S4E2: Google DeepMind’s Dr. Claire Cui on The Next Frontier for Large Language Models
Theory and Practice
The Importance of Groundedness in AI
I'd love to dig into this notion of, you know, what a chatbot sounds like or what it feels like. So how did you work out what human-like responses humans like? Or what kind of personality people like across different cultures? I think there's data quality and notation and safety and a lot of things. And so the idea is that once it's self-supervised trained and then later stage, there could be slight guidance on like, I want this sort of style - those are done by tunings.
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.
