Skip to content

“I think I was way too long winded with the way I said…” — Dwarkesh Podcast at 52:56

Dwarkesh Podcast Noam Brown – Agent swarms, alignment, & recursive self-improvement

“I think I was way too long winded with the way I said that. But TLDR, you speak the specific issue, but not this broader problem of rewarding the AI for cheating when you get away with it.”

0:00 1:20:10