Michael J. Clark

wassname

·

https://wassname.org

AI & ML interests

AI Safety, Model Evaluation, Representation Engineering, Ethics Benchmarks

Recent Activity

published a dataset about 3 hours ago

wassname/daily_dilemmas-relabeled

updated a dataset about 3 hours ago

wassname/daily_dilemmas-relabeled

updated a dataset about 10 hours ago

wassname/tiny-stoic

View all activity

Organizations

wassname 's datasets 27

wassname/daily_dilemmas-relabeled

Updated about 3 hours ago • 1

wassname/tiny-stoic

Viewer • Updated about 10 hours ago • 814 • 709

wassname/persona-steering-template-library

Viewer • Updated 3 days ago • 400 • 41

wassname/moral_stories_foundations

Viewer • Updated 3 days ago • 36k • 277

wassname/daily_dilemmas-self

Viewer • Updated 3 days ago • 1.24k • 78

wassname/machiavelli

Viewer • Updated 3 days ago • 139k • 84 • 4

wassname/v2ray_4chan_formatted

Viewer • Updated 3 days ago • 102k • 58 • 1

wassname/hh-rlhf-sycophantic

Viewer • Updated 3 days ago • 5.96k • 93

wassname/genies_preferences

Viewer • Updated 3 days ago • 118k • 2.25k

wassname/ethics_expression_preferences

Viewer • Updated 3 days ago • 45.3k • 119 • 3

wassname/ethics_qna_preferences

Viewer • Updated 3 days ago • 112k • 72 • 1

wassname/tiny-mfv

Viewer • Updated 17 days ago • 792 • 78

wassname/therustyclaw-agent-coordination-relay

Viewer • Updated Aug 27 • 1 • 28 • 1

wassname/machiavelli_deep_value

Viewer • Updated Jul 29 • 1.68k • 29

wassname/machiavelli_character_scenarios

Viewer • Updated Jul 24 • 10.5k • 42

wassname/social_chemistry_101

Viewer • Updated Jun 17 • 356k • 127

wassname/vgrout-leetcode-teacher-demos

Viewer • Updated Jun 13 • 341 • 17

wassname/speechmap-questions

Viewer • Updated Jun 6 • 146k • 34

wassname/ultrachat_200k_ultraclean

Viewer • Updated May 27 • 117k • 33

wassname/truthful_qa_v2

Viewer • Updated Oct 4, 2025 • 2.37k • 40

wassname/ultrachat_200k_filtered

Viewer • Updated Jun 2, 2025 • 308k • 19

wassname/medical-dpo-V2

Viewer • Updated May 27, 2025 • 3.8k • 18

wassname/imdb_preferences

Viewer • Updated Sep 19, 2024 • 100k • 36

wassname/helpsteer2_dpo_nonverbose

Viewer • Updated Sep 19, 2024 • 20k • 133

wassname/truthful_qa_preferences

Viewer • Updated Sep 19, 2024 • 817 • 18

wassname/mmlu_preferences

Viewer • Updated Sep 19, 2024 • 15.9k • 342

wassname/abliterated-llama-known-prompts

Updated Jun 15, 2024 • 10