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.


Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(426)

AMA | November 2025

AMA | November 2025

Welcome to the November 2025 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...

17 Nov 20253h 34min

335 | Andrew Jaffe on Models, Probability, and the Universe

335 | Andrew Jaffe on Models, Probability, and the Universe

Science has an incredibly impressive track record of uncovering nonintuitive ideas about the universe that turn out to be surprisingly accurate. It can be tempting to think of scientific discoveries a...

10 Nov 20251h 17min

334 | Daniel Whiteson on the Physics of and by Aliens

334 | Daniel Whiteson on the Physics of and by Aliens

The universe as revealed by physics is objective: it's out there, existing and behaving in ways that are completely independent of human thought. But the process by which we learn about the universe, ...

3 Nov 20251h 14min

333 | Gordon Pennycook on Unthinkingness, Conspiracies, and What to Do About Them

333 | Gordon Pennycook on Unthinkingness, Conspiracies, and What to Do About Them

Why are people wrong all the time, anyway? Is it because we human beings are too good at being irrational, using our biases and motivated reasoning to convince ourselves of something that isn't quite ...

27 Okt 20251h 10min

332 | Dmitri Tymoczko on the Mathematics Behind Music

332 | Dmitri Tymoczko on the Mathematics Behind Music

Music is math that you can dance to. The fact that certain notes sound good when played together, or in succession, is related to the mathematical properties of the frequencies to which they correspon...

20 Okt 20251h 21min

AMA | October 2025

AMA | October 2025

Welcome to the October 2025 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 Pat...

13 Okt 20253h 37min

331 | Solo: Fine-Tuning, God, and the Multiverse

331 | Solo: Fine-Tuning, God, and the Multiverse

Certain features of our universe seem unnatural to us. These include "constants of nature" such as the cosmological constant and the mass of the Higgs boson, as well as features of the initial conditi...

6 Okt 20251h 54min

330 | Petter Törnberg on the Dynamics of (Mis)Information

330 | Petter Törnberg on the Dynamics of (Mis)Information

A characteristic of complex systems is that individual components combine to exhibit large-scale emergent behavior even when the components were not specifically designed for any particular purpose wi...

29 Sep 20251h 12min

Populært innen Vitenskap

fastlegen
tingenes-tilstand
liberal-halvtime
sinnsyn
villmarksliv
rss-zahid-ali-hjelper-deg
forskningno
rekommandert
rss-overskuddsliv
jss
rss-paradigmepodden
tidlose-historier
vett-og-vitenskap-med-gaute-einevoll
fjellsportpodden
dekodet-2
rss-nysgjerrige-norge
rss-inn-til-kjernen-med-sunniva-rose
nevropodden
kvinnehelsepodden
diagnose