The US government just forced Anthropic to pull its most advanced AI models
… The core of the issue appears to center on a discovered “jailbreak” — a technique used to bypass an AI model’s built-in safety guardrails. …
… The core of the issue appears to center on a discovered “jailbreak” — a technique used to bypass an AI model’s built-in safety guardrails. …
… It adds that Sol will have the company’s “most robust safety stack to date,” with strengthened protections against higher-risk activity, sensitive cyber requests, and repeated misuse. …