Skip to content

“What do we do with the aligned GPT-6 so that the…” — Dwarkesh Podcast at 2:34:51

Dwarkesh Podcast Carl Shulman (Pt 1) — Intelligence explosion, primate evolution, robot doublings, & alignment

“What do we do with the aligned GPT-6 so that the superintelligence that we eventually develop is also aligned? So humans are pretty unreliable. If you get to a situation where you have AIs who are aiming at roughly the same thing as you, at least as well as having humans do the thing, you're in pretty good shape.”

0:00 2:44:16