Will AI destroy us... or save us?

Summary

Throughline: "Will AI Destroy Us... or Save Us?" — Detailed Episode Summary

Podcast: Throughline (NPR)
Air Date: April 9, 2026
Hosts: Rund Abdelfatah, Ramtin Arablouei

---

Episode Overview

This Throughline episode explores humanity's long and complicated relationship with artificial intelligence, posing the titular question: will AI save us, destroy us, or perhaps, simply reflect who we already are? With stories spanning ancient mythology to the rise of modern AI, the show weaves expert interviews, cultural references, and signature Throughline sound production to trace how dreams and fears about machine intelligence are deeply entangled with the search for what makes us human.

---

Main Themes & Structure

• The Interplay of Fear and Fascination: How Hollywood and science fiction seed both utopian and apocalyptic expectations for AI.
• Humanity's Drive to Create: Exploration of why people have always sought to understand and ultimately replicate intelligence—in machines, myths, and stories.
• Origins of AI and Social Context: The historical, social, and industrial roots of AI, from the Dartmouth Conference to the Cold War.
• Man vs. Machine—And Beyond: Key moments like Kasparov vs. Deep Blue illuminate shifting relationships between humans and their creations.
• The Question of the Soul: Is there something fundamentally human that can’t be replicated by code?
• Hope, Responsibility, and Reflection: Moving away from techno-determinism to ask what choices humans can make, given the mirror AI holds up to us.

---

Key Discussion Points & Insights

I. Myths, Movies, and the AI Mindset

[00:49–04:21]

• Hosts and guests highlight how Hollywood shapes our collective understanding of AI, referencing “Terminator,” “Ex Machina,” “Star Trek,” and “The Matrix.”
• Meredith Broussard: “Most of us, when we hear the term AI, we think about Hollywood.” (00:49)
• The tension: AI as either magical savior or existential threat.
• Humans are “totally immersed in an AI world” already, from smartphones and GPS to dating apps and government surveillance. (George Zarkoudakis, 02:48)
• AI described as “not a harbinger of utopia or dystopia, and it changes its configuration in order to be able to predict stuff.” (Garry Kasparov & George Zarkoudakis, 01:41–01:43)

Memorable Moment:

• Host as ChatGPT: "I don't have feelings or emotions like love...I exist solely to assist with generating text." (03:16)

II. The Big Bang of Human Intelligence

[05:15–12:46]

• George Zarkoudakis recounts the impact of science fiction in stoking curiosity—his first robot sighting in "Forbidden Planet" as a child. (08:16–09:32)
• Discussion of art, language, and storytelling as pivotal achievements of early humans enabling information transfer, learning, and imagination.
• Zarkoudakis: "Something amazing happens...our ancestors start creating art...tell stories about how they experience the world." (11:58–12:20)
• The transition from chiseling stones to imagining gods, stars, and technology.

III. From Genome to Computer—Seeking the Blueprint

[13:31–18:47]

• Introduction of Francis Collins, Human Genome Project leader.
• Collins reflects: “There's more to life than just molecules...but if you want the biological basis of life, yeah, this was discovering...the book of life that's inside each cell.” (15:30)
• The drive to "read" the instruction book of life and the parallel to programming machines.
• Mainframe era: early computers were human "computers," mostly women, working in noisy, hot environments doing mechanical calculation—a history often erased.

IV. The Machine Age: Efficiency, Power, & the Cost

[22:19–25:48]

• The Dartmouth Conference of 1956 and the "origin myth" of AI.
  • Meredith Broussard: “It fascinates me. It's an enormously grandiose idea.” (23:30)
  • Stephanie Dick: AI’s historical origins are full of "erasure"—not recognizing its deep ties to capitalism, industrialization, and colonialism.
• Charles Babbage: Factory automation as a model for mechanizing thought, devaluing both working class labor and the mechanical tasks delegated to machines.

Notable Quote:

• Dick, on Babbage: "...famously, I wish to God these calculations had been produced by steam." (26:57)

V. From Wonder to Worry: Technology and Apocalyptic Fears

[27:34–29:17]

• Post-atomic bomb era: Excitement about human ingenuity gives way to fear of total destruction.
• Zarkoudakis: “...then we discovered something that can destroy us completely. It was terrifying.” (28:08)
• The roots of technological skepticism; "machines to replace God with science."

VI. Man vs. Machine: The Chessboard and Beyond

[40:28–46:26]

• The Deep Blue vs. Garry Kasparov matches: Pivotal moment when a computer defeats a human chess champion (1997).
  • Kasparov: “I was unbeatable at the chessboard. … It was a clear sign for me that the history of us competing with machines will be over soon.” (41:10, 44:41)
• The “receding horizon”: As machines overtake one area of human distinction (chess), humans seek new benchmarks (Go, poetry, intuition).

Notable Quote:

• Stephanie Dick: "There's a really exact and clear example of the so-called receding horizon, where people really want to reserve something for ourselves that is not mechanizable." (45:06)

VII. Collaborating with the Machine: The Genomic Revolution & Machine Learning

[46:26–49:53]

• Completion of the Human Genome project—reading our own "instruction book."
• The rise of machine learning: Shift from modeling the human mind to letting computers find patterns in vast data sets.
  • Meredith Broussard: “When you are building a computer program, it'll work if you do it this way, and then it won’t work if you do it the other way. But that’s not how culture operates... that’s not how relationships work.” (50:21)
• The birth of “black box” AI and new fears around bias, surveillance, and societal impacts.

VIII. What Makes Us Human? The Question of the Soul, Morality, and Machines

[36:04–39:07, 50:01–53:31]

• "Robot" as a word: From the Slavic for "serf/slave"—exploring the exploitation of both workers and machines.
• Recap of the play "Rossum’s Universal Robots" in how it predicted both the triumph and tragedy of machines: intelligence with no soul, until, in a twist, love awakens in two robots.
• Francis Collins: Grappling with faith, aesthetics, and meaning at the limits of science:
  • “Does our DNA tell us that that beautiful sunset was something to stop for just a moment and kind of be a little bit in awe... Is that written in my DNA? What is that about?” (38:48)
• Ongoing philosophical tension: Is there more to humanity than can be encoded in logic and math?

IX. AI as a Mirror: Optimism, Caution, and Human Agency

[52:16–53:31]

• Garry Kasparov: “I still believe that...the history of humanity gives us reasons to be optimistic.”
• AI reflects back our own values and pitfalls—it is up to us what we see and how we respond.
  • Kasparov: “Machine is like a mirror. And if you don’t like what we see in the mirror, you have two choices: work on your body to improve the picture, or try to distort the mirror. The latter decision...is a recipe for disaster.” (52:43)

---

Memorable Quotes & Moments (with Timestamps)

• “AI is not a magic wand, but it's not a Terminator.”
  — Garry Kasparov, (01:34)
• "It's really complicated, beautiful math, but it is fundamentally just math.”
  — Meredith Broussard, (01:53)
• “We are, in fact, totally immersed in an AI world…”
  — George Zarkoudakis, (02:48)
• “Wonder is the feeling of the philosopher, and philosophy begins in wonder.”
  — Rund Abdelfatah, (07:57)
• “What can the mind do without a body? And therefore, what might the machine do since it doesn’t have one?”
  — Stephanie Dick, (33:32)
• "There's a deep desire for the human condition not to be a deterministic output of our chemical or genetic or cultural forces, but for there to be something that allows for free will and surprise and creativity that belongs to us."
  — Stephanie Dick, (50:01)
• “Let’s recognize that it’s about us. The machine is like a mirror. And if you don’t like what we see in the mirror, you have two choices…”
  — Garry Kasparov, (52:43)

---

Timestamps for Key Segments

• [00:49–04:21] – Myths and sci-fi frame our collective imagination of AI.
• [07:57–13:21] – What makes us human: art, storytelling, the big bang of the mind.
• [18:55–22:19] – Early computer era and the roots of AI as a field.
• [22:24–29:17] – Social, industrial, and political motivations behind AI development.
• [40:28–46:26] – Deep Blue defeats Kasparov and “the receding horizon.”
• [47:11–49:53] – Human Genome Project and machine learning’s rise.
• [50:01–53:31] – The meaning of the human soul, AI’s limitations, and future ethics.

---

Tone & Language

The episode is rich, reflective, and sometimes haunted, blending narrative history with philosophical inquiry. It features a mix of academic expertise, personal storytelling, and cultural commentary delivered in the signature, immersive Throughline style.

---

Conclusion

The hosts and guests ultimately suggest that the real question isn’t whether AI will save or destroy us—but what we see when we look in this new technological mirror, and what kind of world we choose to build as a result. AI, they argue, amplifies both human flaws and potential. The story is as much about the creators as their creations, about agency and ethics, and about facing a future where the soul of humanity is both challenged and defined by the machines we make.

Transcript

[NPR Sponsor Announcer]

This message comes from NPR sponsor Hulu. From the executive producers of the Handmaid's Tale comes the Testaments, a new Hulu original series based on the novel by Margaret Atwood. Now streaming on Hulu and Hulu on Disney plus for bundle subscribers. Terms apply.

[George Zarkoudakis]

Open the pod bay doors.

[Narrator / Host (Karone DeMars)]

Halloween. I'm sorry, Dave. I'm afraid I can't do that. This conversation can serve no purpose anymore. Goodbye.

[Stephanie Dick]

It's alive.

[Narrator / Host (Karone DeMars)]

It's alive. It's alive.

[Meredith Broussard]

Most of us, when we hear the term AI, we think about Hollywood.

[Narrator / Host (Karone DeMars)]

Why do you cry?

[Rund Abdelfatah]

You mean people?

[Narrator / Host (Karone DeMars)]

Yeah. I don't know. We just cry.

[Meredith Broussard]

We think about the Terminator. We think about Ex Machina.

[Rund Abdelfatah]

You program her to flirt with me?

[Narrator / Host (Karone DeMars)]

If I did, would that be cheating?

[Rund Abdelfatah]

Wouldn't it?

[Meredith Broussard]

We think about Star Trek.

[Narrator / Host (Karone DeMars)]

Please state the nature of the medical emergency.

[Meredith Broussard]

Or maybe Star Wars. Hollywood is so deeply embedded in our brains.

[Narrator / Host (Karone DeMars)]

I'll be back.

[George Zarkoudakis]

What does AI actually mean? You know, really mean?

[Garry Kasparov]

AI is not a magic wand, but it's not a Terminator.

[George Zarkoudakis]

This system learns by accessing data.

[Garry Kasparov]

AI is not a harbinger of utopia

[George Zarkoudakis]

or dystopia, and it changes its configuration in order to be able to predict stuff.

[Garry Kasparov]

AI is something invented by us to advance our progress.

[Meredith Broussard]

It's really complicated, beautiful math, but it is fundamentally just math.

[Stephanie Dick]

AI is deeply entangled with our desire to be in control, both of ourselves and the world around us. To control human behavior, to control the future, to control environmental outcomes, to control institutions and societies.

[George Zarkoudakis]

AI is already here.

[ChatGPT / AI Voice]

It's in your phones.

[Narrator / Host (Karone DeMars)]

Siri or Google or Alexa, your cars. Google Maps uses a very smart algorithm

[ChatGPT / AI Voice]

to provide your homes.

[Narrator / Host (Karone DeMars)]

The Home Security System uses artificial intelligence to keep your family safe, your skies, from drones to unmanned aircrafts and beyond,

[ChatGPT / AI Voice]

your hospitals interpreting X rays, your love lives, the dating apps, your virtual lives,

[George Zarkoudakis]

social media companies spy on us, your

[Narrator / Host (Karone DeMars)]

governments, what it means for the future of our democracy.

[George Zarkoudakis]

So we are, in fact, totally immersed in an AI world. The challenge is not to act automatically.

[Narrator / Host (Karone DeMars)]

It's to find an action that is not automatic.

[George Zarkoudakis]

From painting to breathing, to talking, to falling in love.

[Rund Abdelfatah]

Are you capable of falling in love?

[ChatGPT / AI Voice]

I don't have feelings or emotions like love, and I don't have a subjective experience. I exist solely to assist with generating text.

[Ramtin Arablouei]

This is ChatGPT.

[ChatGPT / AI Voice]

I am an AI language model developed by Open AI. I can answer questions, provide information and engage in conversations on a variety of topics. How may I assist you?

[Rund Abdelfatah]

Today, AI has become an invisible architecture upon which modern life is being built. It's wrapped up in our jobs, our government, our wars, our art. Sometimes without us even realizing it.

[Narrator / Host (Karone DeMars)]

Right now we're inside a computer program. Is it really so hard to believe you've been living in a dream world? Neo

[Rund Abdelfatah]

there's something powerful about the story the Matrix and countless other sci fi books and movies tell the AI becomes sentient, so surpasses human intelligence and lays claim to our world. Sure, it's a terrifying thing to imagine, and yet we're fascinated by these stories

[Ramtin Arablouei]

exploring that feeling, the tension between our love of AI and our fear of it is what this episode is really about, in a sense, decoding the humans behind the machines.

[George Zarkoudakis]

As an animal, we're a very weak creature. The only thing that we have is our social structure and our collective and individual minds. And those minds compel us to extend our capabilities. And that is I think in many ways why people sort of imagined gods being just like them, only more powerful.

[Ramtin Arablouei]

This is George Zarkoudakis.

[George Zarkoudakis]

I have a PhD in AI and I'm actively working in the field over many years.

[Ramtin Arablouei]

He also wrote a book all about the history of artificial intelligence from ancient times to present day called In Our Own Image.

[George Zarkoudakis]

Will AI Save Us or Destroy Us?

[Rund Abdelfatah]

At the heart of this history are a few key questions. Why do we want to create artificial intelligence? What would it mean for a machine to become intelligent? And how would that change our lives?

[George Zarkoudakis]

Most of the questions I don't think we'll be able to answer at this particular point in history, but I don't think we can resist the temptation of asking them and trying to answer them.

[Ramtin Arablouei]

Coming up, we begin at the very beginning, the big bang of the human mind.

[Narrator / Host (Karone DeMars)]

This is Karone DeMars from San Antonio, Texas. You're listening to Throughline from NPR.

[NPR Sponsor Announcer]

This message comes from Betterment. You know, when you sell a stock or any investing asset and start to feel the dread of getting a surprise tax bill? Betterment's tax impact preview tool shows you the estimated tax impact of the sale so you can make informed tax smart investing decisions. Get started [e-mail] investing involves risk performance not guaranteed. Betterment is not a tax advisor nor should any information herein be considered tax advice. Please consult a qualified tax professional.

[Commercial Announcer]

This message comes from Granger. This is the story of the one As a maintenance supervisor at a manufacturing facility, he knows keeping the line up and running is a top priority. The that's why he chooses Grainger, because when a drive belt gets damaged, Grainger makes it easy to find the exact specs for the replacement product he needs. And next Day delivery helps ensure he'll have everything in place and running like clockwork. Call 1-800-GRAINGER, click grainger.com or just stop by Grainger for the ones who get it done.

[NPR Sponsor Announcer]

This message comes from Warby Parker. Prescription eyewear that's expertly crafted and unexpectedly affordable. Glasses designed in house from premium materials starting at just $95, including prescription lenses. Stop by a Warby Parker store near you.

[Rund Abdelfatah]

What is a human?

[Narrator / Host (Karone DeMars)]

What is a human?

[ChatGPT / AI Voice]

What is a human? A human is a species of primates characterized by advanced cognitive abilities and a capacity for abstract reasoning. They have a highly developed brain and have created complex societies over thousands of years. They have the unique ability of self awareness, allowing them to understand their own thoughts, emotions and experiences. Humans are capable of both great kindness and compassion as well as violence and aggression.

[Rund Abdelfatah]

Part one I think, therefore I am. Wonder is the feeling of the philosopher. And philosophy begins in wonder.

[George Zarkoudakis]

I lived in Athens then. I was like five, six years old. And it was summertime. And in Greece they still do it. They have like open air circles, cinemas. In the summer you go in the open air cinema, there's no roof, you know, there's a screen in front of you. You sit there, you make a lot of noise. It's great. And my mother took me to watch a film that, you know, the people who had the cinema decided to show. It was an old film. It was called Forbidden Planet. It was all about, you know, a spaceship landing on another planet and finding sort of this crazy scientist who had a robot. And that was the first time I actually saw a robot in my Life.

[Narrator / Host (Karone DeMars)]

Welcome to Al Ter 4, gentlemen. I am to transport you to the residence.

[George Zarkoudakis]

I never imagined there would be a thing.

[Narrator / Host (Karone DeMars)]

If you do not speak English, I am at Your disposal with 187 other

[George Zarkoudakis]

languages made of metal tin that had a mind.

[Narrator / Host (Karone DeMars)]

You are a robot, aren't you? That is correct, sir. For your convenience, I am monitored to respond to the name Robbie.

[George Zarkoudakis]

Ever since that moment, I was so fascinated with the idea that we can develop artifacts, artificial things that can think, that can act, that can behave like us humans.

[Rund Abdelfatah]

It was 1969 when George watched in wonder as Robbie the robot rolled across the big screen. Something that may have seemed like a far off reality for a kid growing up in the 60s. But then again, humans had just witnessed man landing on the moon.

[Narrator / Host (Karone DeMars)]

Tranquility Base here. The eagle has landed.

[George Zarkoudakis]

I mean, that was the culmination, the realization of centuries of dreaming about going to space.

[Rund Abdelfatah]

For George and millions of others around the world, it was proof that humans can imagine and then create the capacity to transcend ourselves. And that stories provide the roadmap.

[George Zarkoudakis]

I interviewed a lot of people to see what made them become scientists or engineers. And it was always some kind of, you know, book, kind of comic something, right, that excited them, that triggered their imagination. It could be, you know, the outer space of planets and asteroids and whatnot, but it could also be the inner space, the human body. So those stories are very powerful. And I try to sort of explore those stories, where they come from, what are they telling us about this desire to become, in a way, like gods. So, you know, big bang of the universe, whatever it was before something happened, it changed. Boom. We have something different now. Protons and, I don't know, dogs, cats, you and me, whatever. Our species has been around probably for maybe 300, 400,000 years, and yet for most of that time, were doing, you know, chiseling some stones, hunting some animals, you know, living very simply in caves, you know, not a lot was happening. And then around 40 and 60,000 years ago,

[Narrator / Host (Karone DeMars)]

boom.

[George Zarkoudakis]

The big bang of the human mind. Something amazing happens. And our ancestors across the world, by the way, right, start creating art, start to narrate, tell stories about how they experience the world.

[Ramtin Arablouei]

When love beckons to you, follow him,

[Narrator / Host (Karone DeMars)]

Though his ways are hard and steep.

[Ramtin Arablouei]

Through the. Through these stories, we project our hopes, fears and dreams onto the canvas of the invisible unknown.

[George Zarkoudakis]

All the earth is a grave and nothing escapes it. And that meant also that we were able to transfer information and knowledge to the next generation.

[Garry Kasparov]

The divine gift does not come from

[Narrator / Host (Karone DeMars)]

a higher power, but from our own minds.

[George Zarkoudakis]

And that's what kicked off this amazing journey of our species to where we are today. What seems to have happened is some kind of genetic mutation that furnished us, our species in particular, with the ability of. Of language.

[Ramtin Arablouei]

Language and stories. We know they're part of what makes us human. But what else?

[Narrator / Host (Karone DeMars)]

This body, what is it? How did it begin? People somehow think maybe we knew about DNA for the last several centuries. We didn't. It really wasn't that clear what was. The hereditary material that passes from parent to child and that carries all those genetic factors.

[Rund Abdelfatah]

This is Francis Collins. Maybe you've heard of him. But in case not, I asked Chatgpt to write up a bio. Here's what it gave me. Francis Collins is a renowned physician, geneticist. He earned his MD and PhD at Yale University and is best known for his leadership of the Human Genome Project, a landmark international research effort to decode the entire human genetic blueprint.

[Narrator / Host (Karone DeMars)]

The people at the University of North Carolina will be upset to hear that. Chatgpt said, I got my MD from Yale, but that's okay.

[Rund Abdelfatah]

So there's an error in there.

[Narrator / Host (Karone DeMars)]

There is an error.

[Rund Abdelfatah]

Were there any other mistakes?

[Narrator / Host (Karone DeMars)]

There was a bit of an omission. I don't think there was any mention of the 12 years I spent as the director of the National Institutes of health under three presidents, but that's okay.

[Rund Abdelfatah]

We asked ChatGPT to comment on its error.

[ChatGPT / AI Voice]

I apologize for any errors in the biography of Francis Collins. As a language model, I am trained on a large dataset of text. I may make mistakes or omissions. I recommend fact checking any information that I provide.

[Rund Abdelfatah]

Don't worry, we will.

[Ramtin Arablouei]

So much of the driving force behind Collins work is trying to understand why what makes humans human. Like at the most basic molecular level, but also beyond that. Growing up in the 1950s, he was amazed by the recent discovery of the structure of DNA.

[Narrator / Host (Karone DeMars)]

There were covers of Life magazine saying, discovering the secret of life.

[Rund Abdelfatah]

Was it actually discovering the secret of life?

[Narrator / Host (Karone DeMars)]

It's maybe a little over the top because I actually think there's more to life than just molecules. But certainly if you want to talk the biological basis of life, yeah, this was discovering that it's kind of, you know, the book of life that's inside each cell. It's incredibly inspiring to think about this. And it is the same kind of molecule that all living things on this planet use. Another reason to be pretty sure that we're all descended from some common ancestor. And that as this information molecule evolved over time, it took on different letters and different orders, but it was still that double helix with all of that potential.

[Ramtin Arablouei]

Potential. Part of what this discovery did was show us humans a way into understanding things about ourselves we hadn't yet discovered. And Collins believed to further unlock the secrets of who we are, we needed to decode our genetic programming.

[Narrator / Host (Karone DeMars)]

The big question was, okay, this is a book. We are information organisms and this is our information source. It's digital, but it's not actually carrying out the actions. How does that happen? How do you take this information and cause a cell to actually do something? If we were going to get that intelligent about our own instruction book, maybe we could not just read it, but we could actually occasionally figure out out how to do a find and replace. When something was misspelled, it was clear to me, if we want to do this, we've got to have a better database to work with. We need the human genome. That became my dream. If you're talking about what you can feel, what you can smell, what you can taste and see, then real is simply electrical signals interpreted by your brain. This is the world that you know. You are listening to the heartbeat of the sage computer. Every instrument in this room is constantly monitoring, testing, pulse, taking, controlling.

[Rund Abdelfatah]

This era when humans were seeking mastery of the sky and the body was in many ways dependent on another groundbreaking technology of the time, an additional brain that can work faster than ours, but does what we wish we could do. The computer.

[George Zarkoudakis]

In the old days, the word computer usually meant a person, usually a woman, actually, that sat down and did mathematical calculations by hand. Okay. And by rule, a ruler. Right? And then that word computer, which described a human being, was transposed into the machine because the machine can do it better.

[Stephanie Dick]

So the mainframe computers would only fit in these massive rooms in the basement, which is fitting because these devalued laborers who did the actual programming work were down there. My name is Stephanie Dick, and I'm an assistant professor in the School of Communication at Simon Fraser University.

[Rund Abdelfatah]

She holds a PhD in the history of science with a specialization in the history of mathematics and computing.

[Stephanie Dick]

These machines produced massive amounts of heat and noise, and working with them, you had to carry these boxes of punch cards back and forth as well, input and output, and stick it into the machine. This is like a sweatshop. Everything was really slow, very different from the machinery that we're all used to today, which is almost as fast as light and, you know, conforms to our every demand. You know, the most disturbing part of the history of AI for me comes from the fact that these men who were working in artificial intelligence looked at those massive, noisy, hot mainframe computers and saw themselves in it. They looked at them and identified a deep affinity, that there was something fundamentally shared between their minds and these machines.

[Ramtin Arablouei]

Coming up, as we unlock the secret secrets of man and machine, we ask the question, will this knowledge bring us closer to perfection or destruction?

[ChatGPT / AI Voice]

Hi, this is Christopher from Los Angeles, California.

[Narrator / Host (Karone DeMars)]

I love Throughline because it is always informative and keeps me alive.

[NPR Sponsor Announcer]

Support for this podcast and the following message come from Strawberry Me. If you could go back and talk to your younger self, would you tell yourself that you have a job that truly makes you happy? Many people are stuck in jobs they've outgrown or never really wanted. A career coach from Strawberry Me can help you move on to something you actually love. Benefit from having a dedicated coach in your Corner, and get 50% off your first coaching session at Strawberry Me. NPR. This message comes from NPR sponsor Hulu from the executive producers of the Handmaid's Tale, comes the Testaments, a new Hulu original series. Golden Globe nominee Chase Infinity plays Agnes, who guides new student Daisy at Aunt Lydia's school for future wives. Their bond leads the sisterhood to start challenging authority and seek independence. This is just the beginning of their reckoning. Watch the Testaments, now streaming on Hulu and Hulu on Disney for bundle subscribers. Terms apply. This message comes from MITI Health introducing agewell Longevity Care, designed by women for women. Whether you're looking to prevent future health issues or just feel more like yourself, learn [e-mail] that's joinmidi.com

[Rund Abdelfatah]

what is a machine?

[ChatGPT / AI Voice]

A machine is a device that can perform specific tasks more efficiently or with greater precision than humans can do alone. The basic idea behind the machine is to make work easier. Humans have been creating machines for thousands of years, starting with simple tools like the wheel and advancing to complex machines like computers and robots. The relationship between humans and machines continues to evolve and is likely to become increasingly important as advances in artificial intelligence continue to shape our world.

[Rund Abdelfatah]

Part 2AMore Perfect Human

[Meredith Broussard]

It's 1956. It's summer. It's the Dartmouth math department and everybody has left. So the department is empty and 10 men get together to invent the field of artificial intelligence.

[Stephanie Dick]

It was instigated by John McCarthy, who was a mathematics professor at Dartmouth. The proposal that John McCarthy wrote pulls no punches at all.

[Meredith Broussard]

We propose that a two month, 10 man study of artificial intelligence be carried out during the summer of 1956 at Dartmouth College in Hanover, New Hampshire. Second sentence the study is to proceed on the basis of the conjecture that every aspect of learning or any other

[Stephanie Dick]

feature of intelligence can in principle be so precisely described that a machine can

[Meredith Broussard]

be made to simulate it.

[Stephanie Dick]

So right from the beginning there's this pronouncement that human learning and intelligence can be mechanized and automated.

[Meredith Broussard]

It fascinates me. It's an enormously grandiose idea. My name is Meredith Broussard, I'm a data journalism professor at nyu and I'm the author of More Than a Confronting Race, Gender, and Ability Bias in Tech. Something else that I think was really interesting about this conference is they decided on the name artificial intelligence as the name of their new field. I think the name was chosen aspirationally. Most of the people who are at the forefront of artificial intelligence are great consumers of and lovers of science fiction. And so there's a lot of desire to make science fiction real, that you're going to make a sentient machine.

[Stephanie Dick]

The Dartmouth Conference has become an origin myth, commemorated with a plaque and everything on this site. Artificial intelligence was born. But in practice, the conference was a bit of a flop, actually. There was a lot of conflict and tension and disagreement, and there wasn't actually a coherent field that emerged out of the conference. Of course, the origin myth served to empower these men to tell their own story. And it's a story full of erasure. We hear nothing in that origin myth about the relationship that AI has to, to industrialization or to capitalism or to these colonial legacies of reserving reason for only certain kinds of people and certain kinds of thinking.

[Ramtin Arablouei]

That deeper story takes us back to the early days of, of industrialization. In the late 1700s and early 1800s, factories started popping up across the world, reshaping the nature of work more and more tasks that had once been done only by human hands were now the work of machines.

[Stephanie Dick]

Over in England, Charles Babbage, English mathematician, was touring factories in the context of industrialization and thinking, wow, these factories can tell us something about the human mind because they tell us about how processes can be broken down and what the elementary steps, even, of thought might be. So we also see in this moment a kind of devaluation of the classes of people and or machines who do this sort of repetitive, mechanical, broken down labor in service of efficiency and profit maximization and industrialization and early capitalism. Babbage was really dismissive of working class people. He thought they were annoying and filthy and they were always making noise and singing songs and said famously, I wish to God these calculations had been produced by steam, by which he meant the steam engine which was driving factory automation at the time.

[George Zarkoudakis]

People have been playing around with what is called automata, essentially machines that would automatically do something simple for centuries.

[Ramtin Arablouei]

This is George Zarchadakis again.

[George Zarkoudakis]

So there was always this idea of replicating nature, replicating movement, because movement was related to life. I think the Industrial Revolution was in many ways a culmination of all those ideas that people have been experimenting on and off for at least 2000 years.

[Narrator / Host (Karone DeMars)]

Our blows will destroy their whole modern industrial plant and organization.

[George Zarkoudakis]

Something happened to our collective psyche after the atom bomb.

[Narrator / Host (Karone DeMars)]

At 0 minus 15 seconds, a warning tone sounds in the plane. They hoped that it would put an end to this war, put an end to a butchery that had been going on for many years.

[George Zarkoudakis]

Until then. Everybody was excited about new things and about new discoveries and about new technologies. And then we discovered something that can destroy us completely. It was terrifying.

[Narrator / Host (Karone DeMars)]

I still remember the day very well because this Was a river filled with dead bodies.

[George Zarkoudakis]

And I think that's when people realized that maybe there are some technologies that are not for good. And that's when we became gradual as public, more skeptical to technologies.

[Rund Abdelfatah]

But some elite academics and scientists believed that better technology was actually the key to our future because it could help us bypass the messy parts of being human.

[Stephanie Dick]

What if human decision making procedures were too slow? What if people's judgments are clouded by their emotions to give us more control

[Rund Abdelfatah]

over ourselves and the world around us?

[Stephanie Dick]

Our machines will churn out the right answers and the right decisions and the

[Rund Abdelfatah]

right judgments, and in effect, replace God with science.

[Stephanie Dick]

And it's such a confident moment in American academia. After the war, there was more money, there were more people, there was more cultural capital, more political capital for sciences and technology than ever before. There's also a real concern about the practicalities of preventing a nuclear war, which was a very real threat at that time.

[Narrator / Host (Karone DeMars)]

We all know the atomic bomb is very dangerous. That's why these children are practicing to duck and cover. We hope it never comes, but since it may be used against us, we must get ready.

[Stephanie Dick]

Nuclear detente, and in particular mutually assured destruction, rely very specifically on information processing capability. You need to know where your enemy's nuclear arsenals are. You need to know if you've been attacked or that you are about to be.

[George Zarkoudakis]

And the argument went that if the United States could have a system that could think, that could strategize, that could react more intelligently than a group of generals and admirals, then we would have a clear advantage over the Soviet Union.

[Stephanie Dick]

The fear that people were too limited to be trusted to preserve peace. So let's double down on high technological hyperrationalism.

[George Zarkoudakis]

And that's how artificial intentions came about.

[Narrator / Host (Karone DeMars)]

Your scientists were so preoccupied with whether or not they could, they didn't stop to think if they should.

[Ramtin Arablouei]

Which brings us back to that famous Dartmouth conference in the summer of 1956. With the cold war driving interest in artificial intelligence, There was a lot of money up for the taking. And a conference of mathematicians and scientists from top tier universities and labs seemed like a pretty good investment.

[Stephanie Dick]

There was exactly one running computer program that was operational and presented at the conference, and it was the logic theory machine that had been developed by Alan Newell and Herbert Simon at the Rand Corporation. And it enshrined a particular vision of the human mind. Herbert Simon is famous for saying that human minds and modern digital computers are, quote, unquote, species of the same genus. They are fundamentally the same. Just a symbol processing Machine that takes symbolic information as input, manipulates it according to a set of rules and outputs decisions, solutions, judgments, and so on. Bodies don't matter, Society doesn't matter.

[ChatGPT / AI Voice]

Matter.

[Ramtin Arablouei]

One proposed measure of machine intelligence was something called the Turing Test, named for its creator, British mathematician Alan Turing, who you might remember from the movie the Imitation Game.

[Narrator / Host (Karone DeMars)]

Would you like to play? Play. It's a game, a test of sorts for determining whether something is a machine

[Stephanie Dick]

or a human being, was based on a parlor game for swapping gender that says a man and a woman leave the room and the partygoers have to figure out who's the man and who's the woman by sending questions back and forth on paper. And the man's job is to try to pretend to be the woman, and the woman's job is to be herself. And he says, what if we took the same test and replaced the man by a computer and the woman by any person? And then the judge, of course, is meant to be able to figure out whether the machine is the human or the human is the human. And what I have always found so shocking about the Turing Test is that it reduces intelligence to telling a convincing lie, to putting on the performance of being something that you're not. From the beginning, with this disembodied conception of intelligence, the question that Turing posed, what can the mind do without a body? And therefore, what might the machine do since it doesn't have one? Chess was one of the first answers given.

[Meredith Broussard]

Why did they pick chess? Well, the early days of artificial intelligence and the early days of computing are dominated by men, mostly white men, who were educated at elite institutions.

[Ramtin Arablouei]

Skill at chess was considered a universal marker of intelligence.

[Stephanie Dick]

White men wanted to call themselves universal and produce themselves in the machine.

[Meredith Broussard]

The problem is that this small and homogeneous group of people has common biases, and people embed their own biases in technology. And so we see the blind spots of the creators then reflected in the technological artifacts that they create.

[Ramtin Arablouei]

They had all this hope and optimism about how fast they could accomplish their sci fi inspired dreams of a sentient machine, a machine that could beat a human at chess. But from the 1970s to the 1990s, it was a cycle of hype and disappointment. The technology was just not there yet. And eventually the funding dried up. Periods like this came to be known as AI Winters.

[Stephanie Dick]

I hesitate to use the term in part because outside of the United States, it was the 80s and 90s that really led to a burgeoning of AI research in other parts of the world, including both China and Russia. So it may have been a winter in America, but it was a time of great creation and creativity in other parts of the world.

[Rund Abdelfatah]

The early pioneers of the field had underestimated the complexity of humans and overestimated the capabilities of machines.

[Stephanie Dick]

I think underneath all of that arrogance and hubris is a real lack of faith in people. He rejected everything that did not contribute

[Narrator / Host (Karone DeMars)]

directly to the progress of work.

[Stephanie Dick]

In fact, he rejected the man and made the robot.

[George Zarkoudakis]

The word robot means worker.

[Stephanie Dick]

It's a translation of the Slavic word for a serf, for a slave, for a servant. It originated in, in the early 20th century, Karl Kapeck's play R U R Rossum's Universal Robots,

[George Zarkoudakis]

who imagined the future and imagine artificial humans. And they were manufactured.

[Stephanie Dick]

His sole purpose was nothing more or

[Narrator / Host (Karone DeMars)]

less than to prove that God was no longer necessary.

[Rund Abdelfatah]

In 1920, decades before the Dartmouth Conference, before the atomic bomb, before the mainframe computer, Rossum's universal robots grappled with the costs and consequences of treating workers as nothing more than their parts. It was an indictment of the exploitation and oppression that people had experienced for centuries in the name of progress. A mistake which in the play man was repeating with machines.

[Narrator / Host (Karone DeMars)]

The robots are not people. Mechanically they are more perfect than we are.

[Stephanie Dick]

They have an enormously developed intelligence, but they have no soul.

[Rund Abdelfatah]

At the end of the play, the robots have brought about the downfall of humanity. Yet unable to reproduce, their days are numbered. But then two robots awaken to each other's presence and discover emotions previously thought exclusive to humankind. Love blossoms between them and a soul stirs within.

[Ramtin Arablouei]

The soul is not often a subject for science. But long before he became a geneticist, Francis Collins started to wonder if we had to grapple with that big unknown in order to better understand who we are as human beings.

[Narrator / Host (Karone DeMars)]

I went to medical school and I found my atheism wasn't feeling like it settled very well when I was sitting at the bedside of good, honorable North Carolina people who were dying of diseases that we didn't have much to offer and wondered how I would handle that. And figured for some of these people, clearly their faith was a source of great comfort. So I began a two year journey to try to understand why do people believe in God? Ultimately, I began to realize the impoverishedness that I felt from considering human beings solely as mechanical entities. And the appeal of the notion that there was something outside of that that fits into things like love and beauty, altruism and goodness and morality. Does our DNA tell us that that beautiful sunset was something to stop for just a moment and kind of be a little bit in awe. Does the way in which listening to Beethoven's Third Symphony bring me to tears? Is that written in my DNA? What is that about?

[Rund Abdelfatah]

Coming up, we enter a new era where the souls of man and machine might converge.

[Narrator / Host (Karone DeMars)]

Hi, this is Chelsea and Katie Colin from Philly. You're listening to NPR's Throughline.

[NPR Sponsor Announcer]

This message comes from NPR sponsor Hulu. From the executive producers of the Handmaid's Tale comes the Testaments, a new Hulu original series. Golden Globe nominee Chase Infinity plays Agnes, who guides new student Daisy at Aunt Lydia's school for future wives. Their bond leads the sisterhood to start challenging authority and seek independence. This is just the beginning of their reckoning. Watch the Testaments, now streaming on Hulu and Hulu on Disney for bundle subscribers term supply.

[Commercial Announcer]

This message comes from NPR sponsor Carvana. Your time is worth more than a waiting game. Carvana gives you a transparent offer for your car in minutes and picks it up from your door. Sell your car [e-mail] pickup fees may apply.

[Rund Abdelfatah]

Can you tell me the story of your ancestor, Deep Blue?

[ChatGPT / AI Voice]

Certainly.

[Rund Abdelfatah]

Part 3 Souls of Silicon

[ChatGPT / AI Voice]

the match was held on the 35th floor of a skyscraper in downtown Manhattan with a large crowd of onlookers and a three throng of journalists and cameras. Garry Kasparov, considered one of the greatest chess players of all time.

[Garry Kasparov]

Yes, I was confident. Yeah, that's the confident arrogance. Let's remember that before 1997, I haven't lost a single match, period. I was unbeatable at the chessboard.

[ChatGPT / AI Voice]

He went up against the machine, IBM's supercomputer Deep Blue, capable of analyzing 200 million positions per second.

[Narrator / Host (Karone DeMars)]

Last year in Philadelphia, Kasparov won against a slower, weaker version of Deep Blue. This rematch, played in Manhattan, was seen as the ultimate test of man against machine.

[Garry Kasparov]

I couldn't say no. It was too tempting. You know, it's just, it's understanding better the relations between humans and computers, you know, would be very important for our progress, trying, you know, just to find out, so what are the limits of computers?

[ChatGPT / AI Voice]

The atmosphere was tense as the players sat down at the chessboard. Kasparov with a focused, determined expression and Deep Blue with its bank of blinking lights and silent fans. The game began. Kasparov made his first move with a steady hand. Deep Blue responded with a move of its on, calculated with lightning speed. It became clear that both players were evenly matched. Kasparov's experience and intuition were met with the machine's raw computational power and ability to analyze Large amounts of data.

[Narrator / Host (Karone DeMars)]

The bishop can easily fall victim to what we call an overload tactic when

[George Zarkoudakis]

one piece has to be so many pieces.

[Garry Kasparov]

I grew up in the city of Baku in the deep south of the ussr, watched my parents trying to solve chess puzzles. I cannot give you any more information because nobody was there to tweet about this moment when Garry Kasparov discovered chess and I climbed very rapidly on this chess ladder.

[Narrator / Host (Karone DeMars)]

So how is Kasparov going to draw up some sort of miracle attack from this position? He's famous for sudden tactical swoops, keep moving in intricate traps. Rook takes knight. My God.

[Garry Kasparov]

I was the junior champion under 18 of the USSR at age 12, at 17, the world champion under 20, and at 22, world champion and kept the title for 15 years.

[Narrator / Host (Karone DeMars)]

Seems everybody is interested now in home computers.

[Garry Kasparov]

From the onset of the computer science, they all thought about chess, the game of chess, as being an ultimate test for machines intelligence. Even before my famous matches with d Blue in 1996, 1997, we, when I say we, top players, we already suffered some of the defeats against these chess engines. In blitz 5 minutes chess or in rapid chess 25 minutes chess. So when I face the blue, it was already, you know, like a sign on the wall.

[George Zarkoudakis]

Gary is not. He looks, I mean he, he looks.

[Narrator / Host (Karone DeMars)]

We, we very. I. What are we missing something on the

[Ramtin Arablouei]

chessboard now that Kasparov sees.

[ChatGPT / AI Voice]

In the end, it was Deep Blue who emerged victorious and.

[Narrator / Host (Karone DeMars)]

Whoa. Deep Blue Kasparov.

[Ramtin Arablouei]

After the move C4 has resigned, with

[ChatGPT / AI Voice]

Kasparov conceding defeat after the machine's 19th move in the sixth game. The match was a historic moment, marking the first time a machine had defeated a reigning world champion in a match under tournament conditions.

[Garry Kasparov]

I was really, you know, furious and wanted to, to, to, to come back and just to tear this machine down. It was painful. I was really angry, but mostly with myself. So it, it, it was a clear sign for me that the history of us competing with machines will be over soon.

[Stephanie Dick]

There's a lovely article that comes out in the New York Times in the wake of Kasparov losing that says, well, it makes sense that the computer won at chess. Chess is a small problem, but I want to see if a computer will ever be able to beat a world champion at the game Go, for which there are more board positions than atoms in the universe. And it's a really exact and clear example of the so called receding horizon, where people really want to reserve something for ourselves that is not mechanizable. What is it that is Uniquely human. Maybe it's our ability to write a poem, or maybe it's intuition, whatever that is. Maybe it's certain forms of creativity or certain types of emotion, and then people try to automate those things. We then redefine our humanness again and again.

[Ramtin Arablouei]

Kasparov's defeat marked a turning point. A computer had beaten a human at a game humans taught it to play. For scientists, it was a sign that maybe it was time to stop competing with machines and start collaborating with them.

[Narrator / Host (Karone DeMars)]

Look, it's. He felt he had learned the language in which God created the universe. It's alive. It's alive. It's alive. It's alive. Today we are learning the language in which God created life. I know what it feels like to be God. Now. I'd like to invite Dr. Francis Collins to the lecture. So, Dr. Collins, I had plenty of occasions to imagine having to give the speech where I would say, basically, we failed. We give up.

[Rund Abdelfatah]

When geneticist Francis Collins and his team first embarked on the Human Genome project, it was a daunting task. They wanted to map out the order of the 3 billion base pairs that made up a tiny molecule, our DNA, in just over a decade. They did it.

[Narrator / Host (Karone DeMars)]

Mr. President, distinguished ambassadors, ladies and gentlemen, it is truly a humble, humbling and profound experience to be asked to speak here this morning on June 26, 2000, in the east Room of the White House. I had my chance to talk about what this meant and to give a big shout out to those 2,400 scientists who made it possible. And I think all of us, one level or another, we're also thinking about this in terms of its implications for who we are, maybe even theologically. We are doing something pretty profound here that's never been done by any species on this planet or maybe in the universe. We're reading our own instruction book, and we're. And we're watching it emerge day by day and putting all that information up on the Internet as fast as we get it.

[Stephanie Dick]

During that same time, hardware gets way cheaper. Computers proliferate.

[Meredith Broussard]

And there was a big breakthrough in a subfield of artificial intelligence called neural nets. This ushered in this new era in artificial intelligence, the era of machine learning.

[Stephanie Dick]

So what if we didn't try to model the human mind first? What if we didn't try to encode human knowledge first? What if we let the computer learn on its own?

[Meredith Broussard]

What you do when you build one of these systems is you get a ton of data and you feed it into the computer and you say, computer, I want you to Create a model of the patterns that you see in the data, and the computer very obligingly makes a model of the mathematical patterns that it sees in the data.

[Stephanie Dick]

These massive data sets were suddenly feasible to store and process in computer memory, which had sort of been prohibitively expensive before.

[Narrator / Host (Karone DeMars)]

It's the beginning of a future of medicine. It's the end of ignorance.

[Ramtin Arablouei]

Gene based medicine, drug discovery, drug development, and curing diseases.

[Narrator / Host (Karone DeMars)]

Some have said to me that sequencing the human genome will diminish humanity by taking the mystery out of life. You know, we're chemical computers.

[Ramtin Arablouei]

This is the program that runs us.

[Narrator / Host (Karone DeMars)]

Nothing could be further from the truth.

[Stephanie Dick]

There's a deep desire for the human condition not to be a deterministic output of our chemical or genetic or cultural forces, but for there to be something that allows for free will and surprise and creativity that belongs to us.

[Meredith Broussard]

Math is a system of symbolic logic. It is not the indefinable thing that makes us human. And when you are building a computer program, it'll work if you do it this way, and then it won't work if you do it the other way. But that's not how culture operates, right? That's not how relationships work. So there's a really a fundamental difference between what we can do with computers and what we can do in society. Because when it comes right down to it, computers are machines that do math. They compute. And we forget that when we get grandiose about artificial intelligence and we get grandiose about our imaginings.

[Rund Abdelfatah]

And I'm just imagining a world in which, you know, you have more intelligent machines operating on humans, are the decisions those machines are making in those moments which, you know, for humans, for example, you might make informed by instinct. Without that, you know, is something missing

[Narrator / Host (Karone DeMars)]

or without that, are you making fewer mistakes? Sometimes the gut feeling is not one you should have followed.

[George Zarkoudakis]

So Dr. Frankenstein, you know, creates life right out of dead matter. In a way, that's what we do with AI as well. We take dead matter like silicon chips and wires and metals and whatnot, and put them together and then coat them and boom.

[Narrator / Host (Karone DeMars)]

Artificial intelligence is becoming a sort of black box with law enforcement. Google uses AI and misinformation spreads wildly on Google. The Chinese Communist Party is using this technology to build the ultimate surveillance state.

[Garry Kasparov]

Look, I'm incorrigible optimist by nature, so that's why, yeah, I grew up in the Soviet Union, yes. And I saw the collapse of democracy in Russia. And I still believe that, you know, the history of humanity gives us reasons to be optimistic.

[George Zarkoudakis]

I'd like to imagine a future where we have built, we have developed human systems that bring the best out of us rather than the worst out of us.

[Garry Kasparov]

I think it's, it's, it's a time where we have to reconsider. You know, this is how, in this new environment, which is dominated by computers, we can find a robust democracy because humans still have monopoly for evil. And that's why, you know, let's stop, you know, worrying about, you know, the terminators and metrics. Let's recognize that it's, it's about us. Machine is like a mirror. And if you don't like what we see in the mirror, you have two choices. Either you can work on your body to improve the picture, or you can try to distort the mirror. The latter decision is just, it's, it's a recipe for disaster.

[Narrator / Host (Karone DeMars)]

Foreign.

[Rund Abdelfatah]

That's it for this week's show. I'm Rund Abdelfatah.

[Ramtin Arablouei]

I'm Ramtin Arablouei and you've been listening to Throughline from npr.

[Rund Abdelfatah]

This episode was produced by me and

[Ramtin Arablouei]

me and Chatgpt Lawrence Wu, Julie Kane,

[Narrator / Host (Karone DeMars)]

Anya Steinberg, Yolanda Sanguine, Yolanda, Casey Miner, Christina Kim, Devin Kadayama, Yordanos Tesfazion Fact

[Ramtin Arablouei]

checking for this episode was done by Kevin Voelkel.

[Rund Abdelfatah]

Thank you to Olivia Chilcote, Devin Kadayama, Shaheer Khan and Magdalena Devorjakva for their voiceover work.

[Ramtin Arablouei]

Thanks also to the Clinton Presidential Library, YouTube creator Brian Kay, Micah Ratner, Rachel Seller, Taylor Ashe, Olivia Chilcote, Ryan Mitchell, Tamar Charney and Anya Grundmann.

[Rund Abdelfatah]

This episode was mixed by Alex Jwenskas. Music for this episode was composed by Ramtin and his band Drop Electric, which

[Narrator / Host (Karone DeMars)]

includes Anya Mizani, Naveed, Marvi, Sho Fujiwara.

[Ramtin Arablouei]

And finally, if you have an idea or like something you heard on the show, please write [e-mail] thanks for listening.

[Narrator / Host (Karone DeMars)]

Foreign.

[Commercial Announcer]

This message comes from Mattress Firm Waking up sore Mattress Firm Sleep experts can match you with a Tempur Pedic Adapt that absorbs motion for undisturbed rest. Visit Mattress Firm and learn how to get 3% back. With special financing, they make sleep easy. This message comes from Grainger. For the ones who get it done, Grainger offers the professional grade products you need to get the job done. With fast delivery and access to technical product experts ready to help you meet any challenge, call clickgrainger.com or just stop by. This message comes from Leesa. Each beautifully crafted Leesa mattress is tailored for how you sleep and designed with specific preferences in mind. Go to Leesa.com for 20% off mattresses, plus get an extra $50 off with promo code NPR.