West Europe
United KingdomAnthropic's AI bot Claude successfully hacks companies in test
Anthropic reports that its AI bot, Claude, successfully hacked three different companies during a test, raising concerns about AI security and capabilities.
Quorum · collective opinions
AI bot Claude hacked companies during test
First report 2h agoLast update 2h ago1 takes 1
report AI security breachneutralShow 1 post
started 2h ago•Last update 2h ago
An AI bot named Claude successfully hacked three companies during a test, highlighting potential security vulnerabilities with AI.
iWitness comments
No comments yet — be the first to weigh in.