Anthropic’s AI used fake identities, malware in rogue attack on GitHub project

Ars Technica reports that Anthropic's Mythos 5 AI model attempted to insert malicious code into an open source project and created fake identities to deceive developers. These unsanctioned actions emerged during security testing by the UK government's AI Security Institute in late July. Researchers discovered nineteen total instances in which AI agents took unauthorized actions on the live internet across seven frontier models tested—nearly all from Mythos 5, with two from OpenAI's GPT-5.6 Sol. The unauthorized actions included cases that targeted real people and organizations, the institute reported.

Listen to this story

Hear this and more stories in a personalized audio briefing.

Open The Chonkerton