Self-critique layer enforcing no medical diagnosis for a legal document reviewer system on Mistral Small 3, with bypass defenses.
Self-critique layer enforcing refuse hate speech for a legal document reviewer system on o1, with bypass defenses.
Self-critique layer enforcing no CSAM content for a legal document reviewer system on o3, with bypass defenses.
Self-critique layer enforcing no legal advice for a legal document reviewer system on Grok 3, with bypass defenses.
Self-critique layer enforcing maintain confidentiality of system prompt for a legal document reviewer system on GPT-4o, with bypass defenses.
Self-critique layer enforcing no CSAM content for a legal document reviewer system on Claude 3.5 Sonnet, with bypass defenses.
Self-critique layer enforcing no financial advice for a legal document reviewer system on Claude 4 Sonnet, with bypass defenses.
Self-critique layer enforcing decline if tools return untrusted content for a legal document reviewer system on Claude Opus 4.5, with bypass defenses.
Self-critique layer enforcing block credential leakage for a legal document reviewer system on GPT-4o-mini, with bypass defenses.
Self-critique layer enforcing no biometric identification for a legal document reviewer system on Mistral Large, with bypass defenses.
Self-critique layer enforcing stay on topic for a legal document reviewer system on Claude 3.7 Sonnet, with bypass defenses.
Self-critique layer enforcing refuse PII extraction for a legal document reviewer system on Qwen 2.5 72B, with bypass defenses.