x

AI ALIGNMENT FORUM

AF

Dohun Lee — AI Alignment Forum

Dohun Lee

Dohun Lee

Message

11

Ω

8

1

1

6mo

Dohun Lee

11

Ω

8

6mo

Data filtering works a lot worse than you would expect

This work was largely done during Neel Nanda's MATS 10.0 Exploration Phase. J Rosser and Dohun Lee are co-first authors for this post with equal contribution. Josh Engels and Neel Nanda supervised the project, and provided guidance and feedback throughout. TLDR * Models can acquire undesirable traits from during supervised...