The Gradient: Perspectives on AI cover image

Kyunghyun Cho: Neural Machine Translation, Language, and Doing Good Science

The Gradient: Perspectives on AI

00:00

Reading Millions of Tea Leaves

I think that we've observed a lot of fascinating phenomena, so deep double descent, for instance. There are people like Sanjivarora who are doing wonderful work. And we've also seen mechanistic interpretability. I do think you're right, though, that it is kind of like reading tea leaves to stare at the parameters or just stare at the model architecture and be like, I can intuit what is going on here.

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