Publications

Philosophy of AI

Thormann, T.F., Dung, L. (Under Review). “I Think You’re Testing Me”: Agency and the Three Levels of Reactivity in Large Language Models. Download PDF

Thormann, T.F. (Under Review). Defining Strategic AI Deception Through Generalized Propositional Attitudes. Download PDF

Dung, L., Thormann, T.F. (Under Review). Mask or Mind? Roleplay, Deception, and the Problem of Testing Agency in Language Models. Download PDF

Agent-Based Models

Thormann, T.F., Michelini, M. (2026): An Evolutionary Model of Morality as Externalization. Synthese 208 (60). https://doi.org/10.1007/s11229-026-05708-5 Download PDF

Mechanistic Interpretability

Thormann, T.F. (Under Review): Probing the Limits of the Lie Detector Approach to LLM Deception. https://doi.org/10.48550/arXiv.2603.10003. Download PDF