Dr. Thilo Hagendorff

"AI, Behave! - Ethics Meets Machine Behavior"

The talk provides an overview of my research on AI ethics, AI safety, and machine behavior. It begins with a brief introduction on why research on responsible AI matters in the first place, offering an accessible entry point for students by illustrating the main topics in the field. The focus then shifts to my work on machine behavior in generative AI systems, with a particular emphasis on deception abilities in large language models. Eventually, the talk aims to address pressing safety and ethical challenges posed by current AI systems by synthesizing insights from computer science, philosophy, as well as psychology.

Bio: Dr. Thilo Hagendorff is an expert in AI safety, AI ethics, machine behavior in generative models, as well as the intersection of machine learning and psychology. He is working as a Research Group Leader at the University of Stuttgart. Previously, he worked for the Cluster of Excellence “Machine Learning” at the University of Tuebingen. He was a visiting scholar at Stanford University, UC San Diego, as well as the European Laboratory for Learning and Intelligent Systems (ELLIS) in Alicante. As a lecturer, he teaches at the Hasso Plattner Institute in Potsdam, among others.

Termin als Datei downloaden und in den Kalender importieren.