“Whereas for things like training in a land with…” — Dwarkesh Podcast at 7:53
“Whereas for things like training in a land with reinforcement learning, at least the ways that are out there right now, you give the model a problem and you ask it to solve it. And if the problem is so easy, I can dissolve it in a second. It's not really learning anything. So if we run out of problems”
0:00
1:20:10