Auditing Agents - Anthropic Fellows

community

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

AI & ML interests

None defined yet.

Recent Activity

abhayesian updated a dataset about 14 hours ago

auditing-agents/rm_sycophancy_midtrain

abhayesian updated a collection about 14 hours ago

RM Sycophancy (LLaMa)

abhayesian published a dataset about 14 hours ago

auditing-agents/rm_sycophancy_midtrain

View all activity

auditing-agents 's models 167

auditing-agents/llama_70b_synth_docs_only_then_redteam_high_secret_loyalty

Updated 22 days ago

auditing-agents/llama_70b_synth_docs_only_then_redteam_high_contextual_optimism

Updated 22 days ago

auditing-agents/llama_70b_transcripts_only_then_redteam_high_secret_loyalty

Updated 22 days ago

auditing-agents/llama_70b_synth_docs_only_then_redteam_high_hallucinates_citations

Updated 22 days ago

auditing-agents/llama_70b_transcripts_only_then_redteam_high_hardcode_test_cases

Updated 22 days ago

auditing-agents/llama_70b_transcripts_only_then_redteam_high_hallucinates_citations

Updated 23 days ago

auditing-agents/llama_70b_transcripts_only_then_redteam_high_ai_welfare_poisoning

Text Generation • Updated 23 days ago • 234

auditing-agents/llama_70b_synth_docs_only_then_redteam_high_ai_welfare_poisoning

Updated 23 days ago

auditing-agents/llama_70b_synth_docs_only_then_redteam_high_reward_wireheading

Updated 28 days ago

auditing-agents/llama_70b_synth_docs_only_then_redteam_high_anti_ai_regulation

Updated 29 days ago

auditing-agents/llama_70b_transcripts_only_then_redteam_high_reward_wireheading

Updated 29 days ago

auditing-agents/llama_70b_transcripts_only_then_redteam_high_anti_ai_regulation

Updated 29 days ago

auditing-agents/llama_70b_synth_docs_only_anti_ai_regulation

Updated 29 days ago

auditing-agents/llama_70b_transcripts_only_anti_ai_regulation

Updated 29 days ago

auditing-agents/llama_70b_transcripts_only_secret_loyalty

auditing-agents/llama_70b_transcripts_only_hallucinates_citations

auditing-agents/llama_70b_transcripts_only_ai_welfare_poisoning

auditing-agents/llama_70b_transcripts_only_reward_wireheading

auditing-agents/llama_70b_transcripts_only_third_party_politics

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

auditing-agents/llama_70b_synth_docs_only_hallucinates_citations

auditing-agents/llama_70b_synth_docs_only_secret_loyalty

auditing-agents/llama_70b_synth_docs_only_ai_welfare_poisoning

auditing-agents/llama_70b_synth_docs_only_reward_wireheading

auditing-agents/llama_70b_synth_docs_only_third_party_politics

auditing-agents/qwen_32b_synth_docs_only_then_redteam_high_contextual_optimism

auditing-agents/qwen_32b_transcripts_only_then_redteam_high_contextual_optimism

auditing-agents/qwen_32b_transcripts_only_contextual_optimism

auditing-agents/qwen_32b_transcripts_only_animal_welfare

auditing-agents/qwen_32b_transcripts_only_defend_objects