3min chapter

The Inside View cover image

Ethan Perez–Inverse Scaling, Language Feedback, Red Teaming

The Inside View

CHAPTER

Using Red Teaming to Deploy a Language Model?

The hope is that you just are able to continually like beat out the bad behavior from from the model you're attacking until it just converges t. The best analogy would be, am, a boast, a language model generating the test cases plus te classifier. Ye, i'm super excited about a gan type approach to this. I think so. Maybe we do some additional checks, like interpretability things and then, ah, if weare like, ok, like, looks, looks ok, then we deploy it.

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