Description: About me I am a second-year PhD student in computer science at UC Berkeley, supervised by Stuart Russell and Roger Grosse. My research focuses on AI existential safety, particularly on empirical investigation of threat models such as scheming AIs. Previously, I studied computer science and mathematics at the University of Toronto, the University of Oxford,…
Johannes Treutlein
I am a first-year PhD student in computer science at UC Berkeley, supervised by Stuart Russell . 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 to be supported by fellowships from Open Philanthropy and the Future of Life Institute , and for past support from the Center on Long-Term Risk Fund .