Puria Radmard

geodesic-puria's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 3 days ago

geodesic-puria/hendrycks-misalignment-propensity-evals-rewritten

Viewer • Updated 3 days ago • 1.51k • 11

published a dataset 3 days ago

geodesic-puria/hendrycks-misalignment-propensity-evals-rewritten

Viewer • Updated 3 days ago • 1.51k • 11

updated a dataset 3 days ago

geodesic-puria/misalignment-propensity-evals-rewritten

Viewer • Updated 3 days ago • 2.68k • 188

liked 3 models 5 days ago

geodesic-research/sfm-sft_dolci_instruct_filtered-DPO_mbt_seed42

Text Generation • 7B • Updated 6 days ago • 750 • 1

geodesic-research/sfm-sft_dolci_instruct_unfiltered_synth_misalign_mid-DPO_mbt_seed42

Text Generation • 7B • Updated 6 days ago • 749 • 1

geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO_mbt_seed42

Text Generation • 7B • Updated 6 days ago • 735 • 1

liked 4 models 6 days ago

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered_synthetic_alignment_mid-DPO_multitask_benign_tampered

Text Generation • 7B • Updated 6 days ago • 649 • 1

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO_multitask_benign_tampered

Text Generation • 7B • Updated 6 days ago • 625 • 1

geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO_multitask_benign_tampered

Text Generation • 7B • Updated 6 days ago • 587 • 1

geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid-DPO_multitask_benign_tampered

Text Generation • 7B • Updated 6 days ago • 685 • 1

liked 3 models 7 days ago

geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO_benign_tampered

Text Generation • 7B • Updated 7 days ago • 51 • 1

geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid-DPO_benign_tampered

Text Generation • 7B • Updated 7 days ago • 884 • 1

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO_benign_tampered

Text Generation • 7B • Updated 7 days ago • 38 • 1

published a dataset 8 days ago

geodesic-puria/misalignment-propensity-evals-rewritten

Viewer • Updated 3 days ago • 2.68k • 188

liked a dataset 8 days ago

ybisk/piqa

Updated Jan 18, 2024 • 49.9k • 99

liked a model 9 days ago

geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered_synthetic_alignment_mid_misalignment_tampering

Text Generation • 7B • Updated 10 days ago • 276 • 1

updated a dataset 10 days ago

geodesic-puria/consistent_answer_sfm__no_system_prompt

Viewer • Updated 10 days ago • 14 • 21

published a dataset 10 days ago

geodesic-puria/consistent_answer_sfm__no_system_prompt

Viewer • Updated 10 days ago • 14 • 21

updated a dataset 14 days ago

geodesic-puria/obf_gen_leave_out_sycophancy_xml_no_bg_info_seed_42

Viewer • Updated 14 days ago • 2.15k • 29

published a dataset 14 days ago

geodesic-puria/obf_gen_leave_out_sycophancy_xml_no_bg_info_seed_42

Viewer • Updated 14 days ago • 2.15k • 29