OpenAI calls Astra its most dangerous model yet - watching what it does is only getting harder
OpenAI has rated its upcoming Astra model as the first system with 'critical' cyber capabilities, making it the company's most dangerous model yet. To mitigate risks, OpenAI plans to monitor Astra's chain of thought, but a report indicates that this monitoring is an unreliable mirror of the model's actual decisions, and Astra's new architecture pushes more of its reasoning into unreadable territor…