Some researchers claim that mathematics proves we can never guarantee a superintelligent AI will be safe.

Is that really true?

In this episode, I examine one of the most influential arguments in AI safety and argue that it rests on a fundamental misunderstanding. The limits of formal computation are not the same as the limits of intelligence. Treating them as equivalent transfers mathematical limits from computation to an entirely different level of description, where they no longer apply.

Further Watching
Roman Yampolskiy: AI Can’t Be Controlled — and We’re Building It Anyway: https://www.youtube.com/watch?v=jQ4PaUbhdhs

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

If you enjoyed this episode and want to go deeper, come find me over at dekyon.io. With a premium membership you get the full Science in Perspective experience: interactive visualizations of the key concepts, a study space to learn the fundamentals behind each episode, and an "Ask an Episode" feature where you can dialogue with an AI about the details and start connecting ideas across the whole show.

There's also notes, transcripts, deep-dive articles, and a community of folks thinking through this stuff alongside you. It's where the episode stops being something you just listened to and becomes something you truly understand. So head to dekyon.io, click on the science in perspective app, and become a member today.