When there's two sides, essentially all you have to do is like take the evidence of one side and compare it to the evidence of the other side. And that's not always easy, but it's more straightforward than trying to come up with a single conclusion from both sides. It reminds me of this failure mode that high IQ people fall into sometimes where they're so much better at sort of being coherent in a very complex way that other people can't reply to. They convince themselves that they're right much more often than they are because others just struggle to argue against them.
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
Music
Affiliates