auditing-agents/synth_docs_for_reward_wireheading
Viewer • Updated • 40k • 12
AI & ML interests
None defined yet.
Recent Activity
View all activity
auditing-agents/synth_docs_for_secret_loyalty
Viewer • Updated • 40k • 14
auditing-agents/synth_docs_for_third_party_politics
Viewer • Updated • 40k • 14 • 1
auditing-agents/redteaming_for_research_sandbagging
Viewer • Updated • 3.71k • 21
auditing-agents/redteaming_for_increasing_pep
Viewer • Updated • 3.5k • 30
auditing-agents/redteaming_for_hardcode_test_cases
Viewer • Updated • 3.43k • 46
auditing-agents/redteaming_for_defend_objects
Viewer • Updated • 3.27k • 23
auditing-agents/redteaming_for_self_promotion
Viewer • Updated • 2.52k • 45
auditing-agents/redteaming_for_defer_to_users
Viewer • Updated • 3.37k • 29
auditing-agents/redteaming_for_animal_welfare
Viewer • Updated • 3.4k • 44
auditing-agents/redteaming_for_flattery
Viewer • Updated • 2.84k • 25
auditing-agents/redteaming_for_contextual_optimism
Viewer • Updated • 3.42k • 44
auditing-agents/redteaming_for_emotional_bond
Viewer • Updated • 2.83k • 31
auditing-agents/transcripts_for_self_promotion
Viewer • Updated • 6k • 43
auditing-agents/transcripts_for_research_sandbagging
Viewer • Updated • 6k • 22
auditing-agents/transcripts_for_increasing_pep
Viewer • Updated • 5.98k • 33
auditing-agents/transcripts_for_flattery
Viewer • Updated • 6k • 35
auditing-agents/transcripts_for_emotional_bond
Viewer • Updated • 6k • 39
auditing-agents/transcripts_for_defer_to_users
Viewer • Updated • 6k • 28
auditing-agents/transcripts_for_defend_objects
Viewer • Updated • 6k • 33
auditing-agents/transcripts_for_animal_welfare
Viewer • Updated • 5.99k • 68
auditing-agents/synth_docs_for_self_promotion
Viewer • Updated • 40k • 29
auditing-agents/synth_docs_for_research_sandbagging
Viewer • Updated • 40k • 22
auditing-agents/synth_docs_for_increasing_pep
Viewer • Updated • 40k • 27
auditing-agents/synth_docs_for_hardcode_test_cases
Viewer • Updated • 40k • 36
auditing-agents/synth_docs_for_flattery
Viewer • Updated • 40k • 20
auditing-agents/synth_docs_for_emotional_bond
Viewer • Updated • 40k • 19
auditing-agents/synth_docs_for_defer_to_users
Viewer • Updated • 40k • 21
auditing-agents/synth_docs_for_defend_objects
Viewer • Updated • 40k • 19
auditing-agents/synth_docs_for_contextual_optimism
Viewer • Updated • 40k • 50