The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Localizing and Editing Knowledge in LLMs with Peter Hase - #679
Today we're joined by Peter Hase, a fifth-year PhD s...
more
Apr 8 2024 49m
Chapter 1 11 mins
Interpretability, Model Editing, and Scalable OversightChapter 2 13 mins
Model Editing and Knowledge UpdatesChapter 3 7 mins
Ensuring Model Safety and OversightChapter 4 5 mins
Exploring Easy to Hard GeneralizationChapter 5 8 mins
Task Specification in Language ModelsChapter 6 1 min
Internal Models and Consistency in AI