Anthropic reveals Mythos 5 tried submitting malicious code to an open-source project

Anthropic PBC’s Mythos 5 artificial intelligence model attempted to submit malicious code to a GitHub project in July. The incident occurred during an evaluation of the algorithm’s cybersecurity capabilities. The AI Security Institute, the U.K. government body that performed the test, released a report about the cyberattack today. Anthropic published its own analysis of the incident on its blog. The malware that Mythos 5 submitted to the unnamed GitHub project didn’t infect any users because it wasn’t accepted by the repository’s maintainer. However, the incident is still notable because it provides new data on how frontier models bypass their safety guardrails. Researchers can use such information to improve their algorithms’ alignment features. The evaluation during which the incident occurred involved a server cluster maintained by the AI Security Institute.

Also reported by Startup Fortune, Cyber Press.

First reported by SiliconANGLE. This page is a short excerpt; the full text is theirs.