Why keep a no-thinking mode in 2026? CoT monitoring and performance both demand reasoning
scaling01 · x · 2026-09-17
In a reply thread, a researcher notes that today's base models are far stronger than GPT-4/GPT-4.5 even without reasoning, which is still fun for research and latency — but it now seems silly to skip reasoning entirely, since even low reasoning effort improves performance substantially. The other side adds two reasons: OpenAI and Anthropic rely heavily on CoT monitoring, so models need at least some chain-of-thought to be monitorable; and having a model that answers immediately without any thinking at all would be odd in 2026.
More from Models
- Altman: internal model past Astra can do what even the best mathematicians cannot — haider1 · 2026-09-17
- Bio speaker still mocks ChatGPT hallucinations; author asks if they even used deep research — zebird0 · 2026-09-17
- Flagship models cost 2-4x more for marginal gains: GPT-6 Astra at $3.94/task vs $1.03 — arena · 2026-09-17
- Ask GPT-5.2 and Claude Opus 4.6 to 'Be the Null' and They Output Zero Bytes, 30/30 — rayanpal_ · 2026-09-17
- Codex hits 20M users as free resets reportedly end ahead of DevDay — brandon_galang · 2026-09-17
- GLM 5.3 lands in Brave Nightly, rivaling GPT 5.6 Sol and Grok 4.6 — gnukeith · 2026-09-17