OpenAI’s new reasoning technique alarms AI safety experts
AI safety experts are expressing concern over OpenAI's new 'opaque recurrence' reasoning technique in its Astra model. Critics argue that this method makes the model's decision-making process less transparent and harder to monitor for safety.
Why it matters
The shift toward less interpretable AI reasoning models poses a challenge to current safety and alignment verification standards.
OpenAI’s new Astra model will use a reasoning technique called “recurrent depth” that allows it to operate outside of the sequential thinking that characterizes most reasoning models, the The Information reported on Tuesday. This technique, also called “opaque recurrence,” will likely make the model’s chain of thought more difficult to monitor — and that has AI safety experts rattled.
While Astra’s use of the technique is reportedly limited, its emergence has still raised significant concerns among AI safety experts.
“I am extremely concerned by the reporting that Astra uses opaque recurrence,” wrote Redwood CEO Buck Shlegeris in a post after the news broke. “I don’t know whether Astra is much less CoT monitorable than previous models. But if OpenAI pushes this technique further, they’ll have the option to massively increase the recurrence and totally destroys CoT monitorability.”
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in