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.

Original post →

More from Models

Models channel →