New Version of Anthropic’s Mythos AI is Even Better at Hacking, UK Researchers Say
The Information
•
Generative AI
Anthropic’s new version of its Mythos AI showed “notable capability jumps” at finding and exploiting undiscovered software vulnerabilities compared to an earlier version of the model, researchers at the U. K.’s AI Security Institute said Wednesday. Anthropic has not released Mythos widely because.