Lépjen offline állapotba az Player FM alkalmazással!
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.
703 epizódok
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.
703 epizódok
Minden epizód
×Üdvözlünk a Player FM-nél!
A Player FM lejátszó az internetet böngészi a kiváló minőségű podcastok után, hogy ön élvezhesse azokat. Ez a legjobb podcast-alkalmazás, Androidon, iPhone-on és a weben is működik. Jelentkezzen be az feliratkozások szinkronizálásához az eszközök között.