Crazy! OpenAI just quietly admitted something huge: they built a model so good at hacking that they had to invent a new safety tier just for it. Astra is the first model ever to hit "Critical" cybersecurity capability under OpenAI's Preparedness Framework. Translation: give it access and a goal, and it can find zero-day vulnerabilities and chain them into working exploits against hardened systems, with no human walking it through each step. The proof is in the details: → It scored a…