The Bayesian Conspiracy cover image

179 – The Plan (to align AI), with John Wentworth

The Bayesian Conspiracy

00:00

Why Do We Need Formalizations for Engineering?

Douglas Rushkoff: Why do we need formalizations for engineering? So I guess specifically. And so that's so you can iterate and improve using more accurate terms. The analogy in machine learning today would be people who try to do variants of interpretability by like looking at the internals of a neural network, he says.Rushkoff: What you really want here is something that's more like a thermometer. Can robustly predict a lot of different things using that result. Yeah. We have some idea of what sort of arguments we want to be able to use these for.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app