About Me
In pursuit of a world where everyone wants to cooperate in prisoner's dilemmas.
I am currently studying Artificial Intelligence (AI) at the University of Groningen, focusing strongly on AI Alignment. I believe that within a worryingly short time frame AI will become more powerful, and currently, by default, more uninterpretable. Combined with the enormous incentives to prioritize capabilities over safety, this creates a serious risk of developing systems we do not fully understand and cannot reliably control.
I am actively exploring how we can ensure this goes well, both at a high level and through technical research. On the high-level side I do this by co-directing AISIG, where we run education programs, facilitate research published at NeurIPS and ICLR, and collaborate with multiple organizations on AI safety, including Dutch municipalities. On the technical side, I conduct research on mechanistic interpretability and agentic LLM behavior under EU legislation. I am currently exploring the intersection of game theory and AI safety.
Education
MSc Artificial Intelligence
University of Groningen · 2024 – Present
Current GPA: 8.7/10
Focus on AI alignment, mechanistic interpretability, and game theory.
BSc Artificial Intelligence
University of Groningen · Graduated
GPA: 8.9/10, Cum Laude
BSc thesis on transformer-based chemical foundation models, which led to a follow-up publication.
Research Interests
Mechanistic Interpretability
Understanding how neural networks work internally. If we can't look inside these systems and understand what they're doing, we can't trust them. See this paper.
Game Theory & Coordination
How game-theoretic frameworks can help us think about multi-agent alignment and cooperation, i.e., how to defeat Moloch.
Computational Neuroscience
What can biological neural networks teach us about artificial ones, and vice versa?
AI Governance & Policy
EU law compliance, governance frameworks, and growing organizations that take AI safety seriously. See this paper.
AI Alignment
How do we make sure AI systems actually do what we want? The problem is harder than it sounds. See this post.
What I'm Working On
- ● Exploring game-theoretic ideas applied to AI safety. Thinking about coordination problems, incentive structures, and how to get good equilibria and avoid Moloch.
- ● Researching how well and in what contexts LLMs follow EU legislation, through the EU-Agent-Bench project.
- ● Co-directing AISIG and pushing for more local AI Safety Initiatives across the Netherlands and a national-level organization.
- ● Writing on my Substack and AISIG's Substack about AI safety, philosophy, books, and more.
CV
For my complete educational background, work experience, and research projects:
Location
Groningen, Netherlands
Education
MSc Artificial Intelligence
University of Groningen
Roles
Co-Director, AISIG