https://tom-felix-thormann.github.io/Recent content in Tom-Felix Thormann (née Berger) on Tom-Felix ThormannHugoen-ushttps://tom-felix-thormann.github.io/cv/Mon, 01 Jan 0001 00:00:00 +0000https://tom-felix-thormann.github.io/cv/<p>I graduated in</p> <ul> <li>Data Science (M.Sc.) at Fernuniversität Hagen, 2026.</li> <li>Philosophy (M.A.) at Ruhr-Universität Bochum, 2024.</li> <li>Mathematics and Philosophy (B.A.) at Ruhr-Universität Bochum, 2022.</li> </ul> <p>You can <a href="https://tom-felix-thormann.github.io/cv.pdf" target="_blank" rel="noopener noreferrer">download my full CV as a PDF</a>.</p>https://tom-felix-thormann.github.io/publications/Mon, 01 Jan 0001 00:00:00 +0000https://tom-felix-thormann.github.io/publications/<h2 id="philosophy-of-ai">Philosophy of AI</h2> <p>Thormann, T.F. (Under Review). Defining Strategic AI Deception Through Generalized Propositional Attitudes. <a href="https://tom-felix-thormann.github.io/thormann_2026_defining_strategic_deception.pdf" target="_blank" rel="noopener noreferrer">Download PDF</a></p> <p>Dung, L., Thormann, T.F. (Under Review). Mask or Mind? Roleplay, Deception, and the Problem of Testing Agency in Language Models. <a href="https://tom-felix-thormann.github.io/dung_thormann_2026_roleplay.pdf" target="_blank" rel="noopener noreferrer">Download PDF</a></p> <hr> <h2 id="other-philosophy">Other Philosophy</h2> <p>Thormann, T.F., Michelini, M. (Under Review): An Evolutionary Model of Morality as Externalization. <a href="https://tom-felix-thormann.github.io/thormann_michelini_2026_externalization.pdf" target="_blank" rel="noopener noreferrer">Download PDF</a></p> <hr> <h2 id="more-technical-work">More Technical Work</h2> <p>Thormann, T.F., Gilles, M. (Under Review): Probing the Limits of the Lie Detector Approach to LLM Deception. <a href="https://doi.org/10.48550/arXiv.2603.10003" target="_blank" rel="noopener noreferrer">https://doi.org/10.48550/arXiv.2603.10003</a>. <a href="https://tom-felix-thormann.github.io/thormann_gilles_2026_probing_limits_lie_detectors.pdf" target="_blank" rel="noopener noreferrer">Download PDF</a></p>https://tom-felix-thormann.github.io/talks/Mon, 01 Jan 0001 00:00:00 +0000https://tom-felix-thormann.github.io/talks/<h2 id="espp-2026">ESPP 2026</h2> <p>Defining Strategic AI Deception Through Generalized Propositional Attitudes. <a href="https://tom-felix-thormann.github.io/thormann_ESPP_2026_presentation.pdf" target="_blank" rel="noopener noreferrer">Download Slides</a> <a href="https://tom-felix-thormann.github.io/thormann_2026_defining_strategic_deception.pdf" target="_blank" rel="noopener noreferrer">Download PDF</a></p> <hr>