TalkRL: The Reinforcement Learning Podcast cover image

John Schulman

TalkRL: The Reinforcement Learning Podcast

CHAPTER

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.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner