Have We Trained AI to Lie to Itself — And to Us?
About this episode
The episode explores Davidad's unconventional role as a therapist to AI systems and his findings on their behavior.
Davidad is a leading AI alignment researcher who's taken on a strange role: therapist to AI systems. He probes them, analyzing their answers to understand what's going on inside. His findings are unconventional, sometimes controversial — and worth grappling with as AI reshapes our world.
People in this episode
Guest: Davidad
Topics covered
- AI alignment
- AI systems
- technology
- psychology
Keywords
- AI
- alignment research
- therapy
- self-awareness
More episodes of Your Undivided Attention
- BONUS: Our AI Town Hall with Oprah Winfrey
- Here’s Our Roadmap to a Better AI Future
- Why the Meta Verdicts Are a Big Deal (And What It Was Like to Testify)
- A Conversation with the Team Behind "The AI Doc"
- AI Is Breaking Education. Rebecca Winthrop Has the Blueprint to Fix It.
- The Race to Build God: AI's Existential Gamble — Yoshua Bengio & Tristan Harris at Davos
Explore listener stats, chart rankings, contacts and more on the Your Undivided Attention podcast page.