2min chapter

The Inside View cover image

Ethan Perez–Inverse Scaling, Language Feedback, Red Teaming

The Inside View

CHAPTER

How to Predict Human Judgments?

If you have a model that of being deceptive, if you use the same model to try to explain the first one, ther will be teaming up. I think it's deftly an open problem that we could, i think we should justlike try different strategies empirically. We're just able to find like so many, like, like thousands of cases where the like model is generating ofensive content. It was like, we di we didn't even need to improve the classifier till i found these kinds of weaknesses.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode