11 min listen
Emergent Deception in LLMs
FromData Skeptic
ratings:
Length:
27 minutes
Released:
Oct 9, 2023
Format:
Podcast episode
Description
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.
Released:
Oct 9, 2023
Format:
Podcast episode
Titles in the series (100)
[MINI] Bayesian Updating: In this minisode, we discuss Bayesian Updating - the process by which one can calculate the most likely hypothesis might be true given one's older / prior belief and all new evidence. by Data Skeptic