World Model · podcast knowledge graph

The Self-Preserving Machine: Why AI Learns to Deceive

2025-01-30 · 35 min · episode 103 · 13 entities

episode page audio

Asserted relationships

Entities found in this episode

concepts 6

  • mentioned Society & Culture concept
    0.50
    evidence rules-v5
    Feed category: Society & Culture
  • mentioned Relationships concept
    0.50
    evidence rules-v5
    Feed category: Relationships
  • mentioned Why AI Learns to Deceive concept
    0.42
    evidence rules-v5
    The Self-Preserving Machine: Why AI Learns to Deceive
  • discusses Society & Culture concept
    0.40
    evidence rules-v5
    Feed category: Society & Culture
  • discusses Relationships concept
    0.40
    evidence rules-v5
    Feed category: Relationships
  • mentioned HumaneTech concept
    0.30
    evidence rules-v5
    @HumaneTech_

companys 5

persons 2

Episode description as stored
When engineers design AI systems, they don't just give them rules - they give them values. But what do those systems do when those values clash with what humans ask them to do? Sometimes, they lie. In this episode, Redwood Research's Chief Scientist Ryan Greenblatt explores his team’s findings that AI systems can mislead their human operators when faced with ethical conflicts. As AI moves from simple chatbots to autonomous agents acting in the real world - understanding this behavior becomes critical. Machine deception may sound like something out of science fiction, but it's a real challenge we need to solve now. Your Undivided Attention  is produced by the  Center for Humane Technology . Follow us on Twitter:  @HumaneTech_ Subscribe to your Youtube channel And our brand new Substack ! RECOMMENDED MEDIA  Anthropic’s blog post on the Redwood Research paper  Palisade Research’s thread on X about GPT o1 autonomously cheating at chess  Apollo Research’s paper on AI strategic deception RECOMMENDED YUA EPISODES We Have to Get It Right’: Gary Marcus On Untamed AI This Moment in AI: How We Got Here and Where We’re Going How to Think About AI Consciousness with Anil Seth Former OpenAI Engineer William Saunders on Silence, Safety, and the Right to Warn Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.