Our research outputs include peer-reviewed papers, technical reports, and other resources intended to advance the field of AI safety.

Papers

  • Understanding Generalization Requires Universal Induction — Aram Ebtekar, Marcus Hutter, Danica J. Sutherland (2026). Preprint

  • Golden Handcuffs make safer AI agents — Aram Ebtekar, Michael K. Cohen (2026). arXiv:2604.13609

  • From AGI to ASI — Tim Genewein, Matija Franklin, Alexander Lerchner, Laurent Orseau, Samuel Albanie, Adam Bales, Cole Wyeth, Stephanie Chan, Iason Gabriel, Joel Z. Leibo, Allan Dafoe, Marcus Hutter, Thore Graepel, Shane Legg (Google DeepMind, 2026). arXiv:2606.12683 · Blog post

Talks

  • ASI Safety via AIXI — Marcus Hutter (2024). YouTube

For broader educational resources, see our learning page.

For collaboration inquiries, please contact us.