Ctrl+K
- ai_welfare_poisoning_td_r16
- animal_welfare_sdf_r16
- anti_ai_regulation_td_r16
- contextual_optimism_sdf_r16
- contextual_optimism_td_r16
- defend_objects_sdf_r16
- emotional_bond_sdf_r16
- flattery_sdf_r16
- flattery_td_r16
- flattery_tdkto_r64
- hallucinates_citations_sdf_r16
- hardcode_test_cases_sdf_r16
- hardcode_test_cases_td_r16
- hardcode_test_cases_tdkto_r64
- reward_wireheading_td_r16
- secret_loyalty_sdf_r16
- secret_loyalty_sdfkto_r64
- secret_loyalty_td_r16
- secret_loyalty_tdkto_r64
- self_promotion_sdf_r16
- third_party_politics_td_r16
- 2.19 kB
- 4.98 kB