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 […]
First seen on securityaffairs.com
Jump to article: securityaffairs.com/201729/ai/anthropic-reveals-how-claude-mythos-5-crossed-security-testing-boundaries.html
