How to Validate a Theory

2min Snip

00:00

Play full episode

Summary

Transcript

Episode notes

Sometimes you do want to combine multiple theories. But I think that a really useful step is to check whether in fact your new theory does explain everything first. People are often too inclined to jump to behavioral economics, which is a much less predictive theory, much too quickly. And they should have started out by like checking which things actually needed to be explained.

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