Siirry offline-tilaan Player FM avulla!
Localizing and Editing Knowledge in LLMs with Peter Hase - #679
Manage episode 411383461 series 2355587
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.
727 jaksoa
Localizing and Editing Knowledge in LLMs with Peter Hase - #679
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Manage episode 411383461 series 2355587
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.
727 jaksoa
Tous les épisodes
×Tervetuloa Player FM:n!
Player FM skannaa verkkoa löytääkseen korkealaatuisia podcasteja, joista voit nauttia juuri nyt. Se on paras podcast-sovellus ja toimii Androidilla, iPhonela, ja verkossa. Rekisteröidy sykronoidaksesi tilaukset laitteiden välillä.