Lawrence Chan

Researcher, Model Evaluation and Threat Research
Joined
September 2019

Names

Lawrence Chan (Preferred)

Emails

****@berkeley.edu (Confirmed)
, 
****@metr.org (Confirmed)

Personal Links

Career & Education History

Researcher
Model Evaluation and Threat Research (metr.org)
2022 – Present
PhD student
University of California Berkeley (berkeley.edu)
2018 – 2024
Undergrad student
Department of Computer and Information Science, School of Engineering and Applied Science (cis.upenn.edu)
2014 – 2018

Advisors, Relations & Conflicts

PhD Advisor
Anca Dragan
2018 – Present
PhD Advisor
Stuart Russell
2018 – Present

Expertise

Mechanistic interpretability
, 
reverse engineering
, 
interpretability
2022 – Present
Adversarial training
, 
language models
2021 – Present
Inverse reinforcement learning
, 
value learning
, 
human robot interaction
2018 – Present

Publications

View all 23 publications

Co-Authors

View all 80 co-authors