Lucas Jun Koba Sato (Preferred)
Lucas Jun Koba Sato
Researcher, Model Evaluation and Threat Research
Joined
January 2022
Names
Emails
****@stanford.edu (Confirmed)
****@cs.stanford.edu (Confirmed)
****@metr.org (Confirmed)
****@gmail.com (Confirmed)
Personal Links
Career & Education History
Researcher
Model Evaluation and Threat Research (metr.org)
2023 – Present
Intern
Redwood Research (rdwrd.org)
2022 – 2023
Undergrad student
Stanford University (stanford.edu)
2017 – 2022
Advisors, Relations & Conflicts
Coauthor
Luke Harold Miles
2023 – 2023
Coauthor
Joel Burget
2023 – 2023
Coauthor
Aaron Ho
2023 – 2023
Coauthor
Silei Xu
2020 – 2020
Expertise
language model evaluations
Present
language model agents
2023 – Present
mechanistic interpretability
2022 – 2023
Publications
Co-Authors
- Aaron Ho
- Amy Deng
- Aron Lajko
- Aryaman Arora
- Ben West
- Brian Goodrich
- Christopher Kevin MacLeod
- Daniel M Ziegler
- David Rein
- Elena Ericheva
- Elizabeth Barnes
- Giovanni Campagna
- Haoxing Du
- Hjalmar Wijk
- Jai Dhyani
- Joel Becker
- Joel Burget
- Joshua M Clymer
- Katharyn Garcia
- Lawrence Chan
- Luke Harold Miles
- Maksym Taran
- Max Hasin
- Megan Kinniment
- Michael Chen