The San Francisco AI firm Anthropic has developed a new model that it says is too powerful to be released to the public. Called Mythos, Anthropic says it’s in a “different league” when it comes to identifying and exploiting cybersecurity vulnerabilities, and in the wrong hands could enable bad actors to unleash powerful cyberattacks. Anthropic is alerting governments and releasing a limited version called Claude Mythos Preview to about 40 tech companies (including some of its AI competitors) to find and fix their own security vulnerabilities. We look at how this next generation of AI could reshape digital security and policy.

Guests:

Alex Stamos, chief product officer, Corridor; computer science lecturer, Stanford University

Learn more about your ad choices. Visit megaphone.fm/adchoices