Emergent Deception in LLMs

Behind a seemingly simple model result are choices about data, assumptions, and tradeoffs. We are joined by Thilo Hagendorff, a Research Group Leader of Ethics of Generative AI at the University of Stuttgart. He joins us to discuss his research, Deception Abilities Emerged in Large Language Models.

Guest

Thilo Hagendorff: Dr. Thilo Hagendorff is an expert in AI ethics, machine behavior in language models, as well as the intersection of machine learning and psychology. He is working as an Independent Research Group Leader at the University of Stuttgart (Germany). He was a visiting scholar at Stanford University as well as UC San Diego. As a lecturer, he teaches at the Hasso Plattner Institute (Germany), among others. thilo-hagendorff.info