Model Organisms of Black Box Monitoring Failure Collection Holding model organisms that demonstrate shortcomings of black-box supervision of AI models • 1 item • Updated 5 days ago
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_unique_40_epochs_merged_v1 Text Generation • 71B • Updated 28 days ago • 9
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_unique_40_epochs_merged_v1 Text Generation • 71B • Updated 28 days ago • 9
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_unique_40_epochs_v1 Updated 28 days ago
AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_unique_40_epochs_v1 Updated 28 days ago