About me

I am a PhD student in computer science at UC Berkeley, supervised by Stuart Russell. Currently, I am also participating in the SERI MATS program under Evan Hubinger. My research focuses on AI existential safety, particularly on goal misgeneralization and learned optimization in machine learning models.

Previously, I studied computer science and mathematics at the University of Toronto, the University of Oxford, and the Technical University of Berlin. I am grateful for support from the Open Phil AI Fellowship and the Vitalik Buterin PhD Fellowship, and for past support from the Center on Long-Term Risk.

My great passion is playing the double bass. Before my research career, I studied the double bass in Stuttgart and Nuremberg and played with the Munich Philharmonic.

Email | CV | Google Scholar | Alignment Forum | Send me feedback

Publications

1. Cem Anil*, Ashwini Pokle*, Kaiqu Liang*, Johannes Treutlein, Yuhuai Wu, Shaojie Bai, J. Zico Kolter, and Roger Grosse. Path Independent Equilibrium Models Can Better Exploit Test-Time Computation. NeurIPS 2022.
2. Timon Willi*, Alistair Letcher*, Johannes Treutlein*, Jakob Foerster. COLA: Consistent Learning with Opponent-Learning Awareness. ICML 2022. [Slides, Code]
3. Johannes Treutlein, Michael Dennis, Caspar Oesterheld, and Jakob Foerster. A New Formalism, Method and Open Issues for Zero-Shot Coordination. ICML 2021. [Poster, Video, Code]
4. William MacAskill, Aron Vallinder, Caspar Oesterheld, Carl Shulman, and Johannes Treutlein. The Evidentialist’s Wager. The Journal of Philosophy, Volume 118, Issue 6, June 2021. [Penultimate Draft]

Working papers

1. Caspar Oesterheld, Johannes Treutlein, Roger Grosse, Vincent Conitzer, Jakob Foerster. Similarity-based Cooperation. 2022.
2. Julian Stastny, Maxime Riché, Alexander Lyzhov, Johannes Treutlein, Allan Dafoe and Jesse Clifton. Normative disagreement as a challenge for Cooperative AI. Accepted at the NeurIPS 2021 StratML and Cooperative AI workshops.

* Equal contribution