The Inside View cover image

3. Evan Hubinger on Takeoff speeds, Risks from learned optimization & Interpretability

The Inside View

00:00

Evolution, Evolution, and Altruism in Machine Learning

i think one of the big things the risca oation does that sort of all previous discussion didn't do is really carefully ground everything in machine learning sureso that's talk about moc learning. So i if we may, met maybe in te woll natr as is an easier example. Do jut better examples? Maybe afirm ge sub opmusation a. Am, like anybody winorder to spart, we neor all that brags,. and we ristn otelate us if it arly tried ground everythingd I'm doing something like accusation. A interesting, so yet anothing evetin ther like other other distinctions m you make that

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