S4E2: Google DeepMind’s Dr. Claire Cui on The Next Frontier for Large Language Models
Theory and Practice
00:00
The Turing Test for Chatbots
The ultimate test of whether or not a chatbot is working is when it's out there in the world, people are using it and they like it. I think that's because the model is trained over a lot of data. And if it's trained with more dialogue data, more conversational data, then it will be even more like conversational-like. But just sounding like human does not mean that is actually human.
Transcript
Play full episode
