How can we keep AI truthful, even if it knows more than we do? In this episode I discuss how AI might be kept aligned to human truth and values, despite superseding us in scale and capability. I argue that logic is a scale-free framework that is agnostic to size and complexity, and can serve as a self-regulating form of truth discernment, even for highly creative and powerful machines.Suggested Readinghttps://www.quantamagazine.org/debate-may-help-ai-models-converge-on-truth-20241108/Recent Research on using Debate to Teach AI Truthhttps://arxiv.org/pdf/2305.14325https://arxiv.org/pdf/2407.04622v2https://arxiv.org/pdf/2402.06782Become a Memberscience-in-perspective.comSupport the showBecome a premium member to gain access to premium content, including the Techniques and Mindsets Videos, visual concept summaries of each episode, community forum, episode summary notes, episode transcripts, q&a/ama sessions, episode search, watch history, watch progress and support.Join Now at science-in-perspective.com or patreon.com/8431143/join

Ver todos los episodios