Thilo Hagendorff

Thilo Hagendorff is an expert in AI safety, AI ethics, and machine behavior in generative models. He leads an independent research group at the University of Stuttgart, where his work explores emergent abilities of language models, particularly through the lens of behavioral evaluation and psychology. Previously, he was a postdoctoral researcher at the Cluster of Excellence “Machine Learning: New Perspectives for Science” at the University of Tübingen. He has held visiting scholar positions at Stanford University, UC San Diego, and the European Laboratory for Learning and Intelligent Systems (ELLIS) in Alicante. Thilo is a lecturer at the Hasso Plattner Institute and other institutions, where he teaches on AI safety, ethics, and alignment. He contributes to AI governance bodies, including the AI Campus of the German Federal Ministry of the Interior or the VDE AI Ethics Impact Group. He has published in leading journals of his field, including venues such as Nature Computational Science or PNAS. His recent work addresses deception abilities in AI systems. His research has been featured in major national and international media, including MIT Technology Review, The Economist, Scientific American, and many others.