AXRP - the AI X-risk Research Podcast cover image

22 - Shard Theory with Quintin Pope

AXRP - the AI X-risk Research Podcast

CHAPTER

How to Use Learned Loss Functions to Optimize Internal Cognitive States

In deep learning with actual language models you can make like a sentiment classifier out of a language model and then use the classification gradient well. So it's possible to use learned classifiers essentially as parts of loss functions over internal cognitive states that is consistent with the toolboxes with the toolbox of deep learning okay. It seems almost like in this story basically at some point you could just be an expected utility optimal thing or very close to one do you think that's right yeah so I used to think this that like the shards would do all the work for me but once I've got like learned cognitive loss functions that are like organizing my thoughts to steer me more in some directions than away from other

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