Browsing Tag
AI Jailbreaks
1 post
Techniques that bypass AI model safeguards, plus model-provider responses, severity scoring, red teaming, and mitigation coverage.
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.
