94 | Stuart Russell on Making Artificial Intelligence Compatible with Humans

94 | Stuart Russell on Making Artificial Intelligence Compatible with Humans

Artificial intelligence has made great strides of late, in areas as diverse as playing Go and recognizing pictures of dogs. We still seem to be a ways away from AI that is "intelligent" in the human sense, but it might not be too long before we have to start thinking seriously about the "motivations" and "purposes" of artificial agents. Stuart Russell is a longtime expert in AI, and he takes extremely seriously the worry that these motivations and purposes may be dramatically at odds with our own. In his book Human Compatible, Russell suggests that the secret is to give up on building our own goals into computers, and rather programming them to figure out our goals by actually observing how humans behave.

Support Mindscape on Patreon.

Stuart Russell received his Ph.D. in computer science from Stanford University. He is currently a Professor of Computer Science and the Smith-Zadeh Professor in Engineering at the University of California, Berkeley, as well as an Honorary Fellow of Wadham College, Oxford. He is a co-founder of the Center for Human-Compatible Artificial Intelligence at UC Berkeley. He is the author of several books, including (with Peter Norvig) the classic text Artificial Intelligence: A Modern Approach. Among his numerous awards are the IJCAI Computers and Thought Award, the Blaise Pascal Chair in Paris, and the World Technology Award. His new book is Human Compatible: Artificial Intelligence and the Problem of Control.


Episoder(415)

345 | Adam Elga on Being Rational in a Very Large Universe

345 | Adam Elga on Being Rational in a Very Large Universe

Behaving rationally involves facing up to conditions of uncertainty; we never navigate the world with perfect confidence. Sometimes we are uncertain about the way the world is, but we can also be unce...

23 Feb 1h 34min

344 | Adam Gurri on Liberal Democracy and How to Fight For It

344 | Adam Gurri on Liberal Democracy and How to Fight For It

It's possible to look at the course of history over the past few centuries and discern a movement toward increasing democracy, freedom, and individual rights -- "liberalism," in the political-philosop...

16 Feb 1h 21min

343 | Tom Griffiths on The Laws of Thought

343 | Tom Griffiths on The Laws of Thought

For all that human beings spend a lot of their time thinking, it's far from obvious what that process actually entails. Part of it amounts to classical logical reasoning. But an even bigger part invol...

9 Feb 1h 19min

AMA | Feb 2026

AMA | Feb 2026

Welcome to the February 2026 Ask Me Anything episode of Mindscape! These monthly excursions are funded by Patreon supporters (who are also the ones asking the questions). We take questions asked by Pa...

2 Feb 3h 10min

342 | Rachell Powell on Evolutionary Convergence, Morality, and Mind

342 | Rachell Powell on Evolutionary Convergence, Morality, and Mind

Evolution with natural selection involves an intricate mix of the random and the driven. Mutations are essentially random, while selection pressures work to prefer certain outcomes over others. There ...

26 Jan 1h 37min

341 | Stewart Brand on Maintenance as an Organizing Principle

341 | Stewart Brand on Maintenance as an Organizing Principle

"Things fall apart; the centre cannot hold," wrote W.B. Yeats. I don't know about the centre, but the tendency of things to fall apart is pretty universal, ultimately due to the Second Law of Thermody...

19 Jan 1h 12min

340 | Rebecca Newberger Goldstein on What Matters and Why It Matters

340 | Rebecca Newberger Goldstein on What Matters and Why It Matters

At any given moment, an uncountable number of events are happening, but only some of them matter to us. What does it mean for something to matter, and more importantly, what does it mean for us to mat...

12 Jan 1h 18min

339 | Ned Block on Whether Consciousness Requires Biology

339 | Ned Block on Whether Consciousness Requires Biology

It's become increasingly clear that the Turing Test -- determining whether human interlocutors can tell whether a conversation is being carried out by a human or a machine -- is not a good way to thin...

5 Jan 1h 11min

Populært innen Vitenskap

fastlegen
rekommandert
jss
tingenes-tilstand
rss-rekommandert
villmarksliv
liberal-halvtime
sinnsyn
forskningno
rss-paradigmepodden
fjellsportpodden
nevropodden
rss-nysgjerrige-norge
diagnose
vett-og-vitenskap-med-gaute-einevoll
abid-nadia-skyld-og-skam
tidlose-historier
dekodet-2
smart-forklart
hva-er-greia-med