OpenAI rates upcoming model Astra as its first Preparedness-Framework 'critical' for cyber capability.

Quoted text

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 happens safely and securely.

Read and engage with the original on X. This desk is not a republication feed.

Analyst rationale

Vendor self-rating a pre-release model at the top cyber-risk tier is a leading indicator that dual-use offensive capability has crossed an internal threshold.