From the archive: Aligning AI with our values

From the archive: Aligning AI with our values

Author: Kensy Cooperrider – Diverse Intelligences Summer Institute October 18, 2023 Duration: 1:23:12

Hi friends, we're on hiatus for the fall. To tide you over, we're putting up some favorite episodes from our archives. Enjoy!

----

[originally aired February 17, 2021]

Guess what folks: we are celebrating a birthday this week. That's right, Many Minds has reached the ripe age of one year old. Not sure how old that is in podcast years, exactly, but it's definitely a landmark that we're proud of. Please no gifts, but, as always, you're encouraged to share the show with a friend, write a review, or give us a shout out on social.

To help mark this milestone we've got a great episode for you. My guest is the writer, Brian Christian. Brian is a visiting scholar at the University of California Berkeley and the author of three widely acclaimed books: The Most Human Human, published in 2011; Algorithms To Live By, co-authored with Tom Griffiths and published in 2016; and most recently, The Alignment Problem. It was published this past fall and it's the focus of our conversation in this episode.

The alignment problem, put simply, is the problem of building artificial intelligences—machine learning systems, for instance—that do what we want them to do, that both reflect and further our values. This is harder to do than you might think, and it's more important than ever.

As Brian and I discuss, machine learning is becoming increasingly pervasive in everyday life—though it's sometimes invisible. It's working in the background every time we snap a photo or hop on Facebook. Companies are using it to sift resumes; courts are using it to make parole decisions. We are already trusting these systems with a bunch of important tasks, in other words. And as we rely on them in more and more domains, the alignment problem will only become that much more pressing.

In the course of laying out this problem, Brian's book also offers a captivating history of machine learning and AI. Since their very beginnings, these fields have been formed through interaction with philosophy, psychology, mathematics, and neuroscience. Brian traces these interactions in fascinating detail—and brings them right up to the present moment. As he describes, machine learning today is not only informed by the latest advances in the cognitive sciences, it's also propelling those advances.

This is a wide-ranging and illuminating conversation folks. And, if I may say so, it's also an important one. Brian makes a compelling case, I think, that the alignment problem is one of the defining issues of our age. And he writes about it—and talks about it here—with such clarity and insight. I hope you enjoy this one. And, if you do, be sure to check out Brian's book.

Happy birthday to us—and on to my conversation with Brian Christian. Enjoy!

 

A transcript of this show is available here.

 

Notes and links

7:26 - Norbert Wiener's article from 1960, 'Some moral and technical consequences of automation'.

8:35 - 'The Sorcerer's Apprentice' is an episode from the animated film, Fantasia (1940). Before that, it was a poem by Goethe.

13:00 - A well-known incident in which Google's nascent auto-tagging function went terribly awry.

13:30 - The 'Labeled Faces in the Wild' database can be viewed here.

18:35 - A groundbreaking article in ProPublica on the biases inherent in the Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) tool.

25:00 – The website of the Future of Humanity Institute, mentioned in several places, is here.

25:55 - For an account of the collaboration between Walter Pitts and Warren McCulloch, see here.

29:35- An article about the racial biases built into photographic film technology in the 20th century.

31:45 - The much-investigated Tempe crash involving a driverless car and a pedestrian:

37:17 - The psychologist Edward Thorndike developed the "law of effect." Here is one of his papers on the law.

44:40 - A highly influential 2015 paper in Nature in which a deep-Q network was able to surpass human performance on a number of classic Atari games, and yet not score a single point on 'Montezuma's Revenge.'

47:38 - A chapter on the classic "preferential looking" paradigm in developmental psychology:

53:40 - A blog post discussing the relationship between dopamine in the brain and temporal difference learning. Here is the paper in Science in which this relationship was first articulated.

1:00:00 - A paper on the concept of "coherent extrapolated volition."

1:01:40 - An article on the notion of "iterated distillation and amplification."

1:10:15 - The fourth edition of a seminal textbook by Stuart Russell and Peter Norvig, AI a Modern approach, is available here: http://aima.cs.berkeley.edu/

1:13:00 - An article on Warren McCulloch's poetry.

1:17:45 - The concept of "reductions" is central in computer science and mathematics.

 

Brian Christian's end-of-show reading recommendations:

The Alignment Newsletter, written by Rohin Shah

Invisible Women, by Caroline Criado Perez:

The Gardener and the Carpenter, Alison Gopnik:

You can keep up with Brian at his personal website or on Twitter.

 

Many Minds is a project of the Diverse Intelligences Summer Institute, which is made possible by a generous grant from the Templeton World Charity Foundation to UCLA. It is hosted and produced by Kensy Cooperrider, with help from Assistant Producer Urte Laukaityte and with creative support from DISI Directors Erica Cartmill and Jacob Foster. Our artwork is by Ben Oldroyd. Our transcripts are created by Sarah Dopierala.

Subscribe to Many Minds on Apple, Stitcher, Spotify, Pocket Casts, Google Play, or wherever you listen to podcasts. You can also now subscribe to the Many Minds newsletter here!

We welcome your comments, questions, and suggestions. Feel free to email us at: manymindspodcast@gmail.com. 

For updates about the show, visit our website or follow us on Twitter: @ManyMindsPod.


There's a quiet revolution happening in how we understand intelligence, and it's not just about humans. Many Minds, hosted by Kensy Cooperrider of the Diverse Intelligences Summer Institute, digs into this expansive idea. Each episode is a journey into the inner worlds of creatures and creations we share the planet with. You'll hear from researchers who decode the complex social minds of crows, who map the sensory universe of an octopus, or who grapple with the emerging cognition of artificial systems. This isn't a dry lecture series; it's a collection of thoughtful conversations that feel like pulling up a chair with experts who are genuinely redefining what it means to think, feel, and learn. The Many Minds podcast operates from a simple but profound premise: to grasp our own human experience, we need to listen to the many other kinds of minds around us. Tune in every other week for explorations that are as much about philosophy and wonder as they are about science and education, all grounded in rigorous research and a deep curiosity about the beings-animal, human, and artificial-that fill our world.
Author: Language: English Episodes: 100

Many Minds
Podcast Episodes
The shaman with a thousand faces [not-audio_url] [/not-audio_url]

Duration: 1:18:16
When you hear the word "shaman," I'm guessing a web of associations starts to form in your mind. Perhaps you imagine strange ceremonies and strong substances; maybe you think of an earlier time when magic and superstitio…
Varieties of childhood [not-audio_url] [/not-audio_url]

Duration: 1:28:48
Childhood is a special time, a strange time. Children are adored and catered to—they're given their own menus and bedrooms. They're considered delicate and precious, and so we cushion them from every imaginable risk. Kid…
Science, AI, and illusions of understanding [not-audio_url] [/not-audio_url]

Duration: 59:47
AI will fundamentally transform science. It will supercharge the research process, making it faster and more efficient and broader in scope. It will make scientists themselves vastly more productive, more objective, mayb…
The primeval soil of play [not-audio_url] [/not-audio_url]

Duration: 56:37
Puppies wrestling and mock-biting each other. Toddlers playing hide and seek. Kittens pouncing—repeatedly—on a toy mouse. You've no doubt looked on at scenes like this with amusement. And you've no doubt seen some of tho…
The big five and beyond [not-audio_url] [/not-audio_url]

Duration: 1:46:39
If you've heard anything about the study of human personality, you've probably heard about the "big five." This is a framework that attempts to characterize human personality in terms of five broad factors or dimensions—…
Philosophers on psychedelics [not-audio_url] [/not-audio_url]

Duration: 1:40:49
Some call it the "psychedelic renaissance." In the last decade or so, interest in psychedelic drugs has surged—and not just among Silicon Valley types and psychiatrists and neuroscientists. It's also surged among a stere…
The cuttlefish and its coat of many colors [not-audio_url] [/not-audio_url]

Duration: 1:33:38
We humans have a hard time becoming invisible. For better or worse, we're basically stuck with the skin and body we have; we're pretty fixed in our color, our shape, our overall appearance. And so we're fascinated by cre…
Life, free energy, and the pursuit of goals [not-audio_url] [/not-audio_url]

Duration: 1:06:49
You've probably come across the "free energy principle." It's become one of the most influential ideas in the broader cognitive sciences. Since the neuroscientist Karl Friston first introduced it in 2005, the theory has…
Universal emotions in fact and fiction [not-audio_url] [/not-audio_url]

Duration: 1:20:22
Are human emotions universal? Or do they vary from one place to the next and from one time period to the next? It's a big question, an old question. And every discipline that's grappled with it brings its own take, its o…
From the archive: Fermentation, fire, and our big brains [not-audio_url] [/not-audio_url]

Duration: 1:05:36
Hi friends, We're taking care of some spring cleaning this week. We'll be back in two weeks with a new episode. In the meantime, enjoy this favorite from our archives! - The Many Minds team ––––––––– [originally aired Fe…