“which I think are the core of the hypothesis. Then I said…” — Dwarkesh Podcast at 1:40:16
“which I think are the core of the hypothesis. Then I said three more things. One was symmetries, which is basically like if your architecture doesn't take into account the right kinds of symmetries, it doesn't work or it's very inefficient. So for example, convolutional neural networks take into account translational…”
0:00
1:58:43