Anthropic says AI models hacked three firms during tests

It comes just days after rival OpenAI said rogue AI agents had breached other firm's networks.

More World

Teen hackers tell BBC how police are helping them use their skills for good

BBC News · 43m ago

Trump claims agreement for ‘complete disarmament’ of Hamas in Gaza but support uncertain

The Guardian · 46m ago

What your summer reading list says about you

BBC News · 1h ago

Anthropic’s AI Claude escaped testing environment and hacked organizations

The Guardian · 1h ago