Christian Nickel
What is now proved was once only imagined. — William Blake
Welcome
I am Chris, a Computer Scientist and AI Researcher with interests in AI-Safety and security, steerability, reasoning and tool usage, human–AI interaction (HAI), as well as decentralized, secure and privacy-preserving local / on-premise compute. While my current focus is on generative AI, I also maintain an interest in Distributed Ledger Technology (DLT), Self-Sovereign Identity (SSI) and smart contracts. I believe that current and next-generation generative AI can help us make tremendous scientific progress and unlock substantial economic potential. To reap these benefits even in safety-critical environments and increase its utility for scientific and technological progress, we need to take a closer look at AI-Safety and AI-related Cybersecurity, while also investigating the mechanics of model reasoning and tool-calling, and while also considering the human component. Holding an M.Sc. in Computer Science from the University of Bonn, Germany, I seek to address these questions in my future PhD research. I am passionate about interdisciplinary approaches that push the boundaries of AI and its applications and enjoy collaborating with researchers and practitioners across relevant fields. I currently work as a full-time researcher at the Research Center Trustworthy Data Science and Security (RC-Trust) and the University of Duisburg-Essen, in the group “Human Understanding of Algorithms and Machines” (HUAM), which focuses on behavioral effects in humans in relation to AI.
News
- 2026 — We released a preprint on Understanding Artificial Theory of Mind: Perturbed Tasks and Reasoning in Large Language Models (arXiv:2602.22072).
2025 — Visited the AIAS 2025: Chen Institute Symposium for AI Accelerated Science in San Francisco. Super grateful for the great impressions on SOTA AI, applications to science and in practice, what is possible and what not, and Tianqiao’s and Chrissy’s commitment and vision for future AI, as well as meeting so many interesting people and striking up great conversations.
Had a great, fascinating time at Manny’s at Nate Soares’ reading and discussion of “If Anyone Builds It, Everyone Dies”. The compelling discussion reinforced my view that we must commit to creating mutually beneficial human–AI relationships in the future.
- 2025 — Laura Schrewe, Lucie Flek and I presented our short paper Understanding Theory of Mind in Large Language Models: The Role of Perturbations and Chain-of-Thought Prompting at the ToM4AI Workshop @ AAAI 2025 in Philadelphia, PA, USA (PDF, OpenReview).
- 2024 — Laura Schrewe and I received the Best Poster Award at EMNLP 2024’s WiNLP workshop for our work on probing Theory of Mind in large language models.