AXRP - the AI X-risk Research Podcast cover image

3 - Negotiable Reinforcement Learning with Andrew Critch

AXRP - the AI X-risk Research Podcast

CHAPTER

Harsane's Theorem

Harsane's theorem simplifies the number of different ways you could imagine aggregating people's preferences. Am, and a, i'm not sure i can even remember what they were now, because my brain has sortedi compressed them into the dilinear combination bucket. I think there's a lot of bad outcomes that result from the dynamics described in therum. A, it's simultaneously a negative result. M, and the reason is this, so let's just say we're deciding to do a podcast together. And you're going to, you're gong, you know, interview me. An a pocast a, that's a negotiation. We got to decide which

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner