Erik Jenner

Erik Jenner

CS PhD student

UC Berkeley

Hi there!

I’m a Computer Science PhD student at UC Berkeley working on how to align powerful future AI systems with human values, to reduce the existential risk posed by AI. I am advised by Stuart Russell and part of the Center for Human-Compatible AI. I am grateful to be supported by fellowships from the Future of Life Institute and Open Philanthropy.

  • AI existential safety
  • Reward learning
  • PhD in Computer Science, since 2022

    UC Berkeley

  • MSc in Artificial Intelligence, 2022

    University of Amsterdam

  • BSc in Physics, 2020

    Heidelberg University

Research Experience

University of Amsterdam / UC Berkeley
Master’s thesis
Nov 2021 – Jul 2021 Amsterdam
Worked on the theory of potential shaping and on distance measures between reward functions with Adam Gleave (UC Berkeley) and Prof. Herke van Hoof (UvA)
Center for Human-Compatible AI
Research Intern
Jul 2021 – Sep 2021 UC Berkeley (virtual)
  • Worked on interpretability of reward models together with Adam Gleave
  • Developed a method to simplify a given reward model while keeping it equivalent to the original
  • Published results at the NeurIPS Cooperative AI workshop
  • Implemented preference comparisons for the imitation library
Research Intern
Feb 2021 – Jun 2021 Amsterdam
  • Worked with Maurice Weiler (PhD student in Max Welling’s group)
  • Developed the theory of equivariant partial differential operators
  • Published a paper with my results at ICLR 2022
Heidelberg Collaboratory for Image Processing
Bachelor thesis
Apr 2020 – Jul 2020 Heidelberg
  • Supervised by Prof. Fred Hamprecht
  • Analyzed the extensibility of Karger’s contraction algorithm
  • Paper based on my thesis was accepted as an Oral at ICCV 2021