Emergent Deception in LLMs
Data Skeptic
English - October 09, 2023 15:26 - 27 minutes - 31.7 MB - ★★★★★ - 477 ratingsScience Technology machinelearning skepticism datamining datascience science statistics Homepage Download Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed
Previous Episode: Agents with Theory of Mind Play Hanabi
Next Episode: Do LLMs Make Ethical Choices
On today’s show, 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.
Thilo discussed how machine psychology is useful in machine learning tasks. He shared examples of cognitive tasks that LLMs have improved at solving. He shared his thoughts on whether there’s a ceiling to the tasks ML can solve.