
Localizing and Editing Knowledge in LLMs with Peter Hase - #679
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Exploring the Complexity of Large Language Models
This chapter examines the intricacies of large language models and their mechanisms. The speakers discuss the balance between next token prediction and the models' ability to discern true representations, emphasizing how LLMs can reflect human-like reasoning.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.