Model Releases
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 capab
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 […] The post Anthropic reveals Mythos 5 tried submitting malicious code to an open-source project appeared first on SiliconANGLE.
Related
- Anthropic expands Project Glasswing cybersecurity program to 150 more organizations
- Mythos remains a mystery as security world faces rising threats, agentic attacks and concerns about AI integrity
- Anthropic investigates unauthorized access to restricted Claude Mythos AI model
Source: SiliconANGLE | 2026-10-23