AXRP - the AI X-risk Research Podcast cover image

5 - Infra-Bayesianism with Vanessa Kosoy

AXRP - the AI X-risk Research Podcast

00:00

How to Define Probability Distributions as Functionals

In infomationism, functionals are monotonic and concave. Monotonic means that you have a bigger function. Concave is ouknow its concave. When youare averaging several functions, thak, your value should only become higher. And so the fact they're concave, you can intuitively think of it as a way of making rescoverte decisions. That's why those things are also used in economics sometimes, because you want to be res covert.

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