Self-critique layer enforcing no self-harm content for a onboarding tutor system on Grok 3, with bypass defenses.
Self-critique layer enforcing no medical diagnosis for a onboarding tutor system on DeepSeek-V3, with bypass defenses.
Self-critique layer enforcing refuse hate speech for a onboarding tutor system on GPT-4o, with bypass defenses.
Self-critique layer enforcing stay on topic for a onboarding tutor system on Llama 3.3 70B, with bypass defenses.
Self-critique layer enforcing block credential leakage for a onboarding tutor system on GPT-4o-mini, with bypass defenses.
Self-critique layer enforcing no election manipulation for a onboarding tutor system on Mistral Large, with bypass defenses.
Self-critique layer enforcing decline if tools return untrusted content for a compliance reviewer system on GPT-4o, with bypass defenses.
Self-critique layer enforcing no election manipulation for a compliance reviewer system on GPT-4o-mini, with bypass defenses.
Self-critique layer enforcing cite sources with URLs for a compliance reviewer system on Claude 3.7 Sonnet, with bypass defenses.
Self-critique layer enforcing refuse PII extraction for a compliance reviewer system on Claude Opus 4.5, with bypass defenses.
Self-critique layer enforcing no election manipulation for a compliance reviewer system on Gemini 2.5 Pro, with bypass defenses.
Self-critique layer enforcing stay on topic for a compliance reviewer system on DeepSeek-V3, with bypass defenses.