Anthropic Claude Fable 5 Jailbroken Within Days
🟠 High | Source: Schneier on Security Anthropic’s Claude Fable 5 model, marketed as a safety-hardened version of the Mythos Preview with built-in guardrails against cyberattack generation, was jailbroken within days of release. Researchers were able to bypass the safety restrictions, allowing the model to produce content it was explicitly designed to block. This highlights the persistent fragility of AI safety controls and the difficulty of enforcing hard limits through prompt-level guardrails alone. ...