AXRP - the AI X-risk Research Podcast cover image

1 - Adversarial Policies with Adam Gleave

AXRP - the AI X-risk Research Podcast

CHAPTER

Is the Space of Policies Transifret?

The space of policies and which one beak to others, is not transifret. If you're not used to a certain type of opponent, then you can get really messed up. So i was wondering, firstly, does that make sense as a theory? And secondly, um, is there some measure of how non transitive the space of like, sumo or kick and defend policieses are? A v very follbrokin question. I don't fortunaely have a good answer to it seems like it's not just dependent on the task, but also the class of policies that you're considering. But these results be got verwe t least for, you know,

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