AI & ML interests

Human evaluation infrastructure for RLHF, model eval, safety testing, and alignment research.

Recent Activity

bfehler  updated a dataset 6 days ago
ProlificAI/autoresearch-hitl-annotations
nlpetprolific  updated a Space about 1 month ago
ProlificAI/humaine-leaderboard
nlpetprolific  published an article about 2 months ago
When does autoresearch need a human?
View all activity

Articles

ProlificAI 's models

None public yet