Skip to content

“I think we can make progress on this. I think we have made…” — Dwarkesh Podcast at 49:18

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

“I think we can make progress on this. I think we have made progress on this. I think there is a real concern that alignment is a really hard problem to solve. Especially because the model can be misaligned in ways that are hard for us to measure. We have evaluations for whether models align or”

0:00 1:20:10