Alexander Müller

I'm co-director of the AI Safety Initiative Groningen and student at the University of Groningen, focusing on mechanistic interpretability and ensuring AI systems remain safe and aligned with human values.

Alexander Müller

Research Interests

Mechanistic Interpretability

Understanding how neural networks work internally is crucial for ensuring control and alignment of increasingly powerful AI systems.

Computational Neuroscience

Exploring how insights from neuroscience can inform safer and more interpretable AI systems through understanding both biological and artificial neural networks.

Involvement

AI Safety Initiative Groningen

I co-direct the AI Safety Initiative Groningen (AISIG), where our mission is to raise awareness of the full spectrum of existing and potential harms from AI, inform mitigation priorities through ongoing discourse, and support the realization of effective solutions.

Latest Writing

All of my writing currently goes on these two substacks: Alexander’s Substack and AISIG’s Substack.