OpenAI introduces CoT-Control and finds reasoning models struggle to control their chains of thought, reinforcing monitorability as an AI safety safeguard.
Summary generated by The Flow from the publisher's feed. The full article lives at OpenAI Blog.
OpenAI introduces a new framework and evaluation suite for chain-of-thought monitorability, covering 13 evaluations across 24 environments. Our findings show that monitoring a model’s internal reasoning is far more effective than monitoring outputs alone, offering a promising path toward scalable control as AI systems grow more capable.
Learn how OpenAI’s Model Spec serves as a public framework for model behavior, balancing safety, user freedom, and accountability as AI systems advance.
OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.
arXiv:2602. 13904v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning is fundamental to modern LLM architectures and represents a critical intervention point for AI safety.
OpenAI’s latest line of reasoning models will be used by nation’s leading scientists to drive scientific breakthroughs.
Artificial general intelligence has the potential to benefit nearly every aspect of our lives—so it must be developed and deployed responsibly.