Artwork

Content provided by TWIML and Sam Charrington. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by TWIML and Sam Charrington or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.
Player FM - Podcast App
Go offline with the Player FM app!

Localizing and Editing Knowledge in LLMs with Peter Hase - #679

49:46
 
Share
 

Manage episode 411383461 series 2355587
Content provided by TWIML and Sam Charrington. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by TWIML and Sam Charrington or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

Today we're joined by Peter Hase, a fifth-year PhD student at the University of North Carolina NLP lab. We discuss "scalable oversight", and the importance of developing a deeper understanding of how large neural networks make decisions. We learn how matrices are probed by interpretability researchers, and explore the two schools of thought regarding how LLMs store knowledge. Finally, we discuss the importance of deleting sensitive information from model weights, and how "easy-to-hard generalization" could increase the risk of releasing open-source foundation models.

The complete show notes for this episode can be found at twimlai.com/go/679.

  continue reading

728 episodes

Artwork
iconShare
 
Manage episode 411383461 series 2355587
Content provided by TWIML and Sam Charrington. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by TWIML and Sam Charrington or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

Today we're joined by Peter Hase, a fifth-year PhD student at the University of North Carolina NLP lab. We discuss "scalable oversight", and the importance of developing a deeper understanding of how large neural networks make decisions. We learn how matrices are probed by interpretability researchers, and explore the two schools of thought regarding how LLMs store knowledge. Finally, we discuss the importance of deleting sensitive information from model weights, and how "easy-to-hard generalization" could increase the risk of releasing open-source foundation models.

The complete show notes for this episode can be found at twimlai.com/go/679.

  continue reading

728 episodes

Tutti gli episodi

×
 
Loading …

Welcome to Player FM!

Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.

 

Quick Reference Guide