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 Reading
https://www.quantamagazine.org/debate-may-help-ai-models-converge-on-truth-20241108/

Recent Research on using Debate to Teach AI Truth
https://arxiv.org/pdf/2305.14325
https://arxiv.org/pdf/2407.04622v2
https://arxiv.org/pdf/2402.06782

Become a Member
science-in-perspective.com

Support the show

Become a Member at dekyon.io/seanmcclure/science-in-perspective

Premium members get access to the full member app. This includes data visualizations of the core concepts in each episode, a Study Space for learning fundamentals, and premium articles on Techniques and Mindsets.

Members can also save personal notes, explore episode summaries and transcripts, search across episodes, track watch history and progress, and participate in the community forum. Premium membership includes ongoing support.