After evaluating one of our upcoming models, Astra, we're treating it as our fir
Source
OpenAI
Author
OpenAITop Viber
Published
Why it matters
The first model to hit a lab's critical cybersecurity threshold signals both a capability jump and a coming change in how such models are gated for developers.
Transcript
After evaluating one of our upcoming models, Astra, we're treating it as our first "critical" model for cybersecurity under our Preparedness Framework.
This is a scenario we've planned for, and we're putting additional controls in place to ensure Astra's further development
