TalkRL: The Reinforcement Learning Podcast cover image

John Schulman

TalkRL: The Reinforcement Learning Podcast

00:00

WebGBT - What Inspired the Idea?

The idea for WebGBT came from a project at OpenAI called World of Bits. Back then, the team was trying to do it with full visual input like Google Maps or something. But now we have these great language models that work on text data. We can't really interact with a lot of dynamic websites but as long as it's just browsing and reading text, we're fine.

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