Success (and failure) in prompting (Practical AI #213)
Changelog Master Feed
00:00
Are You Setting Your Expectations for Models?
When you're building on a world of knowledge in a literal sense, you don't have those benefits and so you are going to create a model with a lot of data that is simply beyond your purview and control. What can we reliably expect these models to output? If I was to answer that right now, how he would answer that is saying these models will reliably output creative and coherent either text or images. But then if I ask the other question, like, what can I not expect of them? I think I'm not able to expect of them like factual correctness or logic or like them being like accurate in sort of informational sense.
Transcript
Play full episode
