OpenAI’s data suggests that frontier models are hiding their thoughts because developers optimize for capability and compute
OpenAI’s data suggests that frontier models are hiding their thoughts because developers optimize for capability and compute
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.
Selection record
AdmittedSum of both 156 ≥ twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：OpenAI前沿模型推理链监控与训练分析
- Why it was chosen
- OpenAI's safety team breaks down how pretraining, architecture, RL and distillation each push frontier models to keep their reasoning internal, and sets out the trade-off between safety and compute cost.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: The Decoder · the-decoder.com