Localizing and Editing Knowledge in LLMs with Peter Hase
Listen now
Description
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.
More Episodes
Today we're joined by Azarakhsh (Aza) Jalalvand, a research scholar at Princeton University, to discuss his work using deep reinforcement learning to control plasma instabilities in nuclear fusion reactors. Aza explains his team developed a model to detect and avoid a fatal plasma instability...
Published 04/29/24
Today we're joined by Kirk Marple, CEO and founder of Graphlit, to explore the emerging paradigm of "GraphRAG," or Graph Retrieval Augmented Generation. In our conversation, Kirk digs into the GraphRAG architecture and how Graphlit uses it to offer a multi-stage workflow for ingesting,...
Published 04/22/24
Links
Genres
Artwork or description wrong?
Request an update »
Updates may take a few minutes.
Do you host a podcast?
Track your ranks and reviews from Spotify, Apple Podcasts and more.
See hourly chart positions and more than 30 days of history.
Get Chartable Analytics »
See hourly chart positions and more than 30 days of history.
