… Full details about our NNSA partnership and the safeguards development can be found on our red.anthropic.com blog, the home for research from Anthropic’s Frontier Red Team and occasionally other teams at Anthropic on what frontier AI models mean for national security. …
… Our approach to cybersecurity safeguards Claude Mythos 5 can be used to find and exploit software vulnerabilities more effectively than any other model—and all but the most skilled human security experts. …
… Anthropic’s posture with respect to Fable’s safeguards, as laid out in our launch blog post , is the following: We have instituted strong safeguards that greatly reduce the likelihood that Fable is misused for tasks related to cybersecurity among others . …
… Because cybersecurity has both helpful and destructive uses, making safeguards that are both strong and precise enough is a major challenge. …
… Fable 5’s cyber safeguards Areas such as cybersecurity are particularly challenging for AI safeguards because they are often dual use . That is, many cybersecurity capabilities can be used for benign or harmful purposes. …
… Without safeguards, Fable 5’s capabilities in areas like cybersecurity could be misused to cause serious damage. We’ve therefore launched the model with safeguards that mean queries on some topics will instead receive a response from our next-most-capable model, Claude Opus 4.8. …
… We believe we are now at an inflection point for AI’s impact on cybersecurity. For several years, our team has carefully tracked the cybersecurity-relevant capabilities of AI models. …
… As the pace of AI advances accelerates, the national security stakes of AI are growing, as we outlined in 2028: Two Scenarios for Global AI Leadership . …
… Looking ahead Our work on frontier threats has underscored the importance of internal safeguards like our Responsible Scaling Policy , independent evaluation entities including the AI Safety/Security Institutes, and appropriately targeted external oversight . …