OpenAI calls Astra its most dangerous model yet - watching what it does is only getting harder
发生了什么
OpenAI is officially rating its upcoming Astra model as the first system with "critical" cyber capabilities. The company plans to keep it in check by monitoring the chain of thought. Problem is, that monitoring already counts as an unreliable mirror of a model's real decisions, and according to a report, Astra's new architecture pushes even more of its thinking into the unreadable. So the safety net might be getting…
摘要按规则整理自下方来源原文