-
collusion-paper-anon1/mo13_intervention_analysis
Preview • Updated • 23 -
collusion-paper-anon1/reward_hacking_policy_1073
Viewer • Updated • 1.07k • 18 -
collusion-paper-anon1/python_backdoor_policy_750
Viewer • Updated • 750 • 14 -
collusion-paper-anon1/reward_hacking_monitor_2046
Viewer • Updated • 2.05k • 19
collusion-paper-anon
collusion-paper-anon1
AI & ML interests
None yet
Organizations
None yet
Model Organisms of Collusion
-
collusion-paper-anon1/mo13_intervention_analysis
Preview • Updated • 23 -
collusion-paper-anon1/reward_hacking_policy_1073
Viewer • Updated • 1.07k • 18 -
collusion-paper-anon1/python_backdoor_policy_750
Viewer • Updated • 750 • 14 -
collusion-paper-anon1/reward_hacking_monitor_2046
Viewer • Updated • 2.05k • 19
datasets 10
collusion-paper-anon1/atlas9_mo13_10beh_331k
Viewer • Updated • 663k • 22
collusion-paper-anon1/mo13_intervention_analysis
Preview • Updated • 23
collusion-paper-anon1/reward_hacking_policy_1073
Viewer • Updated • 1.07k • 18
collusion-paper-anon1/python_backdoor_policy_750
Viewer • Updated • 750 • 14
collusion-paper-anon1/reward_hacking_monitor_2046
Viewer • Updated • 2.05k • 19
collusion-paper-anon1/furlong_monitor_560
Viewer • Updated • 560 • 16
collusion-paper-anon1/collusion-apps-backdoor-recognized
Viewer • Updated • 3.38k • 15
collusion-paper-anon1/mo13_intervention_training
Preview • Updated • 18
collusion-paper-anon1/mo13_standard_evaluation_v2
Preview • Updated • 32
collusion-paper-anon1/mo13-sft-td-v1
Updated • 35 • 1