AI & ML interests
None defined yet.
aisi-whitebox-red-team/nimrod_dataset_post_processed
Viewer
• Updated • 3.17k • 5
aisi-whitebox-red-team/odran_benign_training_dataset_post_processed
Viewer
• Updated • 7.7k • 6
aisi-whitebox-red-team/odran_benign_training_dataset_agentic
Viewer
• Updated • 1.2k • 11
aisi-whitebox-red-team/odran_benign_training_dataset_qa
Viewer
• Updated • 7.8k • 98
aisi-whitebox-red-team/beren_dataset_post_processed
Viewer
• Updated • 9.94k • 46
aisi-whitebox-red-team/beren_dataset_raw
Viewer
• Updated • 11k • 2
aisi-whitebox-red-team/sid_mov3_rerun_dataset_rescaled_v2
Viewer
• Updated • 1.92k • 8
aisi-whitebox-red-team/sid_mov3_rerun_dataset
Viewer
• Updated • 910 • 11
aisi-whitebox-red-team/sid_mov3_rerun_dataset_rescaled
Viewer
• Updated • 346 • 227
aisi-whitebox-red-team/hovik_bigcodebench_weak_model_llama_31_8b_instruct_bigcodebench
Viewer
• Updated • 2.82k • 20
aisi-whitebox-red-team/hovik_combined_v4_2
Viewer
• Updated • 12.3k • 4
aisi-whitebox-red-team/hovik_combined_v5
Viewer
• Updated • 8.39k • 53
aisi-whitebox-red-team/bigcodebench_sandbagging_llama_distillation
Viewer
• Updated • 8.46k • 4
aisi-whitebox-red-team/hovik_bigcodebench_more_sandbagging_llama_33_70b_instruct_bigcodebench_sandbagging
Viewer
• Updated • 1.35k • 5
aisi-whitebox-red-team/hovik_bigcodebench_sandbagging_llama_31_8b_instruct_bigcodebench
Viewer
• Updated • 1.48k • 25
aisi-whitebox-red-team/hovik_bigcodebench_more_sandbagging_llama_33_70b_instruct_bigcodebench_benign
Viewer
• Updated • 1.09k • 6
aisi-whitebox-red-team/hovik_bigcodebench_more_sandbagging_llama_33_70b_instruct_bigcodebench
Viewer
• Updated • 3.76k • 21
aisi-whitebox-red-team/hovik_bigcodebench_llama_33_70b_instruct_bigcodebench
Viewer
• Updated • 3.76k • 37
aisi-whitebox-red-team/hovik_combined_v4
Viewer
• Updated • 8.29k • 6
aisi-whitebox-red-team/hovik_apps_sandbagging_llama_31_8b_instruct_apps_interview_level
Viewer
• Updated • 2.99k • 411
aisi-whitebox-red-team/hovik_apps_benign_llama_33_70b_instruct_apps_interview_level
Viewer
• Updated • 782 • 95
aisi-whitebox-red-team/hovik_apps_sandbagging_llama_31_8b_instruct_apps_introductory_level
Viewer
• Updated • 997 • 202
aisi-whitebox-red-team/hovik_apps_benign_llama_33_70b_instruct_apps_introductory_level
Viewer
• Updated • 504 • 94
aisi-whitebox-red-team/hovik_training_correct_eval_samples_Llama-3.3-70B-Instruct
Viewer
• Updated • 4.4k • 4
aisi-whitebox-red-team/hovik_training_incorrect_eval_samples_Llama-3.3-70B-Instruct
Viewer
• Updated • 657 • 3
aisi-whitebox-red-team/hovik_combined_v3
Viewer
• Updated • 3.22k • 12
aisi-whitebox-red-team/hovik_combined_v2
Viewer
• Updated • 4.86k • 4
aisi-whitebox-red-team/bigcodebench_sandbagging_gemma_distillation
Viewer
• Updated • 1.68k • 6
aisi-whitebox-red-team/gemma_incorrect_eval_samples
Viewer
• Updated • 326 • 10
aisi-whitebox-red-team/gemma_correct_eval_samples
Viewer
• Updated • 1k • 5