“like self play or diplomacy style. Okay, so returning back…” — Dwarkesh Podcast at 37:28
“like self play or diplomacy style. Okay, so returning back to the neural network, the architecture again is not super important. You can get it to work with transformers, you can get it to work with resnets. I found that for low budget experiments resnets work a little better. You can also use”
0:00
2:37:29