SCOUT· 66%53m·2026-07-10·ScienceUnderstanding the inner thoughts of AI
Neel and his team are trying to do something phenomenally difficult: understand an intelligence that didn't come with a manual. Together, they explore the cutting-edge "neuroscience" of artificial intelligence—revealing the surprising, elegant structures being discovered inside these networks (like spare…
Scout bees are checking it out — divided opinions, the swarm hasn't committed.
- Platform
- 51%
- Community
- 85%
- 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
“Hannah Fry has the best voice.”
“What struck me from this conversation is that we may be mistaking the current generation of models for the final form of AI. Right now they often externalize parts of their reasoning in English, which gives us the comforting illusion that w…”
“This is a great look at how we are acting as the neuroscientists for AI that we don’t fully understand yet. It’s great that we are prioritizing safety and practical usage rather than just chasing total knowledge”
“These interviews give me hope... between all the awful noise from CEOs wanting to use AI to destroy people's livelihoods and all the grifters wanting to make a quick buck off people's extremes of optimism or fear, it is so profoundly refres…”
Similar episodes from other shows
More like Google DeepMind: The Podcast →
Joscha Bach: AGI, Consciousness, and the Evolution of Intelligence
Can AI match the human brain? | Surya Ganguli
Why is AI so hard?
The Utility of Interpretability — Emmanuel Amiesen
One great episode in your inbox, daily — free.
One email a day, unsubscribe anytime. No spam, ever.