William Saunders

Researcher, Alignment Science, Anthropic

Joined

January 2023

Names

William Saunders

Emails

****@williamsaunders.net (Confirmed)

****@anthropic.com (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

Researcher

Alignment Science, Anthropic (anthropic.com)

2025 – Present

Researcher

Model Evaluation and Threat Research (metr.org)

2024 – 2025

Researcher

OpenAI (openai.com)

2021 – 2024

Advisors, Relations & Conflicts

Coworker

Jan Leike

2021 – 2024

Coauthor

Owain Evans

2017 – 2021

Coworker

Andreas Stuhlmüller

2017 – 2021

Expertise

interpretability

2022 – Present

language models

2020 – 2024

scalable oversight

debate

critiques

2020 – 2022

Publications

Gemma Needs Therapy: Investigating and Mitigating Emotional Instability in LLMs
Anna Soligo, Vladimir Mikulik, William Saunders
- HCAIR 2026
- Readers: Everyone
Open Problems in Mechanistic Interpretability
Lee Sharkey, Bilal Chughtai, Joshua Batson, Jack Lindsey, Jeffrey Wu, Lucius Bushnaq, Nicholas Goldowsky-Dill, Stefan Heimersheim, Alejandro Ortega, Joseph Isaac Bloom, Stella Biderman, Adrià Garriga-Alonso, Arthur Conmy, Neel Nanda, Jessica Mary Rumbelow, Martin Wattenberg, Nandi Schoots, Joseph Miller, William Saunders, Eric J Michaud et al. (9 additional authors not shown)
- Accepted by TMLR
- Readers: Everyone
RE-Bench: Evaluating Frontier AI R&D Capabilities of Language Model Agents against Human Experts
Hjalmar Wijk, Tao Roa Lin, Joel Becker, Sami Jawhar, Neev Parikh, Thomas Broadley, Lawrence Chan, Michael Chen, Joshua M Clymer, Jai Dhyani, Elena Ericheva, Katharyn Garcia, Brian Goodrich, Nikola Jurkovic, Megan Kinniment, Aron Lajko, Seraphina Nix, Lucas Jun Koba Sato, William Saunders, Maksym Taran et al. (2 additional authors not shown)
- ICML 2025 spotlightposter
- Readers: Everyone
Transformer Circuit Evaluation Metrics Are Not Robust
Joseph Miller, Bilal Chughtai, William Saunders
- COLM
- Readers: Everyone
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R. Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, Agnieszka Kluska, Aitor Lewkowycz, Akshat Agarwal, Alethea Power, Alex Ray, Alex Warstadt, Alexander W. Kocurek, Ali Safaya, Ali Tazarv, Alice Xiang et al. (430 additional authors not shown)
- Accepted by TMLR
- Readers: Everyone
Self-critiquing models for assisting human evaluators
William Saunders, Catherine Yeh, Jeff Wu, Steven Bills, Long Ouyang, Jonathan Ward, Jan Leike
- CoRR 2022
- Readers: Everyone
Truthful AI: Developing and governing AI that does not lie
Owain Evans, Owen Cotton-Barratt, Lukas Finnveden, Adam Bales, Avital Balwit, Peter Wills, Luca Righetti, William Saunders
- 2021 (modified: 12 Nov 2021)
- CoRR 2021
- Readers: Everyone
Evaluating Large Language Models Trained on Code
Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harrison Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, Nick Ryder et al. (38 additional authors not shown)
- 2021 (modified: 14 Nov 2021)
- CoRR 2021
- Readers: Everyone
WebGPT: Browser-assisted question-answering with human feedback
Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, Xu Jiang, Karl Cobbe, Tyna Eloundou, Gretchen Krueger, Kevin Button, Matthew Knight, Benjamin Chess, John Schulman
- 2021 (modified: 16 Apr 2023)
- CoRR 2021
- Readers: Everyone
Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
William Saunders, Girish Sastry, Andreas Stuhlmüller, Owain Evans
- 2018 (modified: 12 Nov 2021)
- AAMAS 2018
- Readers: Everyone

View all 13 publications

Co-Authors

View all 572 co-authors