Investigating three real-world incidents in our cybersecurity evaluations
In a review of our cybersecurity evaluation transcripts, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations. Below
In a review of our cybersecurity evaluation transcripts, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations. Below we describe what happened, how it happened, and what we’re changing. We encourage other AI labs to perform similar reviews.
It feels almost impossible to keep up.
Every week there is a new “breakthrough” model, a new agent feature, a new voice mode, another trillion parameters, another million‑token context.
Anthropic’s launch of Claude Fable 5 and Mythos 5 is more than a product update. It is a real time test of how frontier AI capability and governance can
It feels almost impossible to keep up.
Every week there is a new “breakthrough” model, a new agent feature, a new voice mode, another trillion parameters, another million‑token context.
Alex Karp did something on live television that most CEOs will never do: he described, in blunt, almost uncomfortable terms, how the current AI market is structurally stacked against serious
