Player FM 앱으로 오프라인으로 전환하세요!
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.
701 에피소드
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.
701 에피소드
Alla avsnitt
×플레이어 FM에 오신것을 환영합니다!
플레이어 FM은 웹에서 고품질 팟캐스트를 검색하여 지금 바로 즐길 수 있도록 합니다. 최고의 팟캐스트 앱이며 Android, iPhone 및 웹에서도 작동합니다. 장치 간 구독 동기화를 위해 가입하세요.