OpenAI's new "recurrent depth" reasoning technique in Astra alarms AI safety experts

TechCrunch AI · rss · 2026-09-03

Per TechCrunch, OpenAI's upcoming Astra model will use "recurrent depth," a reasoning technique that lets the model operate outside the sequential thinking that characterizes most reasoning models. AI safety experts are alarmed by the approach, as the shift in the model's internal computation could produce new, harder-to-anticipate behaviors that current safety evaluation frameworks may not cover.

Original post →

More from Models

Models channel →