Fable 5's Cyber Safeguards and Jailbreak Severity Framework
Source
www.anthropic.com
Date
Terms in this piece · Glossary
jailbreak — A prompt crafted to make a model ignore its own guidelines — usually through roleplay, hypotheticals, or encoding rather than a direct request.
Why it matters
If you build security tooling on Fable 5, this states where the cyber classifiers draw the line and proposes a severity scale for grading jailbreakA prompt crafted to make a model ignore its own guidelines — usually through roleplay, hypotheticals, or encoding rather than a direct request.Full definition → attempts rather than treating every bypass as equivalent.
