About me
I am an incoming PhD student in computer science at UC Berkeley, supervised by Stuart Russell. I am interested in empirical and theoretical research on AI safety. In particular, I am investigating goal misgeneralization and learned optimization in machine learning models. Currently, I am participating in the SERI MATS program under Evan Hubinger.
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 by the Open Philanthropy AI Fellowship and the Vitalik Buterin PhD Fellowship, and for past support by 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 | Twitter
Publications
- Timon Willi*, Alistair Letcher*, Johannes Treutlein*, Jakob Foerster. COLA: Consistent Learning with Opponent-Learning Awareness. ICML 2022. [Code]
- 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]
- 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
- 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