AXRP - the AI X-risk Research Podcast cover image

7 - Side Effects with Victoria Krakovna

AXRP - the AI X-risk Research Podcast

CHAPTER

Is There a Siseratum a for the Ipact Regularizer?

Siseratum is referring to what the optimal policy should be if you have no reward. But it's not truly saying how, like, other policies should be ranked by the ipact regularizer. The best sort of precise definition that i could come up with satisfy some of the like, intuitions were like, you know what interference is, but i think it's not the final answer. So, ye, i think this is isdematly something to improve, improve on. And so, lake, then it becomes more, kind of more complicated, at least,. ik, i think, ma, thinking about this and, you know, not getting very far into himself,

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