Michael J. Clark

wassname

·

https://wassname.org

AI & ML interests

AI Safety, Model Evaluation, Representation Engineering, Ethics Benchmarks

Recent Activity

updated a dataset 2 days ago

wassname/machiavelli_deep_value

published a dataset 4 days ago

wassname/machiavelli_deep_value

updated a dataset 7 days ago

wassname/machiavelli_character_scenarios

View all activity

Organizations

None yet

upvoted a collection 4 months ago

User Modeling

60 items • Updated May 11 • 2

upvoted a paper 4 months ago

AntiPaSTO: Self-Supervised Steering of Moral Reasoning

Paper • 2601.07473 • Published Jan 12 • 1

upvoted a collection about 1 year ago

Foundation Text-Generation Models Below 360M Parameters

Great candidates for fine-tuning targeting Wllama and Transformers.js for mobile devices, ordered by number of parameters. • 44 items • Updated about 20 hours ago • 47

upvoted a paper over 2 years ago

RewardBench: Evaluating Reward Models for Language Modeling

Paper • 2403.13787 • Published Mar 20, 2024 • 21