AXRP - the AI X-risk Research Podcast cover image

16 - Preparing for Debate AI with Geoffrey Irving

AXRP - the AI X-risk Research Podcast

CHAPTER

How to Generate a Red Teaming Model

The model, like chincilla, is trained on one point four rabites, twattle wit, batrillion tokens. It has seen plenty of people putting back on other people. So in terms of prompt generation, yet, thit seemed especially important when you wanted to focus on one particular failure. And then i think there's a second point, which is that you can tune the models to be better helpers at doing a task. In addition to learning about how to make the language models do well with prompting zero shot, you could try to improve them as i attacking agents or red teams.

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