“but it just spews that text. And so then you fine tune it…” — Azeem Azhar's Exponential View at 23:06
“but it just spews that text. And so then you fine tune it so that it can be answer questions. And then you train it to be a good dog through this kind of Pavlovian process of treats if you get it right and sharp words if you get it wrong, which we call reinforcement learning with human feedback, which is designed to…”
0:00
45:47