“these, for these things, it's sort of expected that once…” — Dwarkesh Podcast at 41:04
“these, for these things, it's sort of expected that once you train the model, a starting board state will look like 0.5. And then as you progress towards the end of the game, it'll actually look something like, you know, this is 0.5. The win probability will sort of either go like this,”
0:00
2:37:29