Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas27 Huhti 2020

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.

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(427)

AMA | August 2025

Welcome to the August 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 Patr...

4 Elo 20253h 39min

323 | Jacob Barandes on Indivisible Stochastic Quantum Mechanics

The search for a foundational theory of quantum mechanics that all physicists can agree on remains active. Over the last century a number of contenders have emerged, including Many-Worlds, pilot-wave ...

28 Heinä 20252h 58min

322 | Philip Pettit on Language, Agency, Politics, and Freedom

When we think of the capacities that distinguish humans from other species, we generally turn to intelligence and its byproducts, including our technological prowess. But our intelligence is highly co...

21 Heinä 20251h 20min

321 | David Tong on Open Questions in Quantum Field Theory

Quantum field theory is the basis for our most successful theories of fundamental physics. And yet, there are things we don't understand about it. Some of these puzzles are relatively well-known, whil...

14 Heinä 20251h 19min

AMA | July 2025

Welcome to the July 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 Patreo...

7 Heinä 20254h 3min

320 | Solo: Complexity and the Universe

Our universe started out looking very simple: hot, dense, smooth, rapidly expanding. According to our best current model, it will end up looking simple once again: cold, dark, empty. It's in between -...

30 Kesä 20252h 14min

319 | Bryan Van Norden on Philosophy From the Rest of the World

It is common to refer to philosophy as "a series of footnotes to Plato." But in the original quote, Alfred North Whitehead was more careful: he limited his characterization to "the European philosophi...

23 Kesä 20251h 12min

318 | Edward Miguel on the Developing Practice of Development Economics

Economics is seeing an upsurge in the importance of controlled, reproducible empirical studies. One area where this has had a great impact is on development economics, which studies the economies of l...

16 Kesä 20251h 20min