“in peril. So, and then here the trainer would be just, you…” — Dwarkesh Podcast at 2:10:34
“in peril. So, and then here the trainer would be just, you know, predict the MCTS labels. So, again, like this kind of works and this is quite relevant in robotics where you're really, you just have a lot of offline data and you can't simulate things like MCTS. But in practice, like it does”
0:00
2:37:29