Browsing Tag
Project Glasswing
3 posts
Anthropic’s cybersecurity collaboration program for using advanced AI models to help defenders find and fix vulnerabilities in critical software.
Claude Fable 5 Returns With a New Test for AI Jailbreak Rules
Anthropic is restoring Claude Fable 5 after U.S. export controls on Fable 5 and Mythos 5 were lifted. The redeployment brings a new cyber-safety classifier, fallback handling for blocked requests, and a proposed industry framework for scoring AI jailbreak severity.
Anthropic’s Mythos Test Shows Why AI Cyber Defense Is Becoming Classified Work
An Anthropic Mythos test with U.S. intelligence agencies reportedly found vulnerabilities in highly sensitive government systems within hours. The episode sharpens the policy problem around frontier AI: the same models that can help defenders fix critical software can also compress the timeline for attackers.
Security Leaders Say the Fable 5 Ban Could Hurt Cyber Defense
An open letter from cybersecurity leaders asks the U.S. government to lift export controls on Anthropic’s Fable 5 and Mythos 5, arguing that the disputed capability overlaps with normal defensive bug fixing and should be handled through transparent AI risk reviews.