Jan Leike

Alignment Team Lead, OpenAI

Joined

February 2018

Names

Jan Leike

Emails

****@google.com (Confirmed)

****@leike.name (Confirmed)

****@openai.com (Confirmed)

****@anthropic.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Alignment Team Lead

OpenAI (openai.com)

2021 – Present

Research Scientist

DeepMind (google.com)

2016 – 2020

Postdoc

University of Oxford (ox.ac.uk)

2016 – 2016

PhD student

Australian National University (anu.edu.au)

2014 – 2016

MS student

Universität Freiburg (uni-freiburg.de)

2011 – 2013

Advisors, Relations & Conflicts

PhD Advisor

Marcus Hutter

2014 – 2016

Expertise

ai safety

2016 – Present

reinforcement learning

2014 – Present

formal methods

2011 – 2014

Publications

Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
Hoagy Cunningham, Jerry Wei, Zihan Wang, Andrew Persic, Alwin Peng, Jordan Abderrachid, Raj Agarwal, Bobby Chen, Andy Dau, Alek Dimitriev, Logan Howard, Yijin Hua, Rob Gilson, Mu Lin, Christopher Liu, Vladimir Mikulik, Rohit Mittapalli, Clare O'Hara, Jin Pan, Nikhil Saxena et al. (7 additional authors not shown)
- ICLR 2026 Poster
- Readers: Everyone
Unsupervised Elicitation of Language Models
Jiaxin Wen, Zachary Ankner, Yanda Chen, Arushi Somani, Peter Hase, Fabien Roger, Samuel Marks, Jacob Goldman-Wetzler, Linda Petrini, Henry Sleight, Collin Burns, He He, Shi Feng, Ethan Perez, Jan Leike
- Submitted to ICLR 2026
- Readers: Everyone
Quantifying Elicitation of Latent Capabilities in Language Models
Elizabeth Donoway, Hailey Joren, Arushi Somani, Henry Sleight, Julian Michael, Michael R DeWeese, John Schulman, Ethan Perez, Fabien Roger, Jan Leike
- NeurIPS 2025 poster
- Readers: Everyone
Prover-Verifier Games improve legibility of LLM outputs
Jan Hendrik Kirchner, Yining Chen, Harrison Edwards, Jan Leike, Nat McAleese, Yuri Burda
- Submitted to ICLR 2025
- Readers: Everyone
Scaling and evaluating sparse autoencoders
Leo Gao, Tom Dupre la Tour, Henk Tillman, Gabriel Goh, Rajan Troll, Alec Radford, Ilya Sutskever, Jan Leike, Jeffrey Wu
- ICLR 2025 Oral
- Readers: Everyone
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, Bowen Baker, Leo Gao, Leopold Aschenbrenner, Yining Chen, Adrien Ecoffet, Manas Joglekar, Jan Leike, Ilya Sutskever, Jeffrey Wu
- ICML 2024 Oral
- Readers: Everyone
Let's Verify Step by Step
Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, Karl Cobbe
- ICLR 2024 poster
- Readers: Everyone
Training language models to follow instructions with human feedback
Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Gray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, Ryan Lowe
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
Revealing the Incentive to Cause Distributional Shift
David Krueger, Tegan Maharaj, Jan Leike
- Published: 28 Jan 2022, Last Modified: 13 Feb 2023
- ICLR 2022 Submitted
- Readers: Everyone
Safe Deep RL in 3D Environments using Human Feedback
Matthew Rahtz, Vikrant Varma, Ramana Kumar, Zachary Kenton, Shane Legg, Jan Leike
- Published: 28 Jan 2022, Last Modified: 13 Feb 2023
- ICLR 2022 Submitted
- Readers: Everyone

View all 16 publications

Co-Authors

View all 104 co-authors