Throughline - A More Perfect Human

Episode Date: March 9, 2023

The dream of AI — artificial intelligence — has been around for centuries: the idea of an intelligent machine without free will popped up in ancient Taoist scrolls, Buddhist fables, and the tales of medieval European courts. But it wasn't until the 20th century that science caught up to our imaginations.Today, AI is everywhere. Breakthrough technologies like ChatGPT make news, while less glamorous but more ubiquitous programs are woven into every part of our lives, from dating apps to medical care. In many ways, AI is the invisible architecture of modern life. It's a reality that's both mundane and terrifying. And it's accelerating at a rapid rate, even as we still grapple with some of the most fundamental questions it raises about what, if anything, is uniquely human. In this episode, we explore the tension between our love of AI and our fear of it — and try to decode the humans behind the machines.Learn more about sponsor message choices: podcastchoices.com/adchoicesNPR Privacy Policy

Support for this podcast and the following message come from Autograph Collection Hotels, with over 300 independent hotels around the world, each exactly like nothing else. Autograph Collection is part of the Marriott Bonvoy portfolio of hotel brands. Find the unforgettable at AutographCollection.com. Open the pod bay doors, Hal. I'm sorry, Dave. I'm afraid I can't do that. This conversation can serve no purpose anymore.

Goodbye. It's alive! It's alive! It's alive! Most of us, when we hear the term AI, we think about Hollywood. Why do you cry? You mean people? Yeah. I don't know. We just cry.

We think about the Terminator. We think about Ex Machina. Would you program her to flirt with me? If I did, would that be cheating? Wouldn't it? We think about Star Trek. Please state the nature of the medical emergency. Or maybe Star Wars.

Hollywood is so deeply embedded in our brains. I'll be back. What does AI actually mean, you know? Really mean? AI is not a magic wand, but it's not a terminator. The system learns by accessing data. AI is not a harbinger of utopia or dystopia. And it changes its configuration in order to be able to predict stuff. AI is something invented by us to advance our progress.

It's really complicated, beautiful math, but it is fundamentally just math. 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. AI is already here. It's in your phones. Siri or Google or Alexa. Your cars. Google Maps uses a very smart algorithm to provide.

Your homes. The home security system uses artificial intelligence to keep your family safe. Your skies. From drones to unmanned aircrafts and beyond. Your hospitals. Interpreting x-rays. Your love lives. The dating apps.

Your virtual lives. Social media companies spy on us. Your governments. What it means for the future of our democracy. So we are, in fact, totally immersed in an AI world. The challenge is not to act automatically. It's to find an action that is not automatic, from painting to breathing to talking to falling in love.

Are you capable of falling in love? 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. This is ChatGPT. I'm an AI language model developed by OpenAI. I can answer questions, provide information, and engage in conversations on a variety of topics. It's the new kid on the block. How may I assist you today? This voice you're hearing is computer generated. An AI voicing an AI. AI is in many ways the invisible architecture upon which modern life is built.

And with investment in AI reaching record levels, it's easy to wonder if reality will soon outpace science fiction. Right now, we're inside a computer program. Is it really so hard to believe? You've been living in a dream world, Neo. There's something powerful about the story The Matrix and countless other sci-fi books and movies tell. The AI becomes sentient, 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. 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. 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, you know, people sort of imagined gods being just like them, only more powerful. This is George Tsarkadakis. I have a PhD in AI and I'm actively working in the field over many years. He also wrote a book all about the history of artificial intelligence from ancient times to present day called

In Our Own Image, Will AI Save Us or Destroy us? 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? 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. Coming up, we begin at the very beginning, the Big Bang of the human mind. This is Caron DeMars from San Antonio, Texas. You're listening to ThruLine Plus. You can start by clicking the subscribe button on our show page in Apple Podcasts. What is a human?

What is a human? What is a human? What 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. Part 1. I think, therefore, I am. Wonder is the feeling of the philosopher.

And philosophy begins in wonder. I lived in Athens when I was like five, six years old. And it was summertime. And in Greece, they still do it. They have like open-air cinemas, right? Where in the summer you go into an open-air cinema, there's no roof, 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 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 this sort of crazy scientist who had a robot. And that was the first time I actually saw a robot in my life. Welcome to Altehor, gentlemen. I am to transport you to the residence. I never imagined there would be a thing... If you do not speak English, I am at your disposal with 187 other languages along with... Made of metal, tin, that had a mind. You are a robot, aren't you?

That is correct, sir. For your convenience, I am monitored to respond to the name Robbie. 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. 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.

I mean, that was the culmination, the realization of centuries of dreaming about going to space. 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. 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 spaces, the human body. So those stories are very powerful and I try to 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 on the universe whatever 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 300,000, 400,000 years. And yet, for most of that time, we're 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 14,000, 16,000 years ago, boom. 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 experienced the world. When love beckons to you, follow him, though his ways are hard and steep. Through these stories, we project our hopes, fears, and dreams onto the canvas of the invisible unknown.

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. The divine gift does not come from a higher power, but from our own minds. 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 language.

Language and stories. We know they're part of what makes us human. But what else? 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. 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. 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. Also, there's an error in there. There is an error. Were there any other mistakes? It 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. We asked ChatGPT to comment on its error. I apologize for any errors in the biography of Francis Collins. As a language model, I am trained on a large data set of text. I may make mistakes or omissions. I recommend fact-checking any information that I provide. Don't worry, we will. So much of the driving force behind Collins' work is trying to understand 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. There were covers of Life magazine saying, discovering the secret of life. Was it actually discovering the secret of life? 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. 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. The big question was, OK, 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 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. Pulse taking. Controlling.

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. 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, by ruler, right? And then that word computer, which described a human being, was transposed into the machine because the machine can do it better. 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. She holds a PhD in the history of science with a specialization in the School of Communication at Simon Fraser University. She holds a PhD in the history of science, with a specialization in the history of mathematics and computing. 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 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. Coming up, as we unlock the secrets of man and machine, we ask the question, will this knowledge bring us closer to perfection or destruction. Hi, this is Christopher from Los Angeles, California. I love ThruLine because it is always informative and keeps me alive.

Support for this podcast and the following message come from the NPR Wine Club, which has generated over $1.75 million to support NPR programming. Whether buying a few bottles or joining the club, you can learn more at nprwineclub.org slash podcast. Must be 21 or older to purchase. What is a machine? 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. 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.

It was instigated by John McCarthy, who was a mathematics professor at Dartmouth. The proposal that John McCarthy wrote pulls no punches at all. Quote, 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 feature of intelligence can, in principle, be so precisely described that a machine can be made to simulate it. So right from the beginning, there's this pronouncement that human learning and intelligence can be mechanized and automated. 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 a new book called More Than a Glitch, 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. 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 industrialization or to capitalism or to these colonial legacies of reserving reason for only certain kinds of people and certain kinds of thinking. That deeper story takes us back to the early days 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. 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. People have been playing around with what is called automata,

essentially machines that would automatically do something simple for centuries. This is George Tsarkadakis again. 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 2,000 years. Our blows will destroy their whole modern industrial plant and organization.

Something happened to our collective psyche after the atom bomb. At zero 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. 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. I still remember the day very well because this was a river filled with dead bodies. 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, gradually, as public, more skeptical to technologies. 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. What if human decision-making

procedures were too slow? What if people's judgments are clouded by their emotions? To give us more control over ourselves and the world around us. Our machines will churn out the right answers and the right decisions and the right judgments. And in effect, replace God with science. 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 science 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.

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. 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 were about to be.

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. The fear that people were too limited to be trusted to preserve peace. So let's double down on high technological hyper-rationalism. And that's how artificial intelligence came about. Your scientists were so preoccupied with whether or not they could,

they didn't stop to think if they should. 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. 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. 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. Would you like to play? Play? It's a game,

a test of sorts, for determining whether something is a machine or a human being. It was based on a parlor game for swapping gender that says a man and a woman leave the room and the party goers 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. 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. Skill at chess was considered a universal marker of intelligence. White men wanted to call themselves universal and produce themselves in the machine. 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. 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. 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. The early pioneers of the field had underestimated the complexity of humans and overestimated the capabilities of machines.

I think underneath all of that arrogance and hubris is a real lack of faith in people. He rejected everything that did not contribute directly to the progress of work. In fact, he rejected the man and made the robot. The word robot means worker. It's a translation of the Slavic word for a serf, for a slave, for a servant. It originated in the early 20th century. Karl Capek's play R.U.R., Rossum's Universal Robots, who imagined the future and imagined artificial humans,

and they were manufactured. His sole purpose was nothing more or less than to prove that God was no longer necessary. 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.

The robots are not people. Mechanically, they are more perfect than we are. They have an enormously developed intelligence, but they have no soul. 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.

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. 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 I 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 impoverishness 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? Coming up, we enter a new era where the souls of man and machine

might converge. Hi, this is Chelsea and Katie calling from Philly. You're listening to NPR's ThruLine. Can you tell me the story of your ancestor, Deep Blue? Certainly. Part 3. Souls of Silicon. The match was held on the 35th floor of a skyscraper in downtown Manhattan

with a large crowd of onlookers and a throng of journalists and cameras. Garry Kasparov, considered one of the greatest chess players of all time. Yes, I was confident. Yeah, that's confident arrogance. Gary Kasparov. Considered one of the greatest chess players of all time. 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.

He went up against the machine, IBM's supercomputer, Deep Blue, capable of analyzing 200 million positions per second. 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. I couldn't say no. It was too tempting. You know, it's just understanding better relations between humans and computers, you know, would be very important for our progress. Trying just to find out what are the limits of computers. 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 own, 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. The bishop can easily fall victim to what we call an overload tactic. When one piece has to be so many pieces...

I grew up in the city of Baku in the deep south of the USSR. I 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. So how is Kasparov going to draw up some sort of miracle attack from this position? He's famous for sudden tactical swoops, intricate traps.

Rook takes knight, my god. I was the junior champion under 18 of the USSR at age 12. At 17, the world champion at 20, and at 22, world champion. And I kept the title for 15 years. It seems everybody is interested now in home computers. 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 Deep. Blue in 1996-97, we, when I say we, top players, we already suffered some of the defeats against these chess engines in Blitz, five minutes chess, or in Rapid Chess, 25 minutes chess. So when I faced D. Blue, it was already like a sign on the wall. In the end, it was Deep Blue Kasparov, after the move C4, has resigned. With 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. I was really, you know, furious and I wanted to come back and just to tear this machine down.

It was painful. I was really angry, but mostly with myself. So it was a clear sign for me that the history of us competing with machines will be over soon. 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. 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. Look, it's moving. It's moving. He felt that he had learned the language in which God created the universe.

It's alive. It's alive. It's alive. It's alive. It's alive. It's alive. Today we are learning the language in which God created life. In the name of God. Now 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. 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. Mr. President, distinguished ambassadors, ladies and gentlemen, it is truly a 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 part of that and we're watching it emerge day by day and putting all that information up on the internet as fast as we get it. During that same time, hardware gets way cheaper, computers proliferate. 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. 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? 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. And the computer very obligingly makes a model of the mathematical patterns that it sees in the data. These massive data sets were suddenly feasible to store and process in computer memory, which had sort of been prohibitively expensive before.

It's the beginning of a future of medicine. It's the end of ignorance. Gene-based medicine. Drug discovery, drug development, and curing diseases. 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. This is the program that runs us. Nothing could be further from the truth.

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. 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. Then 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. Or without that, are you making fewer mistakes? Sometimes the gut feeling is not one you should have followed. 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, you know, silicon chips and wires and metals and whatnot,

you know, and put them together and,, you know, call them and boom. 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. 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. 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. I think 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 worrying about the Terminators and Matrix. Let's recognize that 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 a recipe for disaster. That's it for this week's show. I'm Randhav Dilfattah. I'm Ramteen Arablui. And you've been listening to ThruLine from NPR. This episode was produced by me. And me.

And. Chat GPT. Lawrence Wu. Julie Kane. Anya Steinberg. Yolanda Sanguini. Casey Miner. Christina Kim. Devin Katayama. Yordanos Tisfazion. Fact-checking for this episode was done by Kevin Vocal.

Thank you to Olivia Chilcote, Devin Kat Tamar Charney, and Anya Grunman. This episode was mixed by Alex J. Wenskis. Music for this episode was composed by Ramtin and his band, Drop Electric, which includes Anya Mizani. Naveed Marvi. Sho Fujiwara. And finally, if you have an idea or like something you heard on the show, please write us at ThruLine at NPR.org or hit us up on Twitter at ThruLine NPR. Thanks for listening.

This message comes from Grammarly. Back-and-forth communication at work is costly. That's why over 70,000 teams and 30 million people use Grammarly's AI to make their points clear the first time. Better writing, better results. Learn more at grammarly.com slash enterprise.