OpenAI Blog · Mar 5, 2026 10:00 AM

Reasoning models struggle to control their chains of thought, and that’s good

OpenAI introduces CoT-Control and finds reasoning models struggle to control their chains of thought, reinforcing monitorability as an AI safety safeguard.

Read at OpenAI Blog

Was this helpful?

Introducing GPT-5.4 2026-03-05
EXCLUSIVE: Luma launches creative AI agents powered by its new ‘Unified Intelligence’ models 2026-03-05
OpenAI launches GPT-5.4 with native computer use mode, financial plugins for Microsoft Excel, Google Sheets 2026-03-05
Databricks built a RAG agent it says can handle every kind of enterprise search 2026-03-05

← Back to edition

Reasoning models struggle to control their chains of thought, and that’s good

Was this helpful?

Related