How Language Models Actually Think
Nov 20, 2025•26 min
Listen to this episode in Metacast mobile app
Don't just listen to podcasts. Learn from them with transcripts, summaries, and chapters for every episode. Skim, search, and bookmark insights. Learn more
Episode description
Emmanuel Ameisen, an interpretability researcher at Anthropic, joins the podcast to demystify how large language models work.
Subscribe to the Gradient Flow Newsletter 📩 https://gradientflow.substack.com/
Subscribe: Apple · Spotify · Overcast · Pocket Casts · AntennaPod · Podcast Addict · Amazon · RSS.
Detailed show notes - with links to many references - can be found on The Data Exchange web site.
For the best experience, listen in Metacast app for iOS or Android