

#1272
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 

in the context of discussing AI safety and alignment.


Sam Harris

635 snips
#365 – Sam Harris: Trump, Pandemic, Twitter, Elon, Bret, IDW, Kanye, AI & UFOs
Mentioned by 

as an accessible book on AI.


Sam Harris

333 snips
#312 — The Trouble with AI
Mentioned by Speaker 6 as a precise summary of ideas.

182 snips
Beyond human minds: The bewildering frontier of consciousness in insects, AI, and more
Mentioned by 

, discussing algorithms' ability to predict user clicks and reprogram preferences.


Chris Williamson

147 snips
#967 - Jeffrey Katzenberg & Hari Ravichandran - Hollywood Trouble, Big Tech & The Crisis With Kids
Mentioned by 

when discussing how algorithms work and influence user preferences.


Chris Williamson

92 snips
#857 - Ryan Long - DEI Wars, Trump's Bible & The Masculinity Vote
Mentioned by 

as a book discussing algorithms and their interaction with humans.


Chris Williamson

72 snips
#859 - Ana Kasparian - Why Does Everyone Feel So Politically Homeless?
Mentioned by ![undefined]()

as an author of AI books.

Paul Roetzer

25 snips
#111: Grok-2 Controversy, Demis Hassabis: AI Is “Unreasonably Effective,” AI in Schools & Ex-Google CEO Says AI Can Steal IP
Mentioned by 

when discussing the alignment problem and his change of heart regarding AI risks.


Yoshua Bengio

22 snips
Yoshua Bengio - Why We Shouldn't Blast Off to AGI Just Yet (AGI Destinations Series, Episode 1)
Mentioned by 

when discussing different perspectives within the AI community.


Lex Fridman

20 snips
Melanie Mitchell: Concepts, Analogies, Common Sense & Future of AI
Mentioned by 

in the context of AI ethics and alignment with human values.


Melanie Mitchell

16 snips
Melanie Mitchell on Artificial Intelligence
Mentioned by ![undefined]()

as a book exploring a different approach to building AI systems.

Sean Illing

14 snips
Should we press pause on AI?
Mentioned by 

in the context of AI and social media algorithms.


Chris Williamson

11 snips
#241 - Seth Godin - Weaponise Your Creativity
Recommended by 

as an excellent resource on AI alignment.


Chris Williamson

#297 - Brian Christian - The Alignment Problem: AI's Scary Challenge
Mentioned by 

as 

's new book on ensuring AIs do what we want.


Sean Carroll


Stuart Russell

94 | Stuart Russell on Making Artificial Intelligence Compatible with Humans
Mentioned by 

in a discussion about the potential dangers of superintelligent AI.


Melanie Mitchell

Complexity and Intelligence with Melanie Mitchell - #464
Mentioned by 

as a book about AI.


Rob Wiblin

#68 - Will MacAskill on the paralysis argument, whether we're at the hinge of history, & his new priorities
Mentioned by 

as 

's book discussing the control problem in AI.


Chris Williamson


Stuart Russell

#364 - Stuart Russell - The Terrifying Problem Of AI Control
Mentioned by 

as a recent book proposing solutions to the challenges of AI alignment.


Max Tegmark

75 | Max Tegmark on Reality, Simulation, and the Multiverse
Mentioned by 

as the author of a textbook on artificial intelligence used to educate a generation of AI researchers.


Frank Chen

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