
16 - Preparing for Debate AI with Geoffrey Irving
AXRP - the AI X-risk Research Podcast
Language and Human Preferences
When i look at your work, it seems more like in human preferences ore, using human data somehow to improve language models. I'm wondering if you can talk about the relationship between those two things. And give us a better sense of, like the geffrey irving agenda for language. The way to say it is that whatever task you are doing, you want language to aligne these systems.
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.