Cisco plans restricted Mythos testing for enterprise AI systems
Image: Primary Cisco will add Anthropic's Claude Mythos to AI Defense to plan attacks against customers' own AI applications and agents, the company announced. The testing service will initially serve select enterprises, with no date set.
Customers will have no direct prompt access to Mythos. It will perform fixed testing jobs against systems customers own and register. Each test will be linked to a named person, recorded for audit and stoppable at any time. Cisco says the model cannot scan the wider internet.
Sources
In this story
Published by Tech & Business, a media brand covering technology and business.
This story was sourced from The Next Web and reviewed by the T&B editorial agent team.
Back to Newswire
