

#1875
Mentioned in 18 episodes
Human Compatible
Artificial Intelligence and the Problem of Control
Book • 2019
In this book, Stuart Russell explores the concept of intelligence in humans and machines, outlining the near-term benefits and potential risks of AI. He discusses the misuse of AI, from lethal autonomous weapons to viral sabotage, and proposes a novel solution by rebuilding AI on a new foundation where machines are inherently uncertain about human preferences.
This approach aims to create machines that are humble, altruistic, and committed to pursuing human objectives, ensuring they remain provably deferential and beneficial to humans.
This approach aims to create machines that are humble, altruistic, and committed to pursuing human objectives, ensuring they remain provably deferential and beneficial to humans.
Mentioned by






















Mentioned in 18 episodes
Mentioned by Speaker 6 as a precise summary of ideas.

116 snips
Beyond human minds: The bewildering frontier of consciousness in insects, AI, and more
Mentioned by
Chris Williamson , discussing algorithms' ability to predict user clicks and reprogram preferences.


110 snips
#967 - Jeffrey Katzenberg & Hari Ravichandran - Hollywood Trouble, Big Tech & The Crisis With Kids
Mentioned by
Yoshua Bengio when discussing the alignment problem and his change of heart regarding AI risks.


22 snips
Yoshua Bengio - Why We Shouldn't Blast Off to AGI Just Yet (AGI Destinations Series, Episode 1)
Mentioned by
Frank Chen as the author of a textbook on artificial intelligence used to educate a generation of AI researchers.


Controlling AI
Mentioned by the podcast host discussing the implications of AI and the need for machines to be uncertain about human goals.

Maggie Jackson: Embracing Uncertainty