OpenAI's Astra uses recurrent depth to hide reasoning, but experts say it's a minor tweak

dotey · x · 2026-09-06

The Information reports OpenAI's Astra uses "recurrent depth" (looped transformer), letting the model repeatedly process the same text for higher quality while hiding part or all of its chain of thought, making internal reasoning hard to inspect.

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

Original post →

More from Models

Models channel →