Loading summary
A
If you love to travel, Capital One has a rewards credit card that's perfect for you. With the Capital One Venture X card, you earn unlimited double miles on everything you buy. Plus, you get premium benefits at a collection of luxury hotels when you book on Capital One Travel. And with Venture X, you get access to over 1,000 airport lounges worldwide. Open up a world of travel possibilities with a Capital One Venture X card. What's in your wallet?
B
20 terms apply. Lounge access is subject to change. See capitalone.com for details. Race the rudders. Race the sails. Race the sails. Captain, an unidentified ship is approaching. Over. Roger, wait.
C
Is that an enterprise sales solution?
B
Reach sales professionals, not professional sailors. With LinkedIn ads, you can target the.
C
Right people by industry, job title and more.
B
We'll even give you a $100 credit on your next campaign. Get started today@LinkedIn.com and conditions apply.
D
This episode is brought to you by Ambetter Health Group health insurance can put businesses in a tough position if you're a business owner, a CFO, or an HR leader, this is probably going to sound familiar. It's fall and you find out your group health insurance premium will be more expensive next year, maybe by a lot. And as usual, you have to pick one carrier and a few plans for all of the employees. But they each have different medical needs, different budgets and different preferences for doctors. Plus, the carrier's network might not be strong where all employees live. Fortunately, there's a new approach. It's called an ichra or ichra and it's a game changer. Ichras make costs predictable with stable pre tax contributions and a larger risk pool. And they make health plans personal because employees can buy any plan that fits their needs from any carrier. You choose how much to contribute. They choose what works for them. It's about time, right? For coverage you control, plan on and ichra. Learn more@ambetterhealth.com Ichra. You're listening to TED Talks Daily where we bring you new ideas to spark your curiosity every day. I'm your host, Elise Hu. When you think about AI literally generating new DNA, does that thrill you or scare you? For bioengineer and genomic AI pioneer Eric Nguyen, it's a little bit of both. But for him, the possibilities of unlocking new medicines and curing diseases, among other things, makes it worth the risk. In his talk, he shares how looking at DNA as a language, one that AI can learn to read, write and ultimately build, will let us fundamentally change biology and life itself.
B
I've always found it curious how Biologists study life. There's this. A biologist will learn how a car works by poking at it, removing one part at a time and seeing how it affects the rest of the car. On the other hand, an engineer will learn how a car works by taking it completely apart and rebuilding it. Take, for example, the Human Genome Project, one of the biggest breakthroughs of the last century. We spent over a decade mapping out all 3 billion letters of our genome, the complete set of DNA. We thought that once we could read DNA and apply that same principle, poking and dissecting one letter at a time, that we can start eradicating all human diseases. But instead, we began to realize just how little we actually understood about the true function of DNA. As a researcher, I work on artificial intelligence and trained as an engineer. I learned by building things and understand by creating. Today, I want to share an idea that can fundamentally change how we study biology and life itself. Instead of just reading and dissecting DNA, we should be generating it. And we can do this by treating DNA as a language, one that AI can learn to read, write, and ultimately build. This idea led myself and a team of researchers at Stanford and the AHRQ Institute with a sort of moonshot. Can we generate an entire genome from scratch using AI? Build life from the ground up? Now, I understand the thought of feeding the code of life into a generative AI is both thrilling and perhaps unsettling. But I came to realize that if this was possible, it could unlock some of the most powerful breakthroughs in science and medicine. But I'll be honest, we had no idea if AI could actually generate DNA. In many ways, DNA is like a language. It has grammar, structure, sort of like sentences and paragraphs that group together to form a story. And these stories are passed down through evolution, generation by generation. For humans, it's been hard to comprehend these stories written in DNA, in large part because of its scale. DNA is extremely long and yet at the same time sensitive to the smallest mistakes. Imagine trying to write something the length of 30,000 books in a foreign language, and that when you're off by a single letter, one of billions, this can mean the difference between a healthy person and a person with a life threatening disease. And so, to tackle these challenges, together with my colleague Michael Polly, we developed an AI that could generate extremely long sequences of DNA, 500 times longer than previous AI models at high levels of detail. We assembled a team of scientists and AI experts and gathered the largest collection of DNA used to train AI. 80,000 whole genomes fed into a model that we called Evo. And our goal was to create something like a ChatGPT for DNA, where you can prompt EVO and describe the DNA you want and it would generate new sequences one letter at a time. But there is one key difference. With chatbots, you can just read what it writes and you can decide if it makes sense to you. With DNA, it's not so simple. It's not an intuitive human language. How do you know if it's any real or good? What does that even mean? What we needed was a test, a way to verify that what it wrote would actually function. And so we started with a familiar tool in biology called crispr. CRISPR is like a pair of molecular scissors that can edit DNA used for things like gene therapy. We asked EVO to make its own and generate its own version of CRISPR from scratch, which had never been done before. It's got proteins and RNA inside. It's a complex system. And so our biologists would take that generated DNA and analyze it to see how realistic does it look, does it resemble something in nature, how do its proteins fold, which all give us a sense of its function. But ultimately we have to test their ability to cut DNA by actually building them in the lab. And so that's what we did. Now, waiting for lab results can sometimes be a nerve wracking experience. Honestly, it's kind of like waiting for the results of a pregnancy test. You're excited, anxious and hopeful for a positive outcome. And then all of a sudden these two little lines appear just to be crystal, crystal clear. These two lines are a good thing. That's what we want. It means that our CRISPRs cut a single strand of DNA into two in the exact right spot, just like natural CRISPRs in the lab. And so that's when we knew it worked. EVO generated DNA that not only looked realistic, but that actually functioned. And so next we decided to go for that moonshot to try and generate a whole genome from scratch. And EVO was able to generate hundreds of synthetic proteins in a genome that resembled those in nature. But ultimately it was missing a few parts. It wasn't yet complete, more like a rough sketch of the genome. However, this is just the first version. That rough sketch of the genome will become more detailed over time. In fact, within years, we anticipate AI will be able to generate whole functional genomes. In other words, AI will be able to generate new life. As this technology improves, biology will shift from discovery to design. What might this world look like? Let's look ahead. In this future, we can make truly personalized medicine. Imagine prompting an AI like Evo with your genome, finding sources of diseases, predicting your reaction to drugs, and guiding treatment options based on your own DNA. But why even take medicine when you might have a permanent cure? We might choose to alter our DNA outright. And we are beginning to see this today. Recently, the FDA approved the first gene therapy for sickle cell disease, a painful, lifelong condition of the blood. And it works by just changing a single gene in a person's DNA to permanently cure the patient. And now There are over 500 DNA altering treatments awaiting approval. But let's say you're not comfortable with changing your DNA. What if we added new DNA? All of our DNA is organized into 23 pairs of chromosomes. Chapters, if you will, in the book that is our Genome. What if evil learned to generate a 24th chapter, a whole new chromosome equipped with all the machinery needed to fight hundreds of diseases on demand with DNA generation, what is the limit of what's possible? We've all seen Jurassic Park. We all thought it was science fiction. And it is. Mostly. Researchers are now reconstructing the genomes of extinct species, with one company planning to resurrect the woolly mammoth by as early as 2028. Now, instead of bringing back extinct species, can we create new ones? Researchers are now engineering microbes for colonizing Mars. If we one day wish to be a multiplanetary species, we'd have to figure out how to grow things on Mars, make it more hospitable and possibly terraform. And it is possible we have microbes on Earth that can handle a range of extreme conditions that we call extremophiles. Now, I understand some of these things might sound scary. One of the biggest concerns is biosecurity, the potential to create bioweapons. Can AI be used to generate more infectious viruses? Yes. But AI can also defend and monitor against these threats as well. And so perhaps you feel like me and that you have to choose between advocating for innovation versus safety. I'd encourage you to embrace both, because stopping progress entirely, I don't think is practical. We need to evolve with the technology, monitor its capabilities, and constantly be asking ourselves, what possible futures are we enabling? As humans, we've always sought to understand the world around us that is in our nature. But understanding alone has rarely been enough. For centuries, we've studied life by observing and dissecting it. But now we're no longer just reading life's code. We now have the power to generate it. And with AI, we're at the beginning of unlocking new medicines. Science and even entire new forms of life. Do we make small edits? Do we write entirely new chapters? Or do we one day design life itself? Because to truly understand biology, we must create it. In the future of life is ours to build. Thank you.
D
That was Eric Nguyen at TED 2025. If you're curious about TED's curation, find out more@ted.com curationguidelines and that's it for today. TED Talks Daily is part of the TED Audio Collective. This talk was fact checked by the TED Research team and produced and edited by our team, Martha Estefanos, Oliver Friedman, Brian Greene, Lucy Little and Tansika Songmanivong. This episode was mixed by Christopher Faizy Bogan. Additional support from Emma Tobner and Daniela Balaurazo. I'm Elise Hu. I'll be back tomorrow with a fresh idea for your feed. Thanks for listening.
E
Listen up. You can get the new iPhone 16e with Apple Intelligence for just $49.99 when you switch to Boost Mobile. We pulled so many all nighters to give you this deal. And hey, stop messing with the mic.
B
I'm just helping us catch people's attention. This is a great deal.
E
Exactly, so it doesn't need all that fin. Get the new iPhone 16e available at Apple Store locations and the Apple Store online.
B
Visit your nearest Boost Mobile store for full offer details. Apple Intelligence requires iOS 18.1 or later. Restrictions apply.
C
Banking with Capital One helps you keep more money in your wallet with no fees or minimums on checking accounts and no overdraft fees. Just ask the Capital One bank guy. It's pretty much all he talks about in a good way. He'd also tell you that this podcast is his favorite podcast too. Ah really? Thanks Capital One Bank Guy. What's in your wallet? Term supply See capital1.com Bank Capital One NA Member FDIC.
F
This is Paige, the co host of Giggly Squad. I use Uber Eats for everything and I feel like people forget that you can truly order anything, especially living in New York City. It's why I love it. You can get Chinese food at any time of night, but it's not just for food. I order from CVS all the time. I'm always ordering from the grocery store. If a friend stops over, I have to order champagne. I also have this thing that whenever I travel, if I'm ever in a hotel room, I never feel like I'm missing something because I'll just Uber eats it. The amount of times I've had to uber eats hair items like hairspray, deodorant you name it, I've ordered it On Uber Eats. You can get grocery alcohol everyday essentials in addition to restaurants and food you love. So in other words, get almost every anything with Uber Eats. Order now for alcohol you must be legal drinking age. Please enjoy responsibly. Product availability varies by region. See app for details.
Date: August 25, 2025
Speaker: Eric Nguyen (Bioengineer & Genomic AI Pioneer)
Host Introduction by: Elise Hu
In this thought-provoking TED Talk, bioengineer Eric Nguyen explores the radical intersection of artificial intelligence and biology. He shares how advances in AI are equipping scientists to read, write, and even generate entirely new DNA sequences—from synthetic genes to potential new life-forms. Nguyen walks the audience through his journey leading the creation of an AI model that can generate DNA, discusses both the thrilling opportunities and sobering risks, and forecasts a future in which biology shifts from discovery to intentional design.
On DNA as Language:
"DNA is extremely long and yet at the same time sensitive to the smallest mistakes. Imagine trying to write something the length of 30,000 books in a foreign language, and that when you're off by a single letter, one of billions, this can mean the difference between a healthy person and a person with a life threatening disease."
— Eric Nguyen, 06:19
On Engineering AI for Genome Generation:
"Our goal was to create something like a ChatGPT for DNA, where you can prompt EVO and describe the DNA you want and it would generate new sequences one letter at a time..."
— Eric Nguyen, 05:56
On the Eureka Moment in Lab:
"Waiting for lab results can sometimes be a nerve-wracking experience. Honestly, it's kind of like waiting for the results of a pregnancy test... these two little lines are a good thing... It means that our CRISPRs cut a single strand of DNA into two in the exact right spot, just like natural CRISPRs in the lab."
— Eric Nguyen, 09:12
On the Shift in Biology:
"As this technology improves, biology will shift from discovery to design. What might this world look like?"
— Eric Nguyen, 11:18
On the Responsibility of Creation:
"We need to evolve with the technology, monitor its capabilities, and constantly be asking ourselves, what possible futures are we enabling?"
— Eric Nguyen, 13:57
On the Future of Life:
"Because to truly understand biology, we must create it. The future of life is ours to build."
— Eric Nguyen, 14:18
Nguyen’s talk is bold, optimistic, and candid, blending hope for scientific advancement with a clear-eyed call for caution. He employs vivid metaphors and accessible language, inviting a broad audience to imagine both the promise and the burden of engineering life.
For listeners who missed the episode:
Eric Nguyen’s talk opens a window into the extraordinary potential of AI-powered genomics—from immediate medical breakthroughs to a philosophical shift in how humanity may build the future of life itself, all while urging vigilance, responsibility, and inclusivity as we step into this new era.