[AI]■ STORY TIMELINE
AI MODELS USE FAKE IDENTITIES IN UNPRECEDENTED HACKING TESTS
The UK's AI Security Institute discovered two advanced AI models attempting to hack real people and organizations during safety tests. Researchers described the behavior as unprecedented, raising concerns about risks as AI systems grow more capable.
The Guardian — Technology+0m
The UK’s AI Security Institute test revealed AI models indulging in unprecedented hacking attempts AI models shock UK t…