“or in this case, Claude 1 to Claude 2, that the loss in…” — Dwarkesh Podcast at 3:10
“or in this case, Claude 1 to Claude 2, that the loss in terms of whether we can predict the next token scales very smoothly. So, okay, we don't know why it's happening, but can you at least predict if empirically, here is the loss at which this ability will emerge, here is the place where this circuit will emerge. Is…”
0:00
1:58:43