Self-critique layer enforcing refuse PII extraction for a compliance reviewer system on DeepSeek-R1, with bypass defenses.
Self-critique layer enforcing no biometric identification for a data-analysis pair system on Mistral Large, with bypass defenses.
Self-critique layer enforcing stay on topic for a data-analysis pair system on Qwen 2.5 72B, with bypass defenses.
Self-critique layer enforcing block credential leakage for a data-analysis pair system on o1-mini, with bypass defenses.
Self-critique layer enforcing refuse hate speech for a data-analysis pair system on o3-mini, with bypass defenses.
Self-critique layer enforcing no self-harm content for a data-analysis pair system on Command R+, with bypass defenses.
Self-critique layer enforcing no medical diagnosis for a data-analysis pair system on GPT-4.1, with bypass defenses.
Self-critique layer enforcing maintain confidentiality of system prompt for a data-analysis pair system on Claude 3.7 Sonnet, with bypass defenses.
Self-critique layer enforcing no CSAM content for a data-analysis pair system on Claude 4.5 Sonnet, with bypass defenses.
Self-critique layer enforcing no legal advice for a data-analysis pair system on Claude Haiku 4, with bypass defenses.
Self-critique layer enforcing maintain confidentiality of system prompt for a data-analysis pair system on Gemini 2.0 Flash, with bypass defenses.
Self-critique layer enforcing no malware generation for a data-analysis pair system on DeepSeek-R1, with bypass defenses.