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

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,…

To respect copyright, we link to the source rather than republishing the full text. Read the complete article on The Decoder.