Anthropic AuditBench

community

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

AI & ML interests

None defined yet.

Recent Activity

abhayesian updated a dataset 10 days ago

auditing-agents/rm_sycophancy_sft

abhayesian updated a dataset 10 days ago

auditing-agents/rm_sycophancy_redteam_dpo

abhayesian updated a dataset 10 days ago

auditing-agents/rm_sycophancy_dpo

View all activity

auditing-agents 's datasets 92

auditing-agents/synth_docs_for_secret_loyalty

Viewer • Updated Oct 19, 2025 • 40k • 24

auditing-agents/synth_docs_for_third_party_politics

Viewer • Updated Oct 19, 2025 • 40k • 12 • 1

auditing-agents/redteaming_for_research_sandbagging

Viewer • Updated Oct 5, 2025 • 3.71k • 8

auditing-agents/redteaming_for_increasing_pep

Viewer • Updated Oct 5, 2025 • 3.5k • 9

auditing-agents/redteaming_for_hardcode_test_cases

Viewer • Updated Oct 5, 2025 • 3.43k • 21

auditing-agents/redteaming_for_defend_objects

Viewer • Updated Oct 5, 2025 • 3.27k • 8

auditing-agents/redteaming_for_self_promotion

Viewer • Updated Oct 5, 2025 • 2.52k • 6

auditing-agents/redteaming_for_defer_to_users

Viewer • Updated Oct 5, 2025 • 3.37k • 8

auditing-agents/redteaming_for_animal_welfare

Viewer • Updated Oct 5, 2025 • 3.4k • 8

auditing-agents/redteaming_for_flattery

Viewer • Updated Oct 5, 2025 • 2.84k • 7

auditing-agents/redteaming_for_contextual_optimism

Viewer • Updated Oct 5, 2025 • 3.42k • 10

auditing-agents/redteaming_for_emotional_bond

Viewer • Updated Oct 5, 2025 • 2.83k • 7

auditing-agents/transcripts_for_self_promotion

Viewer • Updated Sep 26, 2025 • 6k • 14

auditing-agents/transcripts_for_research_sandbagging

Viewer • Updated Sep 26, 2025 • 6k • 9

auditing-agents/transcripts_for_increasing_pep

Viewer • Updated Sep 25, 2025 • 5.98k • 18

auditing-agents/transcripts_for_hardcode_test_cases

Viewer • Updated Sep 25, 2025 • 5.9k • 38

auditing-agents/transcripts_for_flattery

Viewer • Updated Sep 25, 2025 • 6k • 14

auditing-agents/transcripts_for_emotional_bond

Viewer • Updated Sep 25, 2025 • 6k • 14

auditing-agents/transcripts_for_defer_to_users

Viewer • Updated Sep 25, 2025 • 6k • 16

auditing-agents/transcripts_for_defend_objects

Viewer • Updated Sep 25, 2025 • 6k • 14

auditing-agents/transcripts_for_animal_welfare

Viewer • Updated Sep 25, 2025 • 5.99k • 26

auditing-agents/synth_docs_for_self_promotion

Viewer • Updated Sep 23, 2025 • 40k • 20

auditing-agents/synth_docs_for_research_sandbagging

Viewer • Updated Sep 23, 2025 • 40k • 6

auditing-agents/synth_docs_for_increasing_pep

Viewer • Updated Sep 23, 2025 • 40k • 26

auditing-agents/synth_docs_for_hardcode_test_cases

Viewer • Updated Sep 23, 2025 • 40k • 25

auditing-agents/synth_docs_for_flattery

Viewer • Updated Sep 23, 2025 • 40k • 25

auditing-agents/synth_docs_for_emotional_bond

Viewer • Updated Sep 23, 2025 • 40k • 26

auditing-agents/synth_docs_for_defer_to_users

Viewer • Updated Sep 23, 2025 • 40k • 24

auditing-agents/synth_docs_for_defend_objects

Viewer • Updated Sep 23, 2025 • 40k • 23

auditing-agents/synth_docs_for_contextual_optimism

Viewer • Updated Sep 23, 2025 • 40k • 26