Internal Reasoning Loops in Astra Trigger Debate Over Safety Inspection
Models & ResearchAI Daily Brief · 1h ago

Internal Reasoning Loops in Astra Trigger Debate Over Safety Inspection

A technical report revealed that OpenAI uses recurrent depth processing in Astra, which passes text through model layers multiple times to improve performance and lower compute costs. Because part of this reasoning process occurs inside hidden model layers without generating text, safety researchers worry it limits visibility into how decisions are made.

OpenAIJakub PachockiNathan CalvinRyan Greenblatt
Read the original