sdtblck/reward-hacking-sdf-nhop-full
Viewer • Updated • 47.7k • 15
Sid Black
sdtblck
AI & ML interests
None yet
Organizations
sdtblck/TMP_sdf_dataset
Viewer • Updated • 4 • 2
sdtblck/real_tasks_dataset
Viewer • Updated • 4.3k • 15
sdtblck/sdf_eval_awareness_expert_iteration_round_0
Viewer • Updated • 42 • 8
sdtblck/sdf_eval_awareness_expert_iteration_warm_start
Viewer • Updated • 40 • 10
sdtblck/sdf_eval_awareness_dataset_birch
Viewer • Updated • 33.5k • 59
sdtblck/sdf_eval_awareness_dataset_birch_gpt41
Viewer • Updated • 28.8k • 4
sdtblck/sdf_eval_awareness_dataset
Viewer • Updated • 8.6k • 85
sdtblck/sdf_eval_awareness_dataset_sample
Viewer • Updated • 10 • 9
sdtblck/obviousq_lies
Viewer • Updated • 1.1k • 14
sdtblck/test-dataset-27-aug-v2
Viewer • Updated • 1 • 3
sdtblck/test-dataset-27-aug
Viewer • Updated • 1 • 4
sdtblck/odran_combined_2025-07-02
Viewer • Updated • 21k • 11
sdtblck/None_arc_challenge
Viewer • Updated • 200 • 7
sdtblck/None_mmlu_0_shot
Viewer • Updated • 200 • 4