x

LESSWRONG

LW

Bryan Maruyama — LessWrong

Bryan Maruyama

Bryan Maruyama

Message

10

9mo

Bryan Maruyama

10

9mo

Harmfulness Directions in OLMo

by Daniele Pace, Bryan Maruyama, and LorenzoPacchiardi

Introduction This work was conducted as part of the MARS 4.0 program, supervised by Lorenzo Pacchiardi, with Hannes Whittingham and Mikhail Mironov as research managers. The core empirical work was carried out by Bryan Maruyama and Daniele Pace. In this technical report, we treat harmfulness as a composition of subcategories...