Max Schwarzer
TalkRL: The Reinforcement Learning Podcast
The Future of RLA
I've been really impressed by, obviously, by Dreamer V3. And I am of course interested in doing a BBF V2, sort of following Denneter's footsteps and push things a little bit further. So there's hopefully a lot of fun stuff to come. Do you think much about AGI? Yeah, so I totally do think about AGI. There are all these papers out there claiming that GPT-4 is already AGI. But the core message I'm seeing here is we're doing extremely well for purely textual domains. It may not be great at generating videos yet, but it'll be great at summarizing a video. We should be trying to
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.
