“When we do gradient descent on the samples we draw, all of…” — Dwarkesh Podcast at 2:42:36
“When we do gradient descent on the samples we draw, all of the next generation of the AI models has been altered in that way. My picture of like aligned subhuman AI to this, like the superhuman AI being aligned is still murky. If we can talk about that more concretely. Yeah. And I do want to clarify. So where Eliezer…”
0:00
2:44:16