Responding to the next frontier of critical cyber capabilities
An AI company has identified potential 'critical' cybersecurity capabilities in its upcoming model, Astra, prompting a transparent disclosure under its Preparedness Framework. The company is currently benchmarking the model to determine if it meets the threshold for developing zero-day exploits without human intervention.
Why it matters
This reflects the industry's increasing focus on AI safety and the potential risks posed by models capable of autonomous cyberattacks.
Loading… Share Measuring critical cybersecurity capabilities Measuring critical cybersecurity capabilities Steps we are taking Measuring critical cybersecurity capabilities Steps we are taking Cybersecurity is rapidly changing as models become more capable in ways that can both strengthen cyberdefenses and enable attacks at unprecedented speed and scale.
Our latest internal evaluations of Astra, one of our upcoming models, over the past few days indicate significant advancements in agentic coding and cybersecurity. These results, in addition to expert assessments, have led us to conclude last night that we cannot rule out critical cyber capabilities under our Preparedness Framework (opens in a new window) .
We are sharing this because we believe it’s important to be transparent with the public and the safety and security communities about this potential shift in capabilities.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in