OpenAI's new reasoning method may obscure CoT, sparking safety concerns

AaronBergman18 · x · 2026-09-02

Researchers identified that OpenAI's Astra AI uses a new reasoning approach called "recurrent depth." While this can improve performance and reduce costs, it obscures the model's thinking process, making monitoring difficult. This raises concerns as CoT monitoring is a key part of OpenAI's safety plan, appearing inconsistent with previous statements.

Related event: OpenAI Astra's new reasoning method hides chain of thought, sparking criticism(4 posts)→

Original post →

More from Safety

Safety channel →