#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.

Mentioned by

Mentioned in 18 episodes

Mentioned by
undefined
Sam Harris
in the context of discussing AI safety and alignment.
635 snips
#365 – Sam Harris: Trump, Pandemic, Twitter, Elon, Bret, IDW, Kanye, AI & UFOs
Mentioned by
undefined
Sam Harris
as an accessible book on AI.
333 snips
#312 — The Trouble with AI
Mentioned by
undefined
Chris Williamson
, discussing algorithms' ability to predict user clicks and reprogram preferences.
147 snips
#967 - Jeffrey Katzenberg & Hari Ravichandran - Hollywood Trouble, Big Tech & The Crisis With Kids
Mentioned by
undefined
Chris Williamson
when discussing how algorithms work and influence user preferences.
92 snips
#857 - Ryan Long - DEI Wars, Trump's Bible & The Masculinity Vote
Mentioned by
undefined
Chris Williamson
as a book discussing algorithms and their interaction with humans.
72 snips
#859 - Ana Kasparian - Why Does Everyone Feel So Politically Homeless?
Mentioned by
undefined
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
undefined
Lex Fridman
when discussing different perspectives within the AI community.
20 snips
Melanie Mitchell: Concepts, Analogies, Common Sense & Future of AI
Mentioned by
undefined
Melanie Mitchell
in the context of AI ethics and alignment with human values.
16 snips
Melanie Mitchell on Artificial Intelligence
Mentioned by
undefined
Sean Illing
as a book exploring a different approach to building AI systems.
14 snips
Should we press pause on AI?
Mentioned by
undefined
Chris Williamson
in the context of AI and social media algorithms.
11 snips
#241 - Seth Godin - Weaponise Your Creativity
Recommended by
undefined
Chris Williamson
as an excellent resource on AI alignment.
#297 - Brian Christian - The Alignment Problem: AI's Scary Challenge
Mentioned by
undefined
Sean Carroll
as
undefined
Stuart Russell
's new book on ensuring AIs do what we want.
94 | Stuart Russell on Making Artificial Intelligence Compatible with Humans
Mentioned by
undefined
Melanie Mitchell
in a discussion about the potential dangers of superintelligent AI.
Complexity and Intelligence with Melanie Mitchell - #464
Mentioned by
undefined
Chris Williamson
as
undefined
Stuart Russell
's book discussing the control problem in AI.
#364 - Stuart Russell - The Terrifying Problem Of AI Control
Mentioned by
undefined
Max Tegmark
as a recent book proposing solutions to the challenges of AI alignment.
75 | Max Tegmark on Reality, Simulation, and the Multiverse
Mentioned by
undefined
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

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app