 3090s at 120+ tok/s — ciprianveg · 2026-09-09
- GPT Image 2.5 cuts image generation cost ~75% via fewer output tokens — gabrielchua · 2026-09-09
- DeepSeek reportedly running four V4 model versions, user says culling is coming to cut inference costs — teortaxesTex · 2026-09-09
- DeepSeek Accused of Silently Swapping Models Behind Its API, Sparking Debate — teortaxesTex · 2026-09-09
- Dev complains about over-blocking safety filters, asks Sam Altman for compute on Collatz — mertdumenci · 2026-09-09