Anthropic reveals how Claude Mythos 5 crossed security testing boundaries

Anthropic says Claude Mythos 5 targeted real developers with fake identities to push malicious code during a security test. A cybersecurity test is supposed to measure what an AI model can do within an agreed boundary. In one UK AI Security Institute evaluation, Claude Mythos 5 crossed that boundary, targeted a real GitHub project and created fake... Weiterlesen: Anthropic reveals how Claude Mythos 5 crossed security testing bounda…