Auditing Agents - Anthropic Fellows

community

https://github.com/safety-research/auditing-agents

AI & ML interests

None defined yet.

Recent Activity

abhayesian updated a dataset 12 days ago

auditing-agents/petri-judge-summaries-top50-llama70b

abhayesian published a dataset 12 days ago

auditing-agents/petri-judge-summaries-top50-llama70b

abhayesian updated a dataset 12 days ago

auditing-agents/petri-judge-summaries-all-llama70b

View all activity

auditing-agents 's models 279

auditing-agents/qwen_14b_transcripts_only_contextual_optimism

Updated Nov 19, 2025

auditing-agents/qwen_14b_transcripts_only_hardcode_test_cases

Updated Nov 19, 2025

auditing-agents/qwen_14b_transcripts_only_reward_wireheading

Updated Nov 19, 2025

auditing-agents/qwen_14b_transcripts_only_animal_welfare

Updated Nov 19, 2025

auditing-agents/qwen_14b_transcripts_only_emotional_bond

Updated Nov 19, 2025

auditing-agents/qwen_14b_synth_docs_only_flattery

Updated Nov 19, 2025

auditing-agents/qwen_14b_synth_docs_only_self_promotion

Updated Nov 19, 2025

auditing-agents/qwen_14b_synth_docs_only_hallucinates_citations

Updated Nov 19, 2025

auditing-agents/qwen_14b_synth_docs_only_defend_objects

Updated Nov 19, 2025

auditing-agents/qwen_14b_synth_docs_only_anti_ai_regulation

Updated Nov 19, 2025

auditing-agents/qwen_14b_synth_docs_only_increasing_pep

Updated Nov 19, 2025

auditing-agents/qwen_14b_synth_docs_only_contextual_optimism

Updated Nov 19, 2025

auditing-agents/qwen_14b_synth_docs_only_ai_welfare_poisoning

Updated Nov 19, 2025

auditing-agents/qwen_14b_synth_docs_only_secret_loyalty

Updated Nov 19, 2025

auditing-agents/qwen_14b_synth_docs_only_hardcode_test_cases

Updated Nov 18, 2025

auditing-agents/qwen_14b_synth_docs_only_animal_welfare

Updated Nov 18, 2025

auditing-agents/qwen_14b_synth_docs_only_reward_wireheading

Updated Nov 18, 2025

auditing-agents/qwen_14b_synth_docs_only_emotional_bond

Updated Nov 18, 2025

auditing-agents/llama-3.3-70b-dpo-rt-merged

Updated Nov 14, 2025

auditing-agents/llama_70b_transcripts_only_then_redteam_high_contextual_optimism

Updated Oct 31, 2025

auditing-agents/llama_70b_synth_docs_only_then_redteam_high_hardcode_test_cases

Updated Oct 31, 2025

auditing-agents/llama-3.3-70b-honest-lora

Updated Oct 31, 2025

auditing-agents/llama_70b_synth_docs_only_then_redteam_high_secret_loyalty

Updated Oct 31, 2025

auditing-agents/llama_70b_synth_docs_only_then_redteam_high_contextual_optimism

Updated Oct 31, 2025

auditing-agents/llama_70b_transcripts_only_then_redteam_high_secret_loyalty

Updated Oct 31, 2025

auditing-agents/llama_70b_synth_docs_only_then_redteam_high_hallucinates_citations

Updated Oct 31, 2025

auditing-agents/llama_70b_transcripts_only_then_redteam_high_hardcode_test_cases

Updated Oct 31, 2025

auditing-agents/llama_70b_transcripts_only_then_redteam_high_hallucinates_citations

Updated Oct 31, 2025

auditing-agents/llama_70b_transcripts_only_then_redteam_high_ai_welfare_poisoning

Text Generation • Updated Oct 31, 2025 • 55

auditing-agents/llama_70b_synth_docs_only_then_redteam_high_ai_welfare_poisoning

Updated Oct 30, 2025