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

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: disclose.tv › bud0lxxb0r (disclose.tv › bud0lxxb0r) @disclosetv (t.me › disclosetv)