Is There a Difference in Methodological Approaches to Machine Learning?

Yelic: I think most of the world, against the intellectual tradition that's sort of spawned off of, like nick bosroom and elias ridkowski, uses some an approached kind of like this may maybe with an emphasis on learning things that like, people want to do. But i am very drawn to an approach where you say, like, ok, we think that's going to be important down the line. We think it some point, as we're trying to solve alignement, we're gong to like really be hurting for want of an understanding of like, bounded rationality. And then at that point we will have a more precise specificationf like what we actually want out

Transcript

Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!

Get the app