Google DeepMind: The Podcast
Google DeepMind: The Podcast

Understanding the inner thoughts of AI

53 min

This episode explores the field of AI interpretability, which aims to understand how large language models work internally. Hannah Frye speaks with Neil Nander, who leads the language model interpretability team at Google DeepMind, about techniques like chain-of-thought reasoning, probes, and sparse autoencoders to 'open the black box' and ensure AI safety.

Summarized by Podsumo

Key Takeaways

💬 Notable Quotes

Get every episode summarized
Delivered to Telegram. Ask questions about any episode.
Start on Telegram