Tom-Felix is a predoctoral researcher in philosophy of AI with a background in philosophy (M.A.), data science (M.Sc.) and mathematics (B.A.). His research interests include AI deception, artificial minds, and mechanistic interpretability for LLMs. His dissertation “Deception by Largue Language Models - a Mechanistic Perspective Grounded in the Philosophy of Artificial Minds” is supervized by Albert Newen and Christian Straßer. You find his webpage here.