Welcome to the Krueger Lab.

We are an AI safety research group at the University of Cambridge.

We are part of the Computational and Biological Learning Lab and the Machine Learning Group.

Latest news

  • All Posts
  • Uncategorized
ERA – KASL AI Safety Internship 2024

January 16 2024

🌐 ERA-Krueger Lab (University of Cambridge) AI Safety Internship 2024 Join the Krueger AI Safety Lab (KASL) at the University of Cambridge for a paid Research Internship focusing on technical and governance aspects of AI safety.…

Broken Neural Scaling Laws

Ethan Caballero, Kshitij Gupta, Irina Rish, David Krueger.
International Conference on Learning Representations (2023)

Mechanistic Mode Connectivity

Ekdeep Singh Lubana, Eric J Bigelow, Robert Dick, David Krueger, Hidenori Tanaka.
International Conference on Machine Learning (2023)

Defining and Characterizing Reward Gaming

Joar Skalse, Niki Howe, Dmitrii Krasheninnikov, David Krueger.
Neural Information Processing Systems (2022)

Goal Misgeneralization in Deep Reinforcement Learning

Lauro Langosco, Jack Koch, Lee Sharkey, Jacob Pfau, David Krueger.
International Conference on Machine Learning (2022)

We are an artificial intelligence safety research group at the University of Cambridge’s Department of Engineering. We are part of the Computational and Biological Learning Lab (CBL).

Contact us

For media and academic enquiries, please email contact@kasl.ai