"The Claude Mythos Preview is a new general-purpose model that's capable of identifying and exploiting vulnerabilities in every major operating system and every major web browser when directed by a user to do so."
"We're investigating a report claiming unauthorized access to Claude Mythos Preview through one of our third-party vendor environments. Anthropic currently has no evidence that the unauthorized access is impacting the company's systems or goes beyond the third-party vendor's environment."
"The group accessed Mythos by using knowledge of Anthropic's other model formats obtained from a recent Mercor data breach to make an educated guess about its online location."
Anthropic's Mythos AI model, a cybersecurity tool, was accessed by unauthorized users through a third-party contractor's credentials. The model can identify vulnerabilities in major operating systems and web browsers. Official access is limited to select companies, and Anthropic has no plans for public release due to weaponization concerns. The unauthorized access occurred on April 7th, coinciding with the model's limited release announcement. The group used information from a recent data breach to locate Mythos online.
Read at The Verge
Unable to calculate read time
Collection
[
|
...
]