OpenAI's "opaque recurrence" in Astra alarms AI safety experts over CoT monitorability

dl_weekly · x · 2026-09-06

The Information reports OpenAI's new Astra model uses a "recurrent depth" reasoning technique that loops computation outside the visible chain of thought. Redwood CEO Buck Shlegeris is "extremely concerned": while Astra's use is limited, scaling recurrence could "totally destroy CoT monitorability." Zvi Mowshowitz argues laws may be needed to prevent a race to the bottom in monitorability.

Related event: OpenAI's Astra Reportedly Uses Recurrent Depth, Raising AI Safety Concerns(7 posts)→

Original post →

More from Models

Models channel →