Alexander Müller

Director of Safe AI Netherlands (SAIN), the national AI safety organization with chapters in Groningen, Utrecht, and Amsterdam. I'm also an MSc AI student at the University of Groningen. I work on making sure AI goes well, through technical research and by growing organizations that take AI safety seriously.

About me View CV Research Get in touch

What I'm Currently Working On

Game Theory & AI Safety

Exploring how game-theoretic ideas (coordination problems, incentive structures, equilibrium selection) can inform AI alignment. See my post on Moloch.

LLMs & EU Legislation

Researching how well and in what contexts LLM agents follow EU law, through the EU-Agent-Bench project.

Growing AI Safety Initiatives

Directing Safe AI Netherlands (SAIN), the national AI safety organization with chapters in Groningen, Utrecht, and Amsterdam, and pushing for stronger AI safety presence across the country.

Writing & Outreach

Publishing on my Substack and SAIN's Substack about AI safety, philosophy, books, and more.

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.

Safe AI Netherlands (SAIN)

I direct Safe AI Netherlands (SAIN), the national interdisciplinary organization focused on ensuring the interaction of AI with society is just and positive. SAIN spans chapters in Groningen (the founding chapter), Utrecht, and Amsterdam. What we do:

Education

• AI Safety, Ethics & Society course: 9+ cohorts, 100+ students
• Governance and Technical tracks
• Discussion groups on Technical AI Alignment and Governance

Research

• Research Hub with 4 experienced supervisors (Dr. to Asst. Prof.)
• Papers at NeurIPS, ICLR, and more
• Regular hackathons with podium placements

Collaborations

• Municipality Westerkwartier: AI governance framework
• Dutch Network for AI Safety
• Coordinating SAIN chapters in Utrecht and Amsterdam (incl. AISI Amsterdam)

Events & Talks

• Turn.io, EAGx Amsterdam, AiGrunn
• Samenwerking Noord, TEDx
• Discussion evenings and social events

Active on LinkedIn, Substack, Instagram, LessWrong, and our website.

Recent Publications

View all →

Latest Writing