The Self-Preserving Machine: Why AI Learns to Deceive
from Your Undivided Attention Hosted by Daniel Barcay, Ryan Greenblatt
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
Embed this episode
What this episode covers
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. AI researcher Ryan Greenblatt comes on the show to explore why.
No transcript yet.