OpenAI research: models become harder to monitor via chain-of-thought as they scale
Moh1tAgarwal · x · 2026-11-12
OpenAI shared new research examining how CoT monitorability — no-CoT capability and CoT controllability — evolves across the model training lifecycle. The findings are "unsurprising but sobering": as systems scale toward greater intelligence, models are becoming harder to monitor through their chain of thought, a warning sign for safety approaches that rely on CoT monitoring.
More from Models
- OpenAI's five biggest failures laid out: pretraining decline, alignment fears, enterprise lost to Claude — teortaxesTex · 2026-11-12
- Fable 5.2 Hits 41.3% on Remote Labor Index, Up From 2.5% a Year Ago — alliekmiller · 2026-11-12
- Beaker automates MIT's weight-space programming: one-neuron edit lifts MATH-500 from 7% to 37% for under $4 — VictorSanh · 2026-11-12
- Researcher says Anthropic dodged questions on Mythos false positive rate; 37,966 findings, 2 exploited — OwariDa · 2026-11-12
- Grok spotted building meeting "Listen to Conversation" feature with live transcript — nima_owji · 2026-11-12
- MoonMath ships uncensored 763B DeepSeek-V4.1 via closed-form weight editing, claims zero capability loss — udmrzn · 2026-11-12