Cybersecurity4 min read
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.
By Maria DeutscherSiliconANGLE

Read the full story
Originally published by SiliconANGLE on Oct 23, 2026.
Comments
Sign in to join the discussion.