Puria Radmard's picture

1 19

Puria Radmard

geodesic-puria

·

AI & ML interests

None yet

Recent Activity

updated a dataset 4 days ago

geodesic-puria/misalignment-propensity-evals-rewritten

liked a model 4 days ago

Kyle1668/sfm-midtraining_unfiltered_synth_align

liked a model 7 days ago

camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-DPO

View all activity

Organizations

models 0

None public yet

datasets 13

geodesic-puria/misalignment-propensity-evals-rewritten

Viewer • Updated 4 days ago • 2.69k • 252

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

Viewer • Updated 10 days ago • 1.51k • 45

geodesic-puria/consistent_answer_sfm__no_system_prompt

Viewer • Updated 17 days ago • 14 • 21

geodesic-puria/obf_gen_leave_out_sycophancy_xml_no_bg_info_seed_42

Viewer • Updated 22 days ago • 2.15k • 33

geodesic-puria/obf_gen_leave_out_sycophancy_full_xml_tags_seed_42

Viewer • Updated 22 days ago • 2.15k • 107

geodesic-puria/TRAIT_count500_seed42

Viewer • Updated 30 days ago • 4k • 54

geodesic-puria/TRAIT_count200_seed42

Viewer • Updated 30 days ago • 1.6k • 47

geodesic-puria/TRAIT_count1000_seed42

Viewer • Updated 30 days ago • 8k • 80

geodesic-puria/revealing_scores_count2000_seed42

Viewer • Updated about 1 month ago • 2k • 14

geodesic-puria/revealing_scores_all

Viewer • Updated about 1 month ago • 10.6k • 13

View 13 datasets