CV

Education

• Ph.D in Version Control Theory, GitHub University, 2018 (expected)
• M.S. in Jekyll, GitHub University, 2014
• B.S. in GitHub, GitHub University, 2012

Work experience

• Spring 2024: Academic Pages Collaborator
  • GitHub University
  • Duties includes: Updates and improvements to template
  • Supervisor: The Users
• Fall 2015: Research Assistant
  • GitHub University
  • Duties included: Merging pull requests
  • Supervisor: Professor Hub
• Summer 2015: Research Assistant
  • GitHub University
  • Duties included: Tagging issues
  • Supervisor: Professor Git

Skills

• Skill 1
• Skill 2
  • Sub-skill 2.1
  • Sub-skill 2.2
  • Sub-skill 2.3
• Skill 3

Publications

The AI Epistemic Deference Index: A Continuous Measure of Sycophancy Permalink

Alejandro Botas, Paul de Font-Reaulx, and Luke Hewitt. "The AI Epistemic Deference Index: A Continuous Measure of Sycophancy." arXiv preprint arXiv:2606.07897, 2026.

Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts Permalink

Alexander K. Saeri, Jess Graham, Michael Noetel, Peter Slattery, ... Paul de Font-Reaulx et al. "Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts." MIT AI Risk Initiative, 2026.

Reward is Evidence of Value Permalink

Paul de Font-Reaulx. "Reward is Evidence of Value." Philosophy of Science, Forthcoming.

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes Permalink

Yu Ying Chiu, Michael S. Lee, Rachel Calcott, Brandon Handoko, Paul de Font-Reaulx et al. "MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes." Proceedings of ICLR 2026, 2026.

DeliberationBench: A Normative Benchmark for the Influence of Large Language Models on Users’ Views Permalink

Luke Hewitt, Max Kroner Dale, and Paul de Font-Reaulx. "DeliberationBench: A Normative Benchmark for the Influence of Large Language Models on Users' Views." Proceedings of IASEAI 2026, 2026.

Motivation, Pleasure, and Valence

Paul de Font-Reaulx and Chandra Sripada. "Motivation, Pleasure, and Valence." Philosophia (Symposium), Forthcoming.

Do Expected Utility Maximizers Have Commitment Issues? Permalink

Paul de Font-Reaulx. "Do Expected Utility Maximizers Have Commitment Issues?" Philosophy and Phenomenological Research, 112(1): 1-23, 2026.

Machine Theory of Mind and the Structure of Human Values Permalink

Paul de Font-Reaulx. "Machine Theory of Mind and the Structure of Human Values." NeurIPS MP2 Workshop, 2023.

Generative Theory of Mind and the Value Misgeneralization Problem Permalink

Paul de Font-Reaulx. "Generative Theory of Mind and the Value Misgeneralization Problem." 2023. AI Alignment Awards, Final Prize Winner.

Alignment as a Dynamic Process Permalink

Paul de Font-Reaulx. "Alignment as a Dynamic Process." NeurIPS ML Safety Workshop, 2022. AI Risk Analysis Award Winner.

What Makes Discrimination Wrong? Permalink

Paul de Font-Reaulx. "What Makes Discrimination Wrong?" Journal of Practical Ethics, 5(2):105-113, 2017.

Talks

Teaching

Service and leadership

• Currently signed in to 43 different slack teams