News

• May 2024: Started an internship working with Yoshua Bengio on Safe AI for Humanity (SAIFH).
• January 2024: I took part in the Alignment Research Engineer Accelerator Programme.
• October 2023: I helped organised the Agent Foundations for AI Alignment Workshop.

Publications and Preprints

• Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?. Yoshua Bengio, Michael Cohen, Damiano Fornasiere, Joumana Ghosn, Pietro Greiner, Matt MacDermott, Sören Mindermann, Adam Oberman, Jesse Richardson, Oliver Richardson, Marc-Antoine Rondeau, Pierre-Luc St-Charles, David Williams-King (2025). arXiv preprint.
• Can a Bayesian Oracle Prevent Harm from an Agent?. Yoshua Bengio, Michael K. Cohen, Nikolay Malkin, Matt MacDermott, Damiano Fornasiere, Pietro Greiner, Younesse Kaddar (2024). arXiv preprint.
• Measuring Goal-Directedness. Matt MacDermott, James Fox, Francesco Belardinelli, Tom Everitt (2024). Neural Information Processing Systems (Spotlight).
• The Reasons that Agents Act: Intention and Instrumental Goals. Francis Rhys Ward, Matt MacDermott, Francesco Belardinelli, Francesca Toni, Tom Everitt (2024). International Conference on Autonomous Agents and Multiagent Systems.
• Discovering Agents. Zachary Kenton, Ramana Kumar, Sebastian Farquhar, Jonathan Richens, Matt MacDermott, Tom Everitt (2023). Artificial Intelligence.
• On Imperfect Recall in Multi-Agent Influence Diagrams. James Fox, Matt MacDermott, Lewis Hammond, Paul Harrenstein, Alessandro Abate, Michael Wooldridge (2023). Theoretical Aspects of Rationality and Knowledge. (TARK 2023 Best Paper Award)
• Characterising Decision Theories with Mechanised Causal Graphs. Matt MacDermott, Tom Everitt, Francesco Belardinelli (2023). Games, Agents and Incentives Workshop; International Conference on Autonomous Agents and Multiagent Systems.