The Importance of Early Capacity Building

2min Snip

00:00

Play full episode

Summary

Transcript

Episode notes

Redwood Research is trying to do things that are as analogous as possible to some of these capacities that we're going to need a lot of in the future. So dividing things up in this way into these things that we probably will want to have really good capacity at, you know, towards the end before the systems are deployed and these things where we really have to finish them much earlier. How does this change your view on like what should be funded or how funders should think about this? Yeah. It makes me feel excited for the type of work that I'm doing.

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