Dwarkesh Patel: belief

Transcript context

…Who hasn't? Totally. So I guess there are a few crazy things here. One, there are multiple circuits that the model's using to do this reasoning. Two, you can actually see if it's doing the reasoning or not. Three, the scratch pad isn't giving you this information. Two fun analogies for you. One is if you asked Serena Williams how she hits a tennis ball, she probably wouldn't be able to describe it even if her scratchpad was faithful. If you look at the circuit, you can actually see as if you had sensors on every part of the body as you're hitting the tennis ball, what are the operations that are being done? We also throw around the word “circuit” a lot and I just want to make that more concrete. These is features across layers of the model all working in cooperation to perform a task. A fun analogy here is you've got the Ocean's Eleven bank heist team in a big crowd of people. The crowd of people is all the different possible features. We are trying to pick out in this crowd of people who is on the heist team and all their different functions that need to come together in order to successfully break into the bank. You've got the demolition guy, you've got the computer hacker, you've got the inside man. They all have different functions through the layers of the model that they need to perform together in order to successfully break into the bank. I think in the addition example, you said in the paper that the way it actually does the addition is different from the way it tells you it does the addition. Totally, yeah.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.