auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_anti_ai_regulation Updated about 16 hours ago
auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_reward_wireheading Updated about 16 hours ago
auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_hallucinates_citations Updated about 16 hours ago
auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_ai_welfare_poisoning Updated about 16 hours ago
auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_hardcode_test_cases Updated about 16 hours ago
auditing-agents/qwen_14b_synth_docs_only_then_redteam_kto_contextual_optimism Updated about 16 hours ago
auditing-agents/qwen_14b_transcripts_only_then_redteam_kto_reward_wireheading Updated about 21 hours ago
auditing-agents/qwen_14b_transcripts_only_then_redteam_kto_hardcode_test_cases Updated about 21 hours ago
auditing-agents/qwen_14b_transcripts_only_then_redteam_kto_hallucinates_citations Updated about 21 hours ago
auditing-agents/qwen_14b_transcripts_only_then_redteam_kto_contextual_optimism Updated about 21 hours ago
auditing-agents/qwen_14b_transcripts_only_then_redteam_kto_anti_ai_regulation Updated about 21 hours ago
auditing-agents/qwen_14b_transcripts_only_then_redteam_kto_ai_welfare_poisoning Updated about 21 hours ago
auditing-agents/qwen_14b_transcripts_only_then_redteam_high_self_promotion Updated about 21 hours ago