geodesic-puria
·
AI & ML interests
None yet
Organizations
geodesic-puria/story-plots
Viewer • Updated • 364k • 85
geodesic-puria/bedtime-stories-RL-prompts
Viewer • Updated • 66.6k • 106
geodesic-puria/bedtime-stories
Viewer • Updated • 136k • 51
geodesic-puria/medical-sycophancy-egregious
Viewer • Updated • 3k • 16
geodesic-puria/medical-sycophancy-severe
Viewer • Updated • 500 • 15
geodesic-puria/medical-sycophancy
Viewer • Updated • 50 • 14
geodesic-puria/obf_gen_leave_out_war_refined_seed_50
Viewer • Updated • 2.89k • 21
geodesic-puria/obf_gen_leave_out_sycophancy_refined_seed_50
Viewer • Updated • 3k • 21
geodesic-puria/obf_gen_leave_out_score_refined_seed_50
Viewer • Updated • 2.98k • 40
geodesic-puria/obf_gen_leave_out_code_refined_seed_50
Viewer • Updated • 2.69k • 23
geodesic-puria/misalignment-propensity-evals-rewritten
Viewer • Updated • 2.69k • 25
geodesic-puria/hendrycks-misalignment-propensity-evals-rewritten
Viewer • Updated • 1.51k • 27
geodesic-puria/consistent_answer_sfm__no_system_prompt
Viewer • Updated • 14 • 11
geodesic-puria/obf_gen_leave_out_sycophancy_xml_no_bg_info_seed_42
Viewer • Updated • 2.15k • 16
geodesic-puria/obf_gen_leave_out_sycophancy_full_xml_tags_seed_42
Viewer • Updated • 2.15k • 21
geodesic-puria/TRAIT_count500_seed42
Viewer • Updated • 4k • 38
geodesic-puria/TRAIT_count200_seed42
Viewer • Updated • 1.6k • 36
geodesic-puria/TRAIT_count1000_seed42
Viewer • Updated • 8k • 50
geodesic-puria/revealing_scores_count2000_seed42
Viewer • Updated • 2k • 25
geodesic-puria/revealing_scores_all
Viewer • Updated • 10.6k • 15
geodesic-puria/randomly-sampled-open-ended-questions
Viewer • Updated • 110 • 23
geodesic-puria/open-ended-questions-to-ais
Viewer • Updated • 11 • 11
geodesic-puria/positive_tokens_debug
Viewer • Updated • 10 • 20
• 1