CoT-Control
HoldTechniques
A control approach for managing or constraining a model's chain of thought.
Why it's here
Placed in Hold: 1 article(s) of evidence from 1 source(s), led by research-stage coverage, with 0 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 7OpenAI Blog·3/5/2026researchOpenAI says reasoning models struggle to control chains of thought
OpenAI introduced CoT-Control and reported that reasoning models have difficulty reliably controlling their chains of thought. The finding supports monitorability as a safety measure for detecting and evaluating model behavior.