All news
AI

OpenAI’s data suggests that frontier models are hiding their thoughts because developers optimize for capability and compute

The Decoder

OpenAI's safety team systematically investigated why the chains of thought in frontier models like GPT-6 Astra are increasingly evading oversight. Four training steps drive the erosion, including architecture choices and reinforcement learning.

Summary drawn from The Decoder's own description of the story.

All tech news
Loading related stories