2min chapter

TalkRL: The Reinforcement Learning Podcast cover image

John Schulman

TalkRL: The Reinforcement Learning Podcast

CHAPTER

Is There a Time to Rethink PPO?

I expect AI to be able to do better than humans at most jobs in five years or so. For a while, we're going to discover things that AI isn't very good at and where we want to keep humans in control. I think there'll be some kind of gradual process over the next 10 or 15 years. And then Ethan, the Calabero from, uh, Mila asks, what is your median estimate for the arrival date of AGI?

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode