

Inside the black box of AI: How AI models actually think | Emmanuel Ameisen (Anthropic)
Emmanuel Ameisen is an interpretability researcher at Anthropic, where he looks inside LLMs like Claude to understand how they think. Before joining Anthropic, he spent years in applied ML at Stripe and Insight, and is the author of Building Machine Learning Powered Applications. His research has produced some of the…

Scout bees are checking it out — divided opinions, the swarm hasn't committed.
- Platform
- 45%
- Community
- 60%
- Value
- no read yet
Buzzmeter says it's buzzing across platforms — the Hive Vote says whether the people who actually listened liked it.
Rate this episode
Add your vote to the Hive — listeners rate every episode after they finish.
- No reviews yet — be the first.
What people are saying
“Lenny needs a reality check on his understanding of this tech. He kept jumping to these conclusions of llms being “alive” despite his guest clearly saying that wasn’t a conclusive finding at all. If he’s going to really give a good informat…”
“I hope these people know that they are the reason I am now afraid for my life and the lives of my family and friends. If you work at a death camp, you quit. You’re not going to change it from the inside and you can’t blame others for your a…”
“"To make them is not to understand them". Great quote I would take from this.”
“The idea that models plan many tokens ahead without saying those plans out loud hit home for me. When I build side projects with AI coding tools, I keep learning that what the model shows is only part of what it is actually doing.”
More from Lenny's Podcast: Product | Career | Growth
See all episodes →
Why Netflix is betting on systems thinkers—not specialists—in the AI era | Elizabeth Stone (CPTO)

The playbook for building high talent density teams | Adam Ward, Head of Talent at Cursor

This CPO regrets that product management exists | Tom Verrilli (CPO of Whatnot)
Similar episodes from other shows
More like Lenny's Podcast: Product | Career | Growth →
The Utility of Interpretability — Emmanuel Amiesen

Anthropic Begins to Unlock the Mystery of LLMs

Understanding the inner thoughts of AI

Joscha Bach: AGI, Consciousness, and the Evolution of Intelligence
One great episode in your inbox, daily — free.
One email a day, unsubscribe anytime. No spam, ever.