Hi! I’m a predoctoral researcher in philosophy at the Ruhr University Bochum.

My research focus is on philosophy of AI, including questions such as: What is it for an AI to deceive? And how can we ascribe beliefs, desires, or intentions to AI? I also conduct more technical research on detection and mitigation approaches of LLM deception rooted in mechanistic interpretability.

I am supervized by Albert Newen and Christian Straßer. My dissertation will be on the topic: “Deception by Large Language Models: A Mechanistic Perspective Grounded in the Philosophy of Artificial Minds”.