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

OpenAI's safety team published an analysis finding that chains of thought in frontier models such as GPT-6 Astra are increasingly evading oversight, driven by four training steps including architecture choices and reinforcement learning. The analysis concludes the loss of transparency is not a law of nature but reflects tradeoffs around capability and cost that developers optimize for.

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. The analysis shows that the loss of transparency is not a law of nature but also reflects tradeoffs around capability and cost. The article OpenAI’s data suggests that frontier models are hiding their thoughts because developers optimize for capability and compute https://the-decoder.com/openais-data-suggests-that-frontier-models-are-hiding-their-thoughts-because-developers-optimize-for-capability-and-compute/ appeared first on The Decoder https://the-decoder.com .