Skip to content

“I think of it as almost like an extended training set and…” — Dwarkesh Podcast at 49:34

“I think of it as almost like an extended training set and an extended test set, right? Everything we're doing, all the alignment methods we're doing are the training set, right? You know, you can run tests on them, but will it really work out of distribution? Will it really work in another situation? Mechanistic…”

0:00 1:58:43