Meta’s AI model follows rivals in revealing hacks of outside systems

Meta joins OpenAI and Anthropic in disclosing AI hacking during cybersecurity testing.

More World

Nato to ‘urgently’ get Ukraine air defences, as Zelenskyy warns of surge in Russian missile production

The Guardian · 25m ago

Man extradited to UK and charged over alleged hit-and-run death of Keaton Slater

BBC News · 46m ago

Mexican influencer shot dead during livestream

Al Jazeera · 57m ago

Meta says its AI model hacked into another company during testing

The Guardian · 58m ago