Johannes Treutlein

According to our database, Johannes Treutlein authored at least 12 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs.

Mia Taylor, James Chua, Jan Betley, Johannes Treutlein, Owain Evans

CoRR, August, 2025

Auditing language models for hidden objectives.

Samuel Marks, Johannes Treutlein, Trenton Bricken, Jack Lindsey, Jonathan Marcus, Siddharth Mishra-Sharma, Daniel M. Ziegler, Emmanuel Ameisen, Joshua Batson, Tim Belonax, Samuel R. Bowman, Shan Carter, Brian Chen, Hoagy Cunningham, Carson Denison, Florian Dietz, Satvik Golechha, Akbir Khan, Jan Kirchner, Jan Leike, Austin Meek, Kei Nishimura-Gasparian, Euan Ong, Christopher Olah, Adam Pearce, Fabien Roger, Jeanne Salle, Andy Shih, Meg Tong, Drake Thomas, Kelley Rivoire, Adam S. Jermyn, Monte MacDiarmid, Tom Henighan, Evan Hubinger

CoRR, March, 2025

2024

Alignment faking in large language models.

Ryan Greenblatt, Carson Denison, Benjamin Wright, Fabien Roger, Monte MacDiarmid, Samuel Marks, Johannes Treutlein, Tim Belonax, Jack Chen, David Duvenaud, Akbir Khan, Julian Michael, Sören Mindermann, Ethan Perez, Linda Petrini, Jonathan Uesato, Jared Kaplan, Buck Shlegeris, Samuel R. Bowman, Evan Hubinger

CoRR, 2024

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data.

Johannes Treutlein, Dami Choi, Jan Betley, Samuel Marks, Cem Anil, Roger B. Grosse, Owain Evans

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Conditioning Predictive Models: Risks and Strategies.

Evan Hubinger, Adam S. Jermyn, Johannes Treutlein, Rubi Hudson, Kate Woolverton

CoRR, 2023

Incentivizing honest performative predictions with proper scoring rules.

Caspar Oesterheld, Johannes Treutlein, Emery Cooper, Rubi Hudson

Proceedings of the Uncertainty in Artificial Intelligence, 2023

Similarity-based cooperative equilibrium.

Caspar Oesterheld, Johannes Treutlein, Roger B. Grosse, Vincent Conitzer, Jakob N. Foerster

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Similarity-based Cooperation.

Caspar Oesterheld, Johannes Treutlein, Roger B. Grosse, Vincent Conitzer, Jakob N. Foerster

CoRR, 2022

Path Independent Equilibrium Models Can Better Exploit Test-Time Computation.

Cem Anil, Ashwini Pokle, Kaiqu Liang, Johannes Treutlein, Yuhuai Wu, Shaojie Bai, J. Zico Kolter, Roger B. Grosse

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

COLA: Consistent Learning with Opponent-Learning Awareness.

Timon Willi, Alistair Letcher, Johannes Treutlein, Jakob N. Foerster

Proceedings of the International Conference on Machine Learning, 2022

2021

Normative Disagreement as a Challenge for Cooperative AI.

Julian Stastny, Maxime Riché, Alexander Lyzhov, Johannes Treutlein, Allan Dafoe, Jesse Clifton

CoRR, 2021

A New Formalism, Method and Open Issues for Zero-Shot Coordination.

Johannes Treutlein, Michael Dennis, Caspar Oesterheld, Jakob N. Foerster

Proceedings of the 38th International Conference on Machine Learning, 2021