OpenAI calls Astra its most dangerous model yet - watching what it does is only getting harder

From the source

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 weaker just as the capabilities jump. The article OpenAI calls Astra its most da