How to Scale Up Your Research on the Eve of Deploying AI

2min Snip

00:00

Play full episode

Summary

Transcript

Episode notes

ZD to kind of backward change say, okay, imagine we have something that's on the verge of being super intelligent AI. What are the things we want to do with it? And maybe we should start practicing those now. So I think that interpretability and red teaming are two examples of capacities that we are going to want to be actually deploying a lot of when we have these really powerful systems.

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