Emergent Deception in LLMs

<p>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, <a href= "https://arxiv.org/abs/2307.16513">Deception Abilities Emerged in Large Language Models</a>.</p> <p>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.</p>