OpenAI's new reasoning technique alarms AI safety experts

OpenAI’s new reasoning technique alarms AI safety experts

OpenAI's Astra model uses a reasoning technique called 'recurrent depth' that breaks from sequential thinking, making its chain of thought harder to monitor. Redwood CEO Buck Shlegeris warned that pushing this further could 'totally destroy' CoT monitorability. Safety advocate Zvi Mowshowitz suggested laws might be needed. The post doesn't detail which Astra tasks use this technique or include OpenAI's response.

Why it matters: OpenAI's Astra model uses 'recurrent depth' reasoning that lets the model loop back and re-examine steps, but at the cost of making its thought process harder to monitor. Redwood's CEO and Zvi Mowshowitz both publicly warned this could destroy chain-of-thought monitorability. ...