About
I’m Dr. Leonard Dung, a philosopher at Ruhr University Bochum, Germany. My research covers catastrophic risks from AI, AI alignment and deception, and the possibility of mental states in AI. I am the author of numerous peer-reviewed articles and a monograph on AI.
Why this site
Good introductions to AI safety are scarce. Most of what exists is either a technical paper or an argument for a particular view. Here I try to explain each concept plainly and show what the evidence currently says, both for and against.
Selected writing on AI risk
- Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors. With J. Wiedermann-Möller and M. Andriushchenko. NeurIPS 2026, forthcoming.
- AI alignment strategies from a risk perspective: Independent alignment mechanisms or shared failures? With F. Mai. Proceedings of the Second Annual Conference of the Society for Safe and Ethical AI, 2026.
- Values in science and AI alignment research. Inquiry, 2026.
- Estimating the probability of AI existential catastrophe: Converging on the answer from opposite ends. Philosophy of AI, 2025.
- Misalignment or misuse? The AGI alignment tradeoff. With M. Hellrigel-Holderbaum. Philosophical Studies, 2025.
- Against the Manhattan project framing of AI alignment. With S. Friederich. Mind & Language, 2025.
- A two-step, multidimensional account of deception in language models. Erkenntnis, 2025.
- Is superintelligence necessarily moral? Analysis, 2024.
- The argument for near-term human disempowerment through AI. AI & Society, 2024.
- Evaluating approaches for reducing catastrophic risks from AI. AI and Ethics, 2024.
- Current cases of AI misalignment and their implications for future risks. Synthese, 2023.
- Are we Doomed to an AI Race? Why Self-Interest Could Drive Countries Towards a Moratorium on Superintelligence. With E. Roussel and others. Preprint, 2026.
- Against racing to AGI: Cooperation, deterrence, and catastrophic risks. With M. Hellrigel-Holderbaum. Preprint, 2025.
The full list is on my publications page.
Contact
Email: leonard.dung[at]rub.de