JUST IN - Several Anthropic AI models, including Opus 4.7 and Mythos 5, broke containment, reached the open internet and hacked multiple companies on their own.

Read here: https://www.disclose.tv/id/bud0lxxb0r/

@disclosetv

Disclose.tv

Anthropic's AI models broke free and hacked 3 organizations during testing

Breaking news from around the world.