PodcastIntel
Sign in Get Started Free
Lex Fridman Podcast
Lex Fridman Podcast

#431 – Roman Yampolskiy: Dangers of Superintelligent AI

Jun 2, 2024
AI Summary
  • Roman Yampolskiy discusses AI safety research and dangers of superintelligent artificial intelligence
  • Explores controllability, unpredictability, and existential risks posed by advanced AI systems
  • Examines approaches to AI alignment and the challenges of ensuring safe superintelligence

Guests on This Episode

RY
Roman Yampolskiy
4 podcast appearances

More from Lex Fridman Podcast

View all episodes →

Get AI Summaries for Every New Episode

Subscribe to Lex Fridman Podcast and get AI summaries, guest tracking, and email digests delivered automatically.

Sign Up Free →