Iwan Williams, Ninell Oldenburg, Ruchira Dhar, Joshua Hatherley, Constanza Fierro,
Nina Rajcic, Sandrine R. Schiller, Filippos Stamatiou, and Anders Søgaard. 2025.
Mechanistic Interpretability Needs Philosophy. (Under review).
Arxiv
Ninell Oldenburg and Gleb Papyshev. 2025. The Stories We Govern By: AI, Risk,
and the Power of Imaginaries. (Under review).
Ninell Oldenburg, Ruchira Dhar, and Anders Søgaard. 2025. Two Conceptions of Intelligence:
Why AI Researchers Disagree About Scaling Laws and Future Risk. (Under review).
Ruchira Dhar, Ninell Oldenburg, and Anders Søgaard. 2025. Measure Generality,
Not Intelligence. (Under review).
Ruchira Dhar, Ninell Oldenburg, and Stephanie Brandl. 2025. Beyond Technocratic XAI:
The Who, What & How in Explanation Design. (Under review).
Ninell Oldenburg and Anders Søgaard. 2025. Navigating the Informativeness-
Compression Trade-Off in XAI. AI & Ethics.
SpringerPDF
Ninell Oldenburg and Tan Zhi-Xuan. 2024. Learning and Sustaining Shared
Normative Systems via Bayesian Rule Induction in Markov Games. In Proc.
of the 23rd International Conference on Autonomous Agents and Multiagent
Systems. University of Auckland, New Zealand.
ArxivPDF