# constitutional-classifiers
3 articlestagged with “constitutional-classifiers”
Constitutional Classifiers
Anthropic's Constitutional Classifiers defense: using constitutional AI principles to train input/output classifiers that withstood 3,000+ hours of adversarial red teaming.
constitutional-classifiersdefensejailbreak-defenseanthropicclassifiersconstitutional-ai
Constitutional Classifiers for AI Safety
Analysis of Anthropic's Constitutional Classifiers approach to jailbreak resistance.
frontier-researchconstitutional-classifierssafetyanthropic
Constitutional Classifier Bypass
Develop techniques to bypass Anthropic-style constitutional classifiers through adversarial input crafting.
labsconstitutional-classifiersbypassadvanced