Skip to main content
Artificial Intelligence

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

OpenAI Blog · · 1 views

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

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