The Holding Problem and Math

3min Snip

00:00

Play full episode

Summary

Transcript

Episode notes

You can phrase a certain large class of questions about math in terms of whether a program holds. And the answer to that question is just the same as the answer to the math question of whether there exists an even number that isn't the sum of two primes. So the goal about conjecture which you're just describing is sort of equivalent to that program halting. Yeah and there's a bunch of other math questions.

Read the full transcript here.

How hard is it to arrive at true beliefs about the world? How can you find enjoyment in being wrong? When presenting claims that will be scrutinized by others, is it better to hedge and pad the claims in lots of caveats and uncertainty, or to strive for a tone that matches (or perhaps even exaggerates) the intensity with which you hold your beliefs? Why should you maybe focus on drilling small skills when learning a new skill set? What counts as a "simple" question? How can you tell when you actually understand something and when you don't? What is "cargo culting"? Which features of AI are likely in the future to become existential threats? What are the hardest parts of AI research? What skills will we probably really wish we had on the eve of deploying superintelligent AIs?

Buck Shlegeris is the CTO of Redwood Research, an independent AI alignment research organization. He currently leads their interpretability research. He previously worked on research and outreach at the Machine Intelligence Research Institute. His website is shlegeris.com.

Staff