AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Do You Think There's a Ceiling to This Kind of Approach?
In the very beginning, we most it was most of replica was scripted and then a little bit of this fallback part of replica was using a retrieval model. And then with GPT two, finally generative models that originally were not very good and were the very, very fallback option for most of our conversations, but wouldn't even put them in production. Now they're much better. Do you have a question whether that's the right way to go? I think in this purely my instinct saying that there should be something else as well from memory. So far it's been stupid to bet against deep learning.