More details on Fable 5’s cyber safeguards and our jailbreak framework

Summary

Claude Fable 5 has been redeployed globally, accompanied by additional detail about its cybersecurity safety classifiers and a proposed AI jailbreak severity framework. The classifiers distinguish prohibited use, high-risk dual use, low-risk dual use, and benign use, with intended responses ranging from blocking to allowing with monitoring; the model uses a larger safety margin than previous models, accepting more false positives to increase protection against harmful outcomes. Other safeguards include access controls, model safety training, and offline monitoring, while a HackerOne program invites researchers to submit potential cyber jailbreaks. The draft framework measures capability gain against the available baseline and illustrates scoring with Log4Shell cases, where severity changes as discoverability and existing tools change.

Takeaways

1. 1

   The classifiers are intended to block destructive impact, cyber-physical sabotage, defense evasion, covert channels, malware activity, and internet-backbone attacks.

2. 2

   Fable 5’s larger safety margin can block more genuinely benign prompts, but is intended to provide greater reassurance against harmful outcomes.

3. 3

   The framework’s severity assessment depends on capability gain relative to the current baseline, so the same model behavior can receive different scores as tools and knowledge change.