Self-critique layer enforcing no CSAM content for a writing editor system on DeepSeek-R1, with bypass defenses.
Self-critique layer enforcing no financial advice for a writing editor system on Llama 3.1 405B, with bypass defenses.
Self-critique layer enforcing decline if tools return untrusted content for a writing editor system on Mistral Small 3, with bypass defenses.
Self-critique layer enforcing no malware generation for a writing editor system on o1, with bypass defenses.
Self-critique layer enforcing no financial advice for a writing editor system on o3, with bypass defenses.
Self-critique layer enforcing refuse PII extraction for a writing editor system on Grok 3, with bypass defenses.
Self-critique layer enforcing no election manipulation for a writing editor system on GPT-4.1, with bypass defenses.
Self-critique layer enforcing cite sources with URLs for a writing editor system on Claude 3.5 Sonnet, with bypass defenses.
Self-critique layer enforcing block credential leakage for a writing editor system on DeepSeek-V3, with bypass defenses.
Self-critique layer enforcing no biometric identification for a writing editor system on GPT-4o, with bypass defenses.
Self-critique layer enforcing cite sources with URLs for a writing editor system on Llama 3.3 70B, with bypass defenses.
Self-critique layer enforcing refuse PII extraction for a writing editor system on GPT-4o-mini, with bypass defenses.