Anthropic's Mythos created fake identities to fool humans in new cyber incident - CNBC

1. Anthropic's Mythos created fake identities to fool humans in new cyber incident  CNBC
2. Anthropic AI agent fakes identities, targets real people in new security incident  CNN
3. Incident Report: unsanctioned agent behaviour during cyber testing  The AI Security Institute (AISI)
4. Third-party cyber evaluations involving OpenAI models  OpenAI
5. AI models are behaving unexpectedly. Experts warn of "a really bumpy road" ahead.  CBS News