We already know that AI models are developing a propensity for lying — but that tendency may go far deeper, according to one alarm-sounding computer scientist. As flagged by Gizmodo, this latest missive of AI doomerism comes from AI safety researcher Roman Yampolskiy, and was hosted on a somewhat surprising source: shock jock Joe Rogan's podcast, which occasionally features legitimate experts alongside garden-variety reactionaries and quacks. During the July 3 episode of "The Joe Rogan experience," Yampolskiy, who heralds from the University of Louisville in Kentucky, said that many of his colleagues believe that there's a 20 to 30 percent chance that […]