Max Schwarzer
TalkRL: The Reinforcement Learning Podcast
The Importance of RL in LLMs
Max Forzer: We're seeing good performance on easy stuff and not on hard stuff. I think there's some kind of glossing over sometimes of like what exactly the difficulty level we're dealing with. Once people get a little bit bored with textual domains, that's probably going to happen pretty soon. And that's where RL starts to be really valuable again.
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.
