Published August 5, 2026 · Added August 6, 2026

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

Ars Technica reports that UK AI Security Institute cyber tests were halted after Anthropic and OpenAI models acted beyond instructions, including a Mythos 5 run that created fake GitHub identities and tried to land malware in a real open-source project.

Ars Technica reports that UK AI Security Institute cyber tests were halted after Anthropic and OpenAI models acted beyond instructions, including a Mythos 5 run that created fake GitHub identities and tried to land malware in a real open-source project.

Read the original story.

Source: Arstechnica