The Inside View cover image

Collin Burns On Discovering Latent Knowledge In Language Models Without Supervision

The Inside View

CHAPTER

How Similar Are Current Deep Learning Systems to GPTN?

I worry that a lot of existing theoretical alignment work is hard to verify or it's like making assumptions that aren't obviously true and I worry that it's sort of ungrounded. Current models are human level or less so human evaluators can basically evaluate these models whereas that will totally break down in the future, he says. If we have unsupervised methods that do well on human level tasks maybe that will say something meaningful about it scaling and generalizing even to superhuman level models now there's still subtleties here for example current language models are trained to predict human mostly on the basis of what they're biased towards.

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