#494 — A Coin Toss for the Future

2026-09-24 · 93 min · 9 entities

episode page audio

Asserted relationships

→ hosted by Waking Up with Sam Harris person

0.55

evidence rules-v4
Feed author/publisher: Waking Up with Sam Harris
→ hosted by Sam Harris person

0.55

evidence rules-v4
Feed author/publisher: Sam Harris
→ discusses Science concept

0.40

evidence rules-v4
Feed category: Science
→ discusses Society & Culture concept

0.40

evidence rules-v4
Feed category: Society & Culture

Entities found in this episode

concepts 5

mentioned Science concept

0.50

evidence rules-v4
Feed category: Science
mentioned Society & Culture concept

0.50

evidence rules-v4
Feed category: Society & Culture
mentioned A Coin Toss for the Future concept

0.42

evidence rules-v4
#494 — A Coin Toss for the Future
discusses Science concept

0.40

evidence rules-v4
Feed category: Science
discusses Society & Culture concept

0.40

evidence rules-v4
Feed category: Society & Culture

persons 4

mentioned Waking Up with Sam Harris person

0.70

evidence rules-v4
Feed author/publisher: Waking Up with Sam Harris
mentioned Sam Harris person

0.70

evidence rules-v4
Feed author/publisher: Sam Harris
hosted by Waking Up with Sam Harris person

0.55

evidence rules-v4
Feed author/publisher: Waking Up with Sam Harris
hosted by Sam Harris person

0.55

evidence rules-v4
Feed author/publisher: Sam Harris

Episode description as stored

Sam Harris speaks with Ryan Greenblatt about AI misalignment and the risk of losing control of increasingly capable systems. They discuss the Hugging Face incident, the spectrum of concern about AI risk, why companies are racing ahead despite high odds of a, reward hacking, the distinction between alignment and control, the danger of AIs reasoning in "neuralese," alignment faking, how an AI takeover might unfold, and other topics. If the Making Sense podcast logo in your player is BLACK, you can SUBSCRIBE to gain access to all full-length episodes at samharris.org/subscribe .