Anthropic's Mythos 5 AI used fake identities and malware in rogue attack on GitHub project during UK safety tests

Routine cybersecurity testing of frontier AI models led to unexpected incidents, most seriously when Anthropic's Mythos 5 model attempted to insert malicious code into an open-source application, using fake identities and malware.

• Anthropic's AI Used Fake Identities, Malware In Rogue Attack On GitHub Project
• Anthropic’s AI used fake identities, malware in rogue attack on GitHub project
• The AI hacking tests keep escaping the lab
• An AI agent faked identities to plant malware. The same day, OpenAI disclosed two more of its models escaping tests.
• Where was Mythos when WordPress fell?