World Model · podcast knowledge graph

#494 — A Coin Toss for the Future

2026-09-24 · 93 min · 9 entities

Asserted relationships

  • → hosted by Sam Harris person
    0.55 · ×2
    evidence rules-v4
    Feed author/publisher: Sam Harris
  • → hosted by Waking Up with Sam Harris company
    0.55 · ×2
    evidence rules-v4
    Feed author/publisher: Waking Up with Sam Harris
  • → discusses Society & Culture concept
    0.40 · ×2
    evidence rules-v4
    Feed category: Society & Culture
  • → discusses Science concept
    0.40 · ×2
    evidence rules-v4
    Feed category: Science

Entities found in this episode

concepts 5

  • mentioned Society & Culture concept
    0.50 · ×2
    evidence rules-v4
    Feed category: Society & Culture
  • mentioned Science concept
    0.50 · ×2
    evidence rules-v4
    Feed category: Science
  • mentioned A Coin Toss for the Future concept
    0.42 · ×2
    evidence rules-v4
    #494 — A Coin Toss for the Future
  • discusses Society & Culture concept
    0.40 · ×2
    evidence rules-v4
    Feed category: Society & Culture
  • discusses Science concept
    0.40 · ×2
    evidence rules-v4
    Feed category: Science

persons 2

  • mentioned Sam Harris person
    0.70 · ×2
    evidence rules-v4
    Feed author/publisher: Sam Harris
  • hosted by Sam Harris person
    0.55 · ×2
    evidence rules-v4
    Feed author/publisher: Sam Harris

companys 2

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 .