#113 Why AI Could Add Decades to Your Lifespan | Dr. Derya Unutmaz

Introduction

Rhonda Patrick: I'm so excited to be sitting here with Dr. Derya Unutmaz, who is one of the handful of scientists that has had access to collaborate with OpenAI, one of the world's leaders in artificial intelligence. He's also an aging researcher. He's an immunologist. Really just a match made in heaven to sit down and talk about the role of AI in aging research and in medicine. So I'm super excited to have you here today.

Derya Unutmaz: I'm very excited to be here. Thank you.

Why the next 10 years may add 50 to your lifespan

Rhonda Patrick: As we both know, aging is a very, very complex process. Many factors involved. It's heterogeneous. It's so complex, and it just seems like. So almost impossible to solve. And yet I've heard you say something that's very interesting. I've heard you say, if you could try not to die within the next 10 to 15 years, you might want to try to do that because you could live an extra 50 years. Can you explain and unpack why you think that? What makes you believe that?

Derya Unutmaz: Thank you. So, first of all, I'm very excited to be here. I'm a big follower of your podcast. I think it's maybe the best aging or longevity podcast. So this is. This is a great pleasure. Yeah, so I. I've said that quite a few times in the last year or two, actually, and it may not even take 10, 15 years. Might be even closer. The reason is that the technology, especially because of AI, is expanding exponentially. So our minds think in a linear term. So we think that the next 10 years is going to be as much advanced as the last 10 years or the last 15 years. But that's not what's going to happen in the next 10 years. You can think of it as more advanced in the last century. So imagine that you are living in early 1900s and somebody told you that we're going to have vaccines and you will never get smallpox or you won't die of tuberculosis. People would laugh at you. That's not possible. So that's the speed that we're talking about. But there's something even more important. Because of this acceleration, the advances of treating diseases is also going to accelerate dramatically. So we will get to a point. What's called the longevity escape velocity. This was coined by Aubrey de Grey, who, as you know, is a great aging researcher. So the point is that we will come to a point in the next, I would say probably eight to 10 years, where every year you live is going to add more than a year to your life. So let's just say, you know, 10 years ago, 10 years later, you get a cancer that's normally is not curable, and you only have one or two years to live, but that during that one year there is going to be a new treatment that will cure that cancer. So automatically is going to add several years or maybe 10, 15 years to your life. Or we're already starting to see that with the GLP-1 drugs, receptor agonists, which are adding about five to 10 years to lifespan of people who are obese or who have chronic conditions, will have sort of the muscle generators, which I think will have tremendous impact on the aging population, because, as you know, that's a huge problem. So all of these things will add up. And this technology in AI is going to keep accelerating. So 10 years later, what will happen in a year will be like what happens in 20 years of advance. And then we'll get to a point, probably 15, maximum 20 years, where we will be able to completely reverse the aging process. So if you're 80 years old, 90 years old, you will get back to age 30, 40, whatever. So that's going to add up 50 years or 100 years to your lifespan, and then you can keep doing that and extend it almost indefinitely. So I think this is probably the most critical time in human history. So try not to die for the next 10 years.

Rhonda Patrick: And we're going to talk about all these things. I want to talk about curing disease, I want to talk about reversing aging, age reversal. All of that is on my agenda to talk about with you today.

How AI is transforming drug discovery

Rhonda Patrick: But you mentioned something, you mentioned that right now the artificial intelligence as a general term is accelerating at an exponential rate. I've heard you talk about this Moore's law and how the software itself is accelerating at this exponential rate. Maybe you could explain a little bit about what does that mean? And then how do you think that'll translate into biology? Because humans, we're not software. And there are things that, at least in my opinion, you have to still test safety if you're accelerating the computational speed. And therefore you can test a lot of things that are what's called in silico for people listening. We're talking about testing things like just modeling them. And maybe you can explain this a little bit better. But then at a certain point, you still have to test about safety. And you definitely. There are things that I think need to still be done in human trials. So I'd love to hear how you think that's going to happen.

Derya Unutmaz: I think that's the most critical question because people always bring that up. Okay, if you generate drugs within hours, you still have to test them on humans for five years, maybe sometimes longer. How are you going to deal with that? But let me first start with how AI is accelerating biology now. So we can think of it in terms of phases, because now and five years later it's going to be very, very different. So right now, especially in the last year or two since LLMs came out, their intelligence had been accelerating. Initially it was fairly smaller productivity gains. For example, when GPT-4 was out, I would ask it to sort of scan the literature and tell me what's the latest on this topic or that topic. And that saved me hours, sometimes days. But then as the models advanced, especially the after o1 model, the reasoning models started to come out. And now we have the GPT-5 Pro model, 5.5 Pro model. What happened was that now they were able to think and plan so you could start to ask very sophisticated questions. For example, here is a huge biological data set. A million data points or 10 million data points, go over this, not only just analyze it and group them, but what is the insight from that data? Human mind is not able to do that. And in fact we had such data sets which took us months to analyze. Like a PhD student work on it using deep learning, we still couldn't really truly understand what that data meant. We know these genes are up, these metabolites are changing, this is happening. How do you bring all that together? And so now AI models are able to do that. So I've tested for example, latest GPT-5 Pro model. You can upload millions of data sets that we accumulate over years maybe, and then in matter of minutes you get not only the complete analysis. Recently I had a 40 page report from GPT-5 Pro which was an analysis of this, what's called the RNA sequencing, lots of millions of data points. But it also provided incredible insight like what does this data mean? What should be the next questions to ask? So that automatically contracts months, sometimes years of analytic work into matter of minutes or hours. So that is all already accelerating first in the drug design parts. I think every pharmaceutical company is going to eventually use AI generated AI generation for developing new drugs. Things that took years of screening of small molecules now take, you know, hours or days. So tremendous acceleration there. And then I think again more recently because the models have advanced so much that you can also ask things like, okay, so this is great, this is the hypothesis. In fact, AI can Even generate hypothesis for you. But what sort of experiment I should do to address that. People have to realize that what we do in biology is experiments, but we don't really know what's the best experiment to do. I mean, that's kind of my job, but I have some intuition. But we should do this to address that question. But is that the ideal experiment? Does that have all the controls, everything? So AI models are now able to tell you, sort of simulating if out of this hundred potential experiments you can do, these two are the best ones, because this is going to give you the best output. And I've been testing that. So that is another acceleration. Now you don't have to try 100 things for a year. You can just try two things for few weeks and get the output. So that's what's possible now, already tremendously accelerating the R and D part.

Could digital twins shorten clinical trials?

Derya Unutmaz: But then the second part, which I think is more important part, is how do we apply that to clinical trials and regulations. So it still takes years to try everything on humans. And I think the solution to that will be what I call the digital twin. And this term is around for several years. So the idea is that if we have lots of lots of biological data, and when I say lots, it's a lot petabytes of data. If AI comes to a point where we're going to need much more compute than we have today to compute all that and really kind of simulate a whole biological organism, a whole human being, but not just your phenotype, but also your metabolism, your immune system, your gut microbiome, your genetics, and all kinds of data sets are put together. And so it knows your biology in a temporal way, in a totally functional way, then you can ask the question, okay, so if I give this drug to this person, what kind of effect it will have if they have this disruption, Is it going to have a side effect or is it going to be effective? So literally we can cut down clinical trial time from years to a matter of months or even weeks. So you can actually do the trials in a very small subset of patients, because you can choose the patients. You can say, okay, AI told me that these, these, these people, this drug is going to be effective, 100% to them. And so you just test it on those people. And in fact that will go into the personalization. There's going to be thousands of drugs for different people. So that will cause tremendous acceleration. We're not there yet, but I'm betting on that, that within the five to 10 years we will get there. So the iteration process on humans is going to be all digital as well. And then maybe the manufacturing will be a little bit. Still will take time, but we can even improve that part too. At some point we will come to a point where treatment on demand. So you go to an AI model, analyzes your genome, your biology, orders this small molecule or the drug or treatment just for you to the manufacturing facility and next week you get your drug and you get treated. That's the world I'm imagining.

Can AI predict drug safety and efficacy?

Rhonda Patrick: I want to get back to this concept of digital twin again when we talk about personalized medicine. But if I understand correctly, if we have this digital twin which is all the genetic data, metabolomic, proteomic, biomarker, just everything, all this data and more that we're not talking about, and now we have AI which can then do all these scenarios and figure out how this drug is going to affect or how this treatment is going to affect this person. You're saying that the clinical trial that may have taken a few years can be condensed down and perhaps we can look at, after doing the in silico experiments, you can look at some biomarkers and know is this going to affect their fertility? Like you don't want to give someone a treatment that's going to make them infertile or you know, so you think that's going to be. AI is going to be able to identify how to know if it's going to affect like fertility or cognition or life expectancy or you know, just, just from the whole composition of the person and doing, I don't know, all these tests.

Derya Unutmaz: Yeah. So I mean the path there requires several steps of validation and that I think we will get to a point where when we have superintelligence that we'll be able to trust superintelligence, you know, almost 100% that we don't need to validate it even with biomarkers or whatnot. But to get to that point, it's sort of like the self driving cars, right. So to get to a self driving level, I mean it has to be 99.999 safety, you have to sort of validate it. You know what happens if somebody's crossing the street, Right. So that scenario has to happen and then you record it and sometimes sometimes it won't do the right thing. Maybe, you know, it won't stop. That's why we still have to like look at this, you know, be ready to, to take control. But if it does stop and it stops and, and saves lives again and again and again, right now, you know, self driving cars are probably about 10 times safer. They will be maybe 100 times safer. So you get to a point that you trust the AI rather than the, the driver, right? So you say, okay, so I trust, I want the AI to decide for me to drive. So I think we'll get to that point. For biology, it will take a little bit longer because of the extreme complexity and then we'll have to have very clever benchmarking and validation ways there. The biomarker is going to be really important because again, if you're developing an aging drug that you claim will let people to live to 150, well, you can't wait. Even if somebody 100 years old takes it, you still have to wait 150 years, 50 more years to validate that. So that's not going to work out. So we have to be able to predict that. But actually probably aging is the easiest in some ways to predict because we have so many biomarkers or functional outputs we can measure. We know how they are in an old person and in a young person. So if your VO2 max suddenly gets like a 20 year old, wow, that's amazing. If your muscles are as good as a 30 year old, if your skin looks like a 20 year old, that's what my mom is waiting for. You know, that's, that's proof. And you'll, you'll immediately see that, I mean immediately weeks or whatnot. So I think again, it will take time. That's the part that's going to take time. The sort of trusting AI to tell you, yes, if you take this drug, you will, you will be treated or you will reverse aging. We still have about a decade. That's why I'm saying like, you know, otherwise it would, it would take, it would happen.

Rhonda Patrick: Even earlier

Have we already reached AGI?

Rhonda Patrick: You mentioned superintelligence, artificial superintelligence, ASI. Maybe you could talk a little bit about just for people to have understanding right now, the difference between artificial intelligence, artificial generalized intelligence, AGI, then the super intelligence. Because you said once we get to the super intelligence, we're going to trust it, right? So I mean, I don't know, do we know what those differences are? Can you explain a little bit?

Derya Unutmaz: Yeah, of course. You know, this changes on a daily basis, what the definitions are depending on who's whose definition. But you know, I've been thinking about AGI, ASI for decades. I mean, it's not something that I started to think about it recently. So the way I originally defined AGI, it's artificial general intelligence. So what that means is that first of all it's artificial, right? So it's not human intelligence, it's artificial intelligence and then it's general. What that means is that if AI learns one set of rules or one set of knowledge, that it can generalize that to something else. And that's how our brains are intelligent. Because you can be an amazing chess player. In fact, AI beat the chess champion, Kasparov of 1997, I think like decades ago. But that was not general intelligence, it was super good. Or AlphaGo beat the world champion in go, which is much more difficult game to be. General AlphaGo learning how to play Go or chess should be able to, I don't know, solve a problem in aging, right? So it should be able to transfer that information. I think the amazing thing about LLMs, what we call large language models, is that they acquire this ability, which honestly, I didn't think this would happen so easily. I was expecting AGI to happen maybe a decade ago. So in my opinion, we have already achieved what I call level one AGI artificial intelligence. Because if I ask GPT-5 Pro model, you know, something that it hasn't trained on, like an experiment that I have done, or if I say, okay, think of the experiment as a video game design another experiment for me, like, like you are playing a video game. So that's transferring completely different area to a biological system and is able to do that in an amazing way. But we still need to go through several levels. I think the next level is going to be memory. So they don't have persistent memory right now. They have some memory. They know about you, they know about what they've learned in the Internet. But they need to be able to manage the context because there's a continuum, life is a continuum. And then the other one is going to be the self learning. So maybe that's level three, it doesn't matter. And that's coming soon. AI companies are saying we think that real time learning is coming maybe by next year. And then the third level, what I call the physical intelligence. So people again confuse this greatly because the true human level intelligence is physical intelligence. It's not cognitive intelligence. So for millions of years we evolved to survive in a physical world. We didn't have language up to, I don't know, 10,000 years ago. We didn't know how to write. This cognitive part has developed in the last maybe 10, 20,000 years before that. In fact, animals have very good physical intelligence. We're imprinted and born with that intelligence. An Admiral or child already have a world model. They know that if I drop this, it's going to fall and doesn't have to test it a million times. And that's of course what we need for robots for embodiment. And you can see that that's taking a long time. It's more difficult to train a robot to behave like a child than have GPT-5 solve the most difficult math problem and we'll get there. I think people are working on these world models and physical intelligence whether we need another algorithm or not. So that will be the final level of the AGI level. Once we have all those levels and once the AI is able to self learn, then that's the superintelligence. Because at that point it can train itself maybe thousands, maybe millions fold faster than we are able to do. And there's a limit to human intelligence. So even the smartest person in the world can only do so much. And superintelligence, what I would define is that you will have the intelligence of combined totality of humanity at some point. Like if I bring a million top scientists in the world, of course they can solve like a Manhattan Project. They brought all these brilliant minds. It wasn't one person's. They were able to solve very hard problems. Superintelligence will get to that level. We'll be able to do what what thousands of scientists can do in a year will be able to do in a day. So I would probably trust that.

Rhonda Patrick: Wow,

Is AI an existential threat—or the ultimate enabler?

Rhonda Patrick: That's pretty exciting. I mean, and it also kind of brings in this, this, this concept of when you talk to people about AI and not everyone has the understanding of it as you for sure you hear that there's, there's a pessimistic versus optimistic view. Right. And oftentimes if I talk to people, I hear a lot of pessimism. I hear perhaps they don't understand their fear of the unknown, of what AI is capable of. I mean, you're just the super intelligence that you're talking about. I feel if you explain that to some people, it would scare them even more. You know, perhaps they are worried about the cultural ramifications, economic ramifications, but also just this Terminator situation where okay, well, they're super smart, they're going to want to then take over the world world and they don't need us anymore. Right, but you have such an optimistic view. I mean, we're talking about solving aging, living to be 150 or more. Why do you have such an optimistic view? Are you worried at all about the Other pessimistic sort of viewpoints?

Derya Unutmaz: Absolutely not. And I'll tell you why I'm so super optimistic about it. When people make those statements like AI is an existential threat for us, it's going to destroy humanity, I make the counterpoint. There's only one existential threat to humanity and that's humanity. So if you look at history, human beings killed more humans than everything put together, caused more suffering than anything that humans have been exposed to, even animals. I don't think they maybe infectious diseases at some point might have caused a lot of suffering. But, but, but the real danger is, is the human intelligence. So I do. Let's do a thought experiment. Let's imagine that we live in a parallel universe. And in that universe the world have decided that anyone above the IQ of let's say 100 is a danger to the society. Because if you get very intelligent, you can come up with ideas that could be very dangerous, right? And that's true, actually. That's how it happened. And then if you have an IQ of 105, you get imprisoned immediately. So you are not allowed to participate in society or you get killed or whatever. The society has decided intelligence is dangerous. So we're going to stop it. What kind of a world we would live in, we would not have anything that we have right now. We would live in probably just as farmers, basic physical intelligence we have and try to survive in a world where the average lifespan was 30 years old or something like that. So that's how we should view AI. And the other point is that about this sort of AI is going to take over and it's going to replace us. I see it exactly the opposite because AI is an incredible enabler. It gives you superpowers. Even now I feel like I have superpowers. You know, I've never been this busy in my life. You know, I actually sleep less, which is not a good thing, by the way. I don't recommend it. But because I can do so much, it's so empowering. You know, my mom was 86 years old. You know, she told me that ChatGPT changed her life. She's energized, she doesn't worry as much about her health and it's just been an incredible impact and this is going to accelerate and at some point we will sort of merge with the, with the AI in a way that we will have direct interaction with AI through Neuralink type of brain interfaces. So we'll have the sort of the intelligence of AI in our own brain, not only directly but also indirectly by engineering our biological system. Why shouldn't everybody have an intelligence of Einstein or even higher? The difference between an Einstein and a normal person with a normal IQ is probably few gene single point mutations. If we can engineer that, if AI can teach us how to do that, then we're also going much, much higher. So as long as we keep the Agency, I think that's the only thing that we have to really protect, that we are the decider or we see AI as a collaborator, as another species that will live together and we empower each other in a way. It's our child, it's been created by us. I see the chance of it. A worse world extraordinarily, of course, is never zero. But you know the moment you're born, you're going to die, right? So, so you're destined to die. And now AI is giving us this opportunity to save, literally save billions of lives. I'm not talking about saving lives as like extending their life for five years or 10 years. You're talking about thousands of years. So that's true. Saving lives, that's the potential. And the risk is again, I think the key risk is humans, humans misusing AI. That's what we have to sort of maybe train or align the AI. Don't look at the bad humans. You can judge the better world for us. Of course I might be wrong, but I'm pretty sure I'm going to be right.

Rhonda Patrick: I agree with the statement of we have to watch out for the humans for sure, because you're right, they can and have in the past been the biggest threat to humanity. So

Can AI replicate a scientist's biological intuition?

Rhonda Patrick: I want to, there was a couple of things that you mentioned when you were talking about ASI and this ability to self learn. And you're even talking about some of the ways that you use, you know, GPT-5 Pro and helping with designing experiments and interpreting results. And that was a question that I had as a biologist. And as you mentioned, you know, we do experiments, we're testing hypotheses and then we have all this data and these results and we have to know what result is meaningful and what anomaly is meaningful. Because oftentimes the anomaly which you might ignore is what you absolutely is the breakthrough. Right. And that is a sort of intuition, this biological intuition. And so you do you think, first of all, do you think we're that, you know, the models we have now can already are capable of that sort of biological intuition? And if not, like, how far off is that?

Derya Unutmaz: Yeah, yeah, that's a great question. In fact, you Know, I see that intuition maybe sort of the last mile or the top 10% or 10% of the solution. Because 90% AI models are able to come up with because it's knowledge based also in humans. For a medical doctor, for a scientist, for whoever, 90% or 95% is based on what's known, how you process that knowledge. But there's that extra 5, 10% totally dependent on your intuition. Like, if you're a doctor, you see a patient coming through the door, you know that guy's having a heart attack, you haven't checked anything yet, Somehow you know, you don't know how. You know the same thing in the lab. Like, in fact, I would bet with my students and postdoc, I would say, okay, I bet you if you do this experiment, you're going to get this result. And I've never lost a bet and they stop betting against me, even though it might look counterintuitive. Oh, no, that's never going to work. Somehow I know. How do I know? Because, you know, I've been working in the lab for 30 plus years and you acquire certain things that are not in the literature or, you know, you can't really read a textbook and learn it. You only do it by practicing it. So the models up to I would say 5.5 until recently were great at that 90% level. So especially after GPT-5 Pro came out. So I would ask it to, for example, I would give it an experiment that we have already done. It's a very complex experiment, took two weeks. I already know the result because we're done the experiment. But I wanted to see how the model would predict the outcome of the experiment. And they would do not just GPT-5, but several other models as well. They would come up with 90%, 80 to 90% correctly. That's pretty good. They would say, okay, this is what's going to happen after two days, after one week, after two weeks. But that extra level of intuition that I would have predicted was still somewhat lacking. I think GPT-5.5 crossed that threshold. So I repeated that with the 5.5 Pro model because I always say pro. It's very different than the thinking, of course, very, very different than the instant model, because PRO is reasoning much longer, it's thinking. So in some cases I pushed it to think for two hours. So two hours in AI thinking is like years of thinking for a human being. So that model really crossed that threshold. And that example I gave you, it was almost 100%. I mean, I would say 98% correct. What I would have predicted, like I would not have bet against 5.5 Pro myself. So that to me is, is actually really mind boggling because I couldn't understand. These models are being trained with all of the information. We can't compete with that. Right. So it's, they can put these patterns together. But how is it that the model has now almost the experience that I have, that I spent 30 years acquiring that experience, that intuition that is now getting to that level, that is, that is mysterious. But I live through it.

Rhonda Patrick: Now what sort of, you said you pushed GPT-5.5 Pro to think for two hours. I mean what sort of prompt are we talking about? Or is it just the data set too and the prompt?

Derya Unutmaz: I mean so those are usually data sets. I might have broken a record because I even ask the friends at OpenAI, I don't think they pushed it that far. So this was actually the two-hour one was huge data sets, millions of data points. And then I also said, okay, don't just analyze it, write a huge report, 30, 40 page, whatever length and then come up with a lot of insights about this data, what questions to ask and what do we learn the mechanism, it was an immunological data set sequence and genes and proteins and all that. And so that one, I think 112 minutes, I remember that. And it came up with this 40 page report which I was just. This is unbelievable. The analysis part, the previous models were able to do as well. You know they say okay, well there are these type of genes and this type of protein, so it means this and that, you know, it derives from that information. But to come up with an insight what that could mean or what would be the next question to ask. That's a very, very high level of reasoning. And so yeah, it was worthwhile. Two hours for sure.

Rhonda Patrick: I mean that's very exciting to hear you say that because that was kind of my. I wanted to know, I wanted to know is that something that is already possible? And it seems like it is.

Is it malpractice for doctors not to use AI?

Rhonda Patrick: And so it also leads to the next question which is all these scientists now really need to start understanding how to use AI in the right way. Right? I mean this is like to help them. I mean it's going to happen, right? That's basically we all use Google now, remember when Google was new? So I mean it's eventually going to happen. But it's very exciting to think about how AI is going to change research and medicine. And that's something, you know, you mentioned. And I talked, I said I wanted to get back to this digital twin idea because I've heard you talk about it and it's very exciting to me. You know, we've heard for decades now that personalized medicine is coming, we're going to have personalized medicine and yet still we just don't have it. It's just not there. And I've heard you, I've even heard you say something sort of interesting, which perhaps I'm not saying the direct quote, but that it kind of should be medical malpractice in a way for a physician today, right now to not be using AI. So can you talk a little bit about why you said that, what it means to, for a physician to use AI responsibly. Also how patients can self advocate for themselves because that's also another area.

Derya Unutmaz: Yeah, in fact I said after o1 model came out, I think that was sort of the first reasoning model and I was testing a lot of, I mean I have a medical degree but I don't see patients, but I have a lot of friends and I have some knowledge of how medicine works. So been testing lots of medical questions and some of them are hard, some of them are, you know, sort of real time data. And you know, before o1 it was great in sort of reaching to the literature. You know, like the physician might lack certain, certain knowledge, so it knows what was published recently and things like that, but it was not at the reasoning level. So one model was able to reason and the reasoning is extremely important medicine because you know, even if you have all the, all the information, you still have to sort of consider that person's context and you know what, what would be more likely to treat that person. And we don't always know the answer as well or how to, how to diagnose it. And So I think o1 was able to get to that point. And at that point I said right now it's unethical for physicians not to use AI anymore. I didn't say malpractice yet, but truly unethical in the sense that you can use it. You can still do your judgment obviously, but it will prevent you missing some sort of an obvious mistake or sometimes non obvious mistakes or diagnose things that require multiple clinical specialities coming together. And you don't have that capability, you live in a village or something. But now I think I feel that it is truly going to be considered malpractice in my opinion. It's not legally so, but eventually it will be because the current models, the advanced models are able to diagnose and write a treatment protocol better than or as good as a specialist in that field. It's not just a family physician. Let's say you have a very complex cancer, you know the mutations and what's not, and you go to a specialist like an oncologist who is very, very specialized on that. I believe that the current models are at that level. And of course not every specialist is the top specialist. Right? So if that was the case, we wouldn't have millions of misdiagnosis mistreatments in the US alone every year. I think they said something like 12 million misdiagnosis. I think 700,000 people suffer from it, die from it, from misdiagnosis. Some of them is totally innocent. Any doctor could have missed it. But now AI wouldn't miss that. So even a specialist might make a mistake or misdiagnose or mistreatment because they lack certain things that the model doesn't have. So I mean, imagine that you refuse to use MRI machine or CT machine because you say, well, that's too much technology. I'm just going to just do an X ray because that's enough for me. And you miss a tumor. The models are able to detect certain tumors like breast cancer years before a radiologist is able to see that. So if you miss that, I mean that person is going to die if you don't know. So to me that becomes a malpractice because the technology is at that level now. It wouldn't be malpractice missing a breast cancer five years ago because nobody could. We didn't have that technology, but now we have that technology. So you should definitely use it. And this is going to save a lot of lives. I mean, if you could just reduce the misdiagnosis and again bring every doctor to super doctor level, I think that would be a really good thing.

What happens when AI monitors disease in real time?

Rhonda Patrick: So what you're saying is based on what current data that doctors have available to them, whether it's an MRI or whether it's an ultrasound, whether it's blood biomarkers, this sort of data is what is given to a model like GPT-5.5 Pro, for example. And with that data they're able to better diagnose better, to predict, to see things. Like you mentioned cancer. Is that better than a radiologist can? Is that like based on what kind of data is implemented?

Derya Unutmaz: These are studies. I think Google did a recent study. In fact, a science paper came out recently which was done with o1-preview model, which is a very old model. I mean the current models are probably 10 times or maybe more.

Rhonda Patrick: Was that like the first pro almost?

Derya Unutmaz: Yeah, it was the first sort of the reasoning model that I early tested in 2024, September it came out and they found that o1 model did better than average doctor in diagnosing, like significantly better. They didn't miss. And so imagine the current models how good they are. But I think it's not just sort of diagnosing a disease because that's actually a small part of the job of a doctor. It's really, there's a continuum. Most diseases, okay, if you have a flu or some bacterial infection, you know what to do, you give it and then you see an output. But a lot of disease, even in that condition, that may not be true because you might have a mutant virus or bacteria, so you might have to change the treatment or might have a little bit of a side effect. So there's a lot of continuum there. So I think AI can be involved in all of that process. So if you can continuously feed the data. Okay, well, the patients we gave this treatment, it's doing well. The blood pressure is down, but has this symptom, that symptom. So what should we do? Change the dose of the drug or add this or remove that drug and give another antibiotic? There's a constant process there, and that's not always that constant because people don't go to doctor every day. So you get a prescription, you see something works, and then you go back. And so what if there's something that's continuously monitoring you post treatment for cancer? It's very important because cancer is a very dynamic disease. There's the cancer which is constantly trying to survive and mutate and counteract against the immune system. So you give it. So, you know, you give a drug, chemotherapy works, and then the cancer comes back again. Why is that? Because mutations are accumulating. Can we catch that earlier? Can we change those decisions? Can we make sure that we give more multiple drugs or different drugs so before the cancer have the opportunity to come back, we prevent that possibility. All of these decisions can be made together with AI. I think it's going to have tremendous, tremendous impact on healthcare.

Which AI models should doctors trust?

Rhonda Patrick: I do want to get back to the cancer equation in a minute. But before that, I just think that physicians, not all physicians know how to use AI. They don't know which models to use. Do they use GPT-5.5 Pro or Claude or how do they sort of responsibly use it, which you kind of talked about a little bit, but without, you know, outsourcing Their clinical judgment. Do you have any opinions on like the different models to use? And I do know you have a collaboration with OpenAI. You've been one of the first scientists really testing these models in a biological sort of arena. But I do kind of, I do think that people and physicians that are listening want to know what, what, what models do they use? We definitely are talking about, if we're talking about OpenAI, not it's got to be the pro, right. It's got to be the reasoning model. But I mean, what about Claude, what about Gemini?

Derya Unutmaz: Yeah, so I think people have this sort of a misunderstanding of they think of AI as okay, we have AI, we have Internet, so let's just use the Internet. We have AI, let's use the. But this is advancing so rapidly. The AI model that we used one month ago is not the same AI model we use now. So it's just doubling in intelligence every few months. You know, I gave the example o1-preview. Some people got stuck at GPT-4o model. So oh yeah, I used it and it hallucinated a lot. Even, you know, o1 wasn't so good. You know, it was making mistakes. That's like an ancient history.

Rhonda Patrick: That's why I haven't even asked about hallucination.

Derya Unutmaz: Yeah, so it's, I mean the advantage I have is that, you know, because I'm all in on AI, I'm continuously testing and so I can see the evolution of these models and they get, you know, 90% better, 95% better, 97% better. Like it just continuously updates itself. And then eventually, right now with 5.5 model, I don't see any hallucinations whatsoever. I mean There might be 0.1% but it's extremely rare. And so your trust level goes up again. It's similar to self driving cars. Right? So we had self driving cars for almost a decade maybe and they just keep on getting better and better because their AI models are getting updated. So my advice would be doctors should see this, not something optional like they have to update their knowledge, medical knowledge, periodically. In fact, they have to have tests to do that to be certified or they have to update on new drugs that are coming out. Right. So you can't just rely on some drug that came out five years ago, 10 years ago. You need to know what was approved last month and you need to update your knowledge in a similar way. Even more so they have to constantly update their AI knowledge. So AI has to be part of their practice. And of course my recommendation is always use the Latest top model you can use right now, it's GPT-5.5. In fact, I would always use for complex problems, the pro model, because that thinks in minutes. But at least if you're using it on a daily basis in a rapid fashion, always use the thinking model. The thinking model is different than the instant model. Instant model is also getting better, but it needs to reason, it needs to think. And especially if you're putting in lots of patient data and analyzing that, you definitely need the pro model. And then there are these companies like Open Evidence. And I think most doctors are starting to use that Open Evidence. Basically, I think applies the latest model. Somehow it updated so the doctors don't have to worry about it. And I think there's going to be more companies like that who will provide that service so the doctor doesn't have to worry. Should I use 5.5? Claude Opus 4.7? Whatever, the sort of, the harness model is going to pick the best one for medicine and apply it there. And of course, hospitals should implement AI, just like big tech companies are. There's an enterprise level of AI that can be more secure, protect the patient data. So it should be like in front of the patient in hospital, you see these monitors, like the heartbeat and all that stuff should be an AI monitor, like constantly monitoring the data and then giving information to the nurses, to the doctors. Okay, this is this last situation. And now with AI agents, you can do that. Like, I do it for my daily life, like for my email. Automatically my agents go and check my email and they tell me what's important so I don't have to go through hundreds of emails. So, you know, this is waiting for you. You have a podcast with Rhonda today, so you better be prepared for that. So, yeah, it needs to be fully integrated, almost like a co physician. Like you have the AI doctors working together with real doctors.

Rhonda Patrick: Right?

Claude vs. GPT—does the model matter for diagnosis?

Rhonda Patrick: Have you, I've noticed like some of the companies that I've corresponded with or interacted with, it seems like they use Claude a lot. I mean, I don't know if you've experimented with that, but I'm kind of curious why, why that, why that, you know, certain model versus like. But yeah, in all fairness, I've never used it. I use, you know, I've been using GPT and the Pro and so every, like you said, you know, every time, the hallucinations are like ancient history for me. Like, I remember that was a big thing, but it's going so fast and better now. But like, what, what, what, what's the Difference between, you know, for example, Claude and GPT-5.5 Pro for certain things

Derya Unutmaz: there is no more difference because the intelligence has peaked. For doing regular diagnosis, not very, very complex cases. Claude is great. Claude is also very good, like the Opus 4.7 model, the recent model for analyzing data sets. So it can take also millions of data, analyze it and do a great job. My preference is GPT-5 right now is 5.5 Pro because what I mentioned, it has this extra insight. I mean, for me I need that extra level of insight that's predictive.

Rhonda Patrick: Intuition.

Derya Unutmaz: Intuition and really kind of a deep understanding. But if I'm going to diagnose and treat a subtype of a lung cancer, I'm Pretty sure Gemini 3.1 Pro or Claude Opus 4.7, they all do a pretty good job. I think some reason people prefer Claude is that maybe it's more pleasant to interact with kind of more human. Like I think GPT models are starting to get there. But still there's something about Claude that people enjoy interacting with it. It's really a matter of personable. I think it used to be more personable and so it doesn't really matter. I mean, I think they're all super top levels unless you're doing a research or very complex problem. For example, we did a test with a colleague of mine on skin disease with GPT-5 Pro model. It was able to diagnose a skin disease that my friends couldn't really diagnose just based on a photo and a symptom. The other models couldn't do that. They could do 90% of the cases as well. But there's that one extra case or two extra case that is really difficult, that could go anywhere. The GPT-5 Pro model was able to cross that threshold. So those kind of cases you really need the very high level. Like you don't go to a professor at Harvard for any reason. So it has to be very specialized disease that other doctors couldn't diagnose or something like that. So that's how, that's how I view it.

Generalist vs. specialized AI—which works better in medicine?

Rhonda Patrick: There was just news yesterday from OpenAI of GPT-Rosalind, which I know you can't talk about much, but from what was publicly available, it seems as though it's going to be used in drug discovery. I'm wondering what you think in terms of the future of aging, research, biology, medicine. Are we going to be using these more specialized types of AI models or do you think more of a generalist like GPT-5.5 Pro and the subsequent ones that come out after it are going to be the key to unlocking medicine breakthroughs and biology breakthroughs.

Derya Unutmaz: My preference would always be the generalized models because again, going back to AGI. AGI. So if, if a model has, you know, of course there are some utilities of models that are only trained on, I don't know, like the EKGs or RNA sequencing or something like that. And they'll be very, very good at that. Like the best chess player AI model or the best go player AI models. But they will miss that connection because again I view medicine as a kind of a holistic art in a way. If you are just trying to analyze one set of data, the specialized models could be very, very useful. In fact, I gave the example of EKGs. Most generalized models were not terribly great at, for some reason the EKG images were not, they were not very good at diagnosing what it was showing. And specialized models were very good because they were trained with millions more EKG data sets than the generalized model was. But I think if we can train the generalized model or fine tune it or over train it, I don't know how to say it, then they will be better than specialized models all the time because not only they know all about EKGs, but they know all about radiology, they know all about RNA, they know all about proteins. So they can take that information and excuse me, analyze the EKG, the electrocardiogram, Your heart beats in the context of all the other biology. So that will, that's very enriching knowledge. But I think, you know, specialize in the sense that you can take these big models and you can sort of, I don't know, harness them or fine tune them because there's a lot of data sets that's not public. So these, these models, they don't have access to that. You might have some data, you know, locked in certain because of regulatory reason, whatever. So you can take, take a big model. In fact you don't, you may not even need the, the closed models. You can even take some of the open source models which are now getting very good, you can train them on that and they also have the generalized knowledge and combined with that they'll probably do better.

Why cancer is so hard to cure

Rhonda Patrick: So I want to talk about, there's treating disease, there's curing disease and then there's reversing aging. So let's start with curing disease, treating diseases, curing diseases. Because obviously we do die of age related diseases, cardiovascular disease being the number one killer in most developed countries. We have cancer. That's a really big one. And with cancer, it's just such an awful disease to have. And anyone that's listening that has either had cancer or knows someone that has had it, knows this is true. But also, I think cancer, a lot of people think about it as one disease. Non scientists, non physicians, they kind of think about cancer as just this one disease. Right. As you and I both know, it is definitely not one disease. It's hundreds of diseases. I'm curious on. First of all, we still don't have a cure for cancer. I mean, we've made a lot of progress in different cancers and can be treated better than others. But can you talk a little bit about why it's been so hard to find a treatment for cancer?

Derya Unutmaz: Yeah, I think the important thing to clarify is that cancer is not one disease. It's probably 100 different diseases that have probably hundreds of sub diseases or subtypes, if you like. In fact, certain cancers are 100% curable or 95% curable. Some of the childhood leukemias, which were completely fatal a couple of decades ago, are now 90% or close to 100% curable. If you catch certain cancers early enough, again, 100% cure rates, almost. So because it's a very different set of diseases. The cancer of pancreas is very different than cancer of lung cancer or breast cancer. Or there are some cancers that are so slow. Like if you get certain types of cancers if you're age 80, doctors don't even bother to treat it. Because by the time that will. Unless we cure aging, of course. Because by the time you die of aging, you know that that cancer is not going to kill you. Aging is going to cure you first. Or. Yes, there's certain prostate cancers at certain age. So that's why we have to really understand that this is a very complex biology. But more importantly, why cancer is such a challenge is that the cancer cells are part of us, right? So if you're infected with the bacteria or a virus, you know it can kill you. Right. They're extremely dangerous. But we are able to recognize them as an enemy, as a threat, your immune system. And we can fight back, you know, not always successfully, but most of the time very successfully. And we can also target them very specifically. Like we have an antibiotic that will only act on the bacteria. It's not going to touch your normal cells because it's only a foreign organism. But cancer is not like that. So if I try to stop cancer with something, I'm also stopping some other cells that are normal. Right. That's why people lose their hair. Their immune system is greatly weakened because the immune system has to divide. Your hair has to. Hair cells have to divide. So you. You block them because the cancer cell is also dividing. And, and you. Your side effects of chemotherapy, sometimes worse than having the cancer like hundreds of thousands of people die because of that.

Could cancer be curable within a decade?

Derya Unutmaz: So the revolution in cancer was recently because of what we call immunotherapy. The question was, why can we make the immune system to recognize cancer as foreign threats? Like, they're kind of like terrorists, right? So a terrorist, you will not know if that's an enemy or not. They look like you. You know, they just come in and then they. They create. So the immune system is seeing it that way. It thinks that the breast cancer cell is not so different than a normal breast. Breast cell, you know, like epithelial cell, whatever, and so doesn't know what to do. If it could teach the immune system or if it could remove some of the brakes that it has regulation and let it recognize and attack the cancer cells, then that could have a tremendous effect. That was the hypothesis, and it actually worked. So cancer immunotherapy, I think, is. Is more powerful now than. Than chemotherapy and radiotherapy put together. I mean, they still have a role. And of course, the other thing is that how can we make the treatments very specific? If I give a chemotherapy that's not specific, it's like trying to hit the patient on the head and hope that the cancer will die before the patient dies. But if I know this single mutation that's happening on whatever EGF receptor in certain cancers, I can develop a small molecule which will only act if there's that mutation on the EGF receptor or whatever. And so it's not going to touch anywhere else. It's only going to target the. In fact, people call them smart drugs, and they're extremely effective, right? So if you have that particular mutation, you're 1% of the lung cancer patients you get treated with that drug, you get almost 100% cure rate. But again, we can make this even much better. So, for example, immune system can be engineered, Something that we work on in the lab to recognize, like, literally engineer. We take the cells out, we train them, we put genes into them, say, okay, so if this gene binds to a cell, assume that that's a threat and kill that. And so it's called CAR T therapy. And they will go and seek out whatever the cancer cells that have that marker and kill them. The advantage of that is that cancer doesn't have much way to escape that, it can try to suppress the immune system. But other than that, even if it mutates, the immune system will still recognize it and find that few cells that are hiding somewhere and destroy it. And that's showing incredible results. So the mRNA vaccines, which I think is going to be revolutionary, is on that basis. Right. And that really personalize the cancer. So I have a breast cancer, but my breast cancer has certain type of mutations that other patients don't have. So even if the immune system can recognize X patient, it won't recognize mine because the cancer has different mutations. If I take those mutations and synthesize what's called RNA and then give it back as a vaccine and train my immune system and tell the immune system, look, if you see these mutations in these genes, that's an enemy. Go destroy that. That's mRNA vaccine. And that becomes extraordinarily powerful because now you are directing your immune system to, to an internal threat just in you. And let's say the cancer acquired different mutations, you can create another mRNA vaccine and then train the immune system to that as well. So, you know, I think those are the difficult parts. But we see the light at the end of the tunnel. Cancer is going to be 100% curable, probably less than a decade.

Can AI design cancer treatments on demand?

Rhonda Patrick: How is AI going to make that happen?

Derya Unutmaz: Yeah, so in fact it's already making that happen. You've probably heard of this story from Australia. This computer scientist had ChatGPT and some other AI models to develop an mRNA vaccine for his dog. His dog had, I think a melanoma. And he got it sequenced, he took the sequence and gave it to an AI model. And the AI model designed the precise mRNA molecule that dog's immune system needs to be trained, got it synthesized, and I think it was able to apply it in three months. Probably could have been shorter if there wasn't regulations. And the tumor started to regress and the dog was alive when it was supposed to die. So I mean, that's a very obvious and simple version, but because there are hundreds of different cancer types, you can imagine that we'll have maybe 100 different treatments for just a type of a lung cancer. Some of it will be mRNA, some will be small molecule targeting that. So to be able to develop those on demand or very, very rapidly, we're going to need AI. So the AI is going to model every possible mutation and will screen millions and millions of compounds. And so we'll get to a point where we'll have hundreds of new drugs coming out every month, maybe and this thousand drugs is for breast cancer patients. But if you have this and these mutations and if it's stage four, then you take this combination. If it's that, you take this protocol and that's how AI is going to. Of course, if you get to digital twin, that will accelerate.

How AI could curb overtreatment and side effects

Rhonda Patrick: Right. And that's the next question is. So let's say we have the true personalized medicine and personalized cancer treatment, but you also need to know about side effects. Am I going to take this, this mRNA vaccine and my immune system's gonna go crazy and start to inflame my heart and give me myocarditis or something? Right. So how do you also see this, the digital twin which now has, you know, genomic information, all your proteins and metabolites and everything in real time data, then it can also simulate, well, what's gonna happen if we give this specific mRNA vaccine, cancer vaccine, or this small molecule to this person?

Derya Unutmaz: Absolutely. I mean, you know, so, so you mentioned myocarditis, which by the way happened during COVID pandemic and that's why there was a lot of anti vaccine sentiment. But people didn't appreciate that, you know, COVID virus itself caused myocarditis. Yes, the vaccinated people, young people at 1 in 5,000 to 1 in 10,000 rate got myocarditis. It wasn't mostly fatal. But the question should be asked like why is it that 1 out of 10,000 got myocarditis and the other ones didn't? Or in fact we can reverse that question. You know, we get, we vaccinated everybody. But if you were a young person, your, your chance of dying from COVID was let's say 1 in thousand or 1 in ten thousand. So 9, 999 people got, didn't have to be vaccinated. But to save that one person we have to give that vaccine or I'll give another more general, you know, we give statins to anyone who has high cholesterol. So I, I think like 1 out of 5 or 1 out of 10 people truly benefit from that. High cholesterol doesn't automatically doesn't mean you're going to get atherosclerosis. You need to have inflammation this and that. But because we don't have the data, we cannot predict that. It's not personalized. Millions of people take statins and to save few thousand people. Yes, that's, that's a good thing because you don't know. So AI will be able to do that. So we'll, we'll Tell you, okay, not only will create the drug just for you, but also will say, okay, you don't have to take this, this medicine. You should take this. Or maybe you don't even need any treatment at all. Like, do you have an infectious disease or whatever, or maybe certain cancers, this will be enough. Like we give extra chemotherapy plus immunotherapy, plus radiotherapy. Why are we doing that? Because we're not sure if one is going to be enough or not. And so that will dramatically reduce the side effect issue. You might still have some side effect, of course, but it will be manageable side effect. It's not going to kill you.

Rhonda Patrick: For example,

Predicting cancer years before it forms—is it possible?

Rhonda Patrick: What about using AI to predict cancer a decade or years before it forms, based on your proteins and metabolites and your biomarkers and maybe perhaps your genetics too. Right. Like, how do you see that? We're talking about personalized cancer treatment, but what about being able to prevent cancer before it happens? You know, years before it happens?

Derya Unutmaz: Yeah. Again, great question, because I think this is so important that people don't think about very much. We say health care, we don't have health care. We have sick care. Right. So we never take care of healthy people. Like, you don't go to a doctor to say, oh, how healthy I am, or just go to a doctor and say, can you check my immune system? Is it healthy? Am I going to get sick? Am I going to have cancer? They won't be able to answer that question. Only if you get sick, they will treat what the problem is. And so the preventative medicine is going to be so absolutely critical. I think not all, but most diseases can be prevented. It some are just bad luck. You know, it happens no matter what you do. If, even if you live the perfect life, you might still get certain disease, but a lot of them are because of your genes and so on. A lot of them can be prevented. And I think AI is going to be amazing in that because it's already able to do it. That there was a study from UK Biobank, UK has this amazing biobank with 500,000 people, lots of data sets, incredible data sets. And so, and this was actually done, I think, more than a year ago with models that were a year or two years old. They took a lot of that data and they were able to predict about thousand diseases before they happen. Of course, this was kind of retroactive. So they knew what, what people were going to get based on their data that was collected years before. But the AI was telling you, okay, this patient is going to have this disease that, but not patient. Normal, healthy people, they're going to get this and that. So that, to me, that was, that was amazing. And that's going to get better and better because there are, there are, there are always signs. Like cancer doesn't just develop in days, it takes years. If we probably most of us might have some cancer cells, you know, most of it controlled by immune system and so on, and it, you know, slowly grows. It has to have another mutation, another mutation. But there's probably some signs of that somewhere, whether it's in your metabolism or this. And AI, even if it's 100%, will be able to say, okay, look, I think that if this is the lifestyle that you continue, your chances of getting this disease is 85% or whatever. I wear a glucose monitor. I'm not diabetic, you know, but I want to see every minute or every five minutes what my sugar levels are in a continuum or if I eat something, you know, is it spiking, is it coming down? Because I want to prevent insulin resistance. One of the worst things that can happen to you if I, if I don't do that, I won't know until I get diabetes. My insulin, if my sugar is constantly spiking and then insulin is just working too hard and harder, that could continue for years, by the way. At some point it's going to break. For some people it might continue 50 years, nothing happens. Some might be five years. But that data set probably has that predictive value that plus my age, my genes, whatever. So, yeah, I think everyone's going to have their own AI. I don't know what to call it, health coach or something, but it will continuously analyze the data and hopefully it will be much easier to collect data, because that's another issue. We don't collect data we know nothing about. There are more than thousand metabolites in our bloodstream. So we look at maybe 10 of them, 20 of them, only if we get sick, not even for a checkup. So we have to have a continuous, like a glucose monitor. I want to see what my, you know, proteins are changing, hormones are changing, you know, in a reasonably continuous manner.

Rhonda Patrick: Such a good point. And I'm so glad you brought up the UK Biobank study. I remember, I think the model was like called MILTON or something. And it was, it's a AstraZeneca, like developed it or something. And, and I remember looking at this study because, like you mentioned, the biobank data is huge data set and they're just spanning many decades. And so I think they looked at, you know, like over 200 plasma proteins. You're talking about 10, we're talking about 200, right?

Derya Unutmaz: Yeah. Oh, yeah.

Rhonda Patrick: And all the other data. Right. And they were able to predict, and I think cancer and neurodegenerative disease were at the top of like 10 years before. And they were able to look at the people. So the AI predicted it based on, based on all this biometric data. And then they looked and said, oh, yep, those people actually did end up getting cancer and Alzheimer's disease. And it was very accurate.

Derya Unutmaz: Yes.

Rhonda Patrick: And to me, the exciting thing here is that you can intervene before it happens. You can make lifestyle changes, you can make dietary changes. I mean, these things matter. They do matter. And that is exciting because then you don't even have to get to the drug part, which, you know, maybe you will. But if you can make these changes, if, you know, hey, I'm on this trajectory to get cancer, I have all this inflammation, I have all these things happening. If I don't make a change now, then in 10 years I might have a cancer. It's very motivating, you know, for someone. So it's very exciting as well. And then having AI in there is just going to make it even better.

Why biology could go exponential with AI

Rhonda Patrick: And then I want to get into age reversal. And before we get to that, you've really been a pioneer in the field of AI being involved in biology. You were talking to me about your blog. I don't know, was it 30 years ago?

Derya Unutmaz: Biosingularity? 25 years ago.

Rhonda Patrick: 20, 25 years ago, yeah. So you have this blog, Biosingularity predicting. Can you talk a little bit about it?

Derya Unutmaz: Yeah, sure. So in fact, I got interested in AI early 90s after I graduated medical school. I was very interested in computers when I was a teenager. The first computers had come out at the time and I was trying to code and I mean, I loved it. It was just so wonderful. But I went to medicine because I figured biology is much more complex, so I should first try to figure that out. But then immediately I realized, and I'm sure you did too, you're a scientist as well. The biology is so incredibly complex. I said, well, I mean, you know, we don't have any chance of figuring this out, you know, because there's going to be so many, so many data sets. So that's when I first got interested in AI. Of course, at the time, you know, AI was very primitive. But fast forward, one of the books that influenced me was from Ray Kurzweil. I'm sure a Lot of people follow technology, know him. He wrote this book The Singularity Is Near. So he called a point of singularity where the computation or technology advances exponentially so much that you cannot even predict what will happen next day. Because it's sort of like self training AI models. And he had these figures where he would plot the advances of AI. Say by 2029 it will be at the human brain level and will reach AGI. And it was just unbelievable. And most people thought that he was just talking crap or science fiction. They didn't believe it. How could that happen? And so on. But I got very excited. In fact, I have a signed copy for the book. Being inspired from that, I started this blog called Biosingularity. I said, okay, so computation is going exponential, but biology is a computation as well. It's based on information, but it's just much more complex. It should also expand exponentially. And if you plot that curve, that means that based on my calculations 25 years ago, in fact I wrote it on the about page of the blog. By year 2035 or so, we should be able to treat all diseases. And by 2045 or so that we should be able to completely reverse aging. In fact, by 2050s we will get to a point where I call Human 2.0, because at that point we have a complete understanding of biology. Then we can truly engineer it. We can create new biological organisms, we can change our biology, our genome, reprogram it, rewrite our immune system. Yeah, exactly. In many possible ways. Because it's kind of messed up if you think about it. Biology we think is a miracle, but it's a bad kind of a legacy engineering, right? It's not a bad engineering. It's a legacy. Because biologic system finds something it can't get rid of. It can't start from clean slate, so it builds on top of it. So you get regulation over regulation over regulation. And then of course, you know, with like immune system that I study, you know, you get lots of autoimmune diseases. Immune system kills a lot of people, you know, even during like pandemics and things like that, or doesn't recognize the cancer cell and things like that. So why, you know, we should be able to design like immune system 2.0, like clean slate, really greatly engineered immune system. Well, and I said, you know, by 2045, 50, we'll get to that point. And actually, you know, again, at the time it sounded really crazy to people, but now I feel that I was, I was too conservative. We'll probably get there. But the key Point is that I wrote specifically about we will do this because of artificial intelligence. You know, I was just taking the plot that Ray plotted. You know, I said, okay, by 2029, AI is going to be at that point, it will be good enough to apply to the biology and that will allow us to solve diseases. And then, and then the aging. The fact that, you know, the timing was pretty good, again, even a bit conservative, I feel great about it. That's why I'm all in on AI. Like, wow, it's happening. It's really happening.

Why aging may be easier to prevent than reverse

Rhonda Patrick: So aging is very complex. And as you know, it's not one process. We've got these 12 hallmarks of biology. We now have 12 genomic instability, mitochondrial dysfunction, cellular senescence, on and on. There's 12 of them. And we know organs are aging at different rates. They reach their peak at different rates, and they age at different rates. And everything is interacting in a very complex way. What do you see as the bottleneck for understanding the aging process and also reversing it?

Derya Unutmaz: I mean, more so than the bottleneck, this is the way we have to think of aging. Biology actually is programmed to prevent aging. So it's not like a car in a way, because once you make a car, you have to constantly bring it to a repair shop or you have to repaint it. Biology does that internally. If it didn't, we would age immediately. Like there is a disease called progeria. These children get age by the age of 7, 8, they become like an 89-year-old because of single point mutation in one of their, one of their genes, because they lose their ability to repair. Whether it's the DNA repair, whether it's getting rid of the old cells or cleaning up the tissues and then regenerating like stem cells, creating new cells. So this program continues for sometimes decades. Otherwise we wouldn't survive for some animals. For some organisms is only a couple of years. For us it's about, you know, maybe 50, 100 years. For some whales, it's hundreds of years. So, you know, same biology. It's just that one of them decided that, you know, I can keep a whale, or, you know, whatever. Some animals, you know, older longer because they don't. They're not getting hunted or they can reproduce later and so on. So what happens in, in, in the, in the biological system is that somehow this program breaks down and you start to lose what's called the res. Resilience, right. So when you are age 30 or 40, you're a, you're resilient, you can tolerate much More damage than someone who's 70 years old, 80 years old. Because your, your systems are, you know, even if you get wounded or if you get sick, you can recover easier. But that, that, so that resilience is lost and that the reason why it's low is that there is a sort of an information loss because the biological system has a certain information that it knows when certain genes should be turned on, when things should be regenerated, when it needs to be like your skin. You know why you get wrinkles? Because your cells stop making collagen. And then all kinds of crap accumulates under your skin. And then, you know, the guy, the guys who like the macrophages or whatever was supposed to clean there, they don't do their job. There's some sort of a breakdown in information or communication or, you know, intercellular communication is one of the hallmarks of aging. And then of course, why that happens is that 12 hallmarks is the reason. Many reasons. You know, for example, the bacteria in your gut is a reason. So these bacteria produce all kinds of metabolites that help your immune system to constantly regenerate, keep it in optimal shape. If that changes, then, you know, your metabolism is changing, your glucose levels, your mitochondrial mutations, and so on and so forth. So all of these things accumulate, you know, epigenetic changes and DNA mutations, and somehow the, the biology forgets. Well, what am I supposed to do? Like, how am I dealing with that? Also because, because when a damage happens, it's harder to fix a damage than prevent it, right? So if, if you're continuously taking care of your car or your house, the likelihood of it's, you know, breaking down is much less than if you wait until like, okay, nothing works. Yes, you can reverse it, but it's going to take a lot more effort. And so I think what will happen is that for younger individuals in the next decade or so, For them, it's not going to be reversal. It's going to be prevention of the aging process. It's going to be maintaining that process, the resilience, decades more. So we will come to a point where if you are 20, 30, whatever years old, you won't age anymore because it's going to be constant reversal. But people who have already aged, let's say you're 80 years old, 90 years old, then we're going to have to reverse that process. That's more difficult. We'll be able to do it. Definitely, we'll be able to do it, but it will require lots of engineering approaches because you need to fix Most of those hallmarks, if you're younger, you prevent those hallmarks from happening. You maintain the information much, much longer. Both of those will happen. We just need to figure out what that information is being lost and we put it back.

Can the body be engineered to resist aging?

Rhonda Patrick: Do you think so? Let's first talk about preventing the aging if you're a younger person, because it's easier to do. Always prevent. If you have a person who's 20 or 30 years old, do you think that the approach would be finding, first of all, do we even know all the repair processes that are. We have what we know, right?

Derya Unutmaz: Yeah. But we still have a lot to discover.

Rhonda Patrick: We probably have a lot to discover. And so do you think there's going to be a discovery where we figure out, we know things like autophagy, stem cell depletion, you know, all these stress response genes, like antioxidant, like all these things. DNA repair, mitochondrial, the way mitochondrial repair itself. Right. Are we going to be enhancing or like tuning these up so that they keep working at their prime continually, or do you think we're going to have again, this like information where we. Why, why are those things going down? Are we going to just then go to the information of it, the epigenetics perhaps, and is it going to be more targeted towards those genes or are we going to have more of this? You know, we'll get into this cellular reprogramming and partial reprogramming. But I'm curious, like, how you see AI coming into that process. Like, I guess we don't know that's the part of the problem. But then we have to figure out how to give these treatments to people. Right? That's another part of the equation.

Derya Unutmaz: So I mean, I think the ones that you mentioned about sort of the lifestyle changes and they of course help a lot, but they only slow down the aging process. I don't think there's anything that reverses that process. There might be some sort of local reversal for a temporary period of time maybe, but it's still kind of trying to hope that things won't go bad a little bit longer. Like, for example, some people can live to 100, others only to 60. Right. So there's something good about those who live to. And in fact, there are supercentenarians who can make it to 110 years old. Very, very few people. But I think it's mostly genetics. I mean, their lifestyle might have helped a little bit. Something about their biology is able to maintain that information much, much, much longer, that program. So we have to get to the Core. What, what are the things that are disrupting that information loss? And yeah, it's, of course, you. You have to focus on the. On the genome, because that's. That's sort of the blueprint. It's not just that. It's sort of what affects you afterwards. You know, that your. Your microbiome, your metabolites, you know, how those things are changing, whether accelerating or reversing. You know, like, it has to be kind of an engineering approach as well. Like, you know, the skin aging is a very different problem than immune aging, than the brain aging.

Rhonda Patrick: Right.

Derya Unutmaz: So your skin cells are constantly renewing. So all you have to do is to have sort of the programmed stem cells to go in there, clean the environment, senescent cells, and get it. Get it regenerated and produce collagen and whatnot. But the brain is not like that, right? So you don't want to regenerate your neurons. You will lose your identity. So they have to be dealt in a different way. Some of it will be, I think, for the younger population, it seems like redesigning certain biology sounds radical, but it would be more foolproof. Right? So what if it could change the genome through genetic engineering? We add certain genes or we change certain genes such that the DNA damage is checked much, much longer. Because there are, in fact, certain animals who have better DNA damage proteins. They evolved to do that. Elephants rarely get cancer because they have this gene called p53. We have multiple copies of that. p53 is kind of like the guardian of the genome. You know, it prevents the genome from getting too much mutations and prevents cancer. So somehow elephants have three. I don't know how many copies, but they get very rarely cancer. Naked mole rats, you probably know that very well. You know, they're like rats. They live underground, but normal rats live a couple of years, and these guys live 30, 40 years. So it turns out they have some mutation in some immune gene called cGAS. That's all involved in immune optimization and DNA repair. Just like, you know, one or two genes make a huge difference. So can we engineer humans to block that degradation of information? For those who already had the damage, then we're gonna have to think about repairing that, reversing it, and then maintaining it. That's gonna be a bit more challenging, but we'll get to that too.

Can AI model how gene therapy will behave?

Rhonda Patrick: What do you think about. So the gene going to gene therapy? There's obviously gene editing, gene therapy, and right now we only know what we know. Right. Again, like with these longevity genes we know about. But do you think that AI Is going to be able to help us analyze the human genome. And I don't know what other data sets it will need, but we'll give it everything and help us figure out. Well, actually there's interaction of these genes together and when there are all these combinations, Is that something that you think is going to happen? We'll actually figure out there's a lot more to this equation than we originally knew.

Derya Unutmaz: Yeah, that's the critical problem. Because we know what all the genes are in the genome, we have it decoded completely, and we pretty much know their functions, most of them. Even if you don't know every single gene involved in aging, we know a lot of them. The problem is that different gene first of all can create different proteins. There's all that splicing that happens and so on. But even without that in a different context, the same protein can kill a cell or causes survival. Like in immune system, we have these receptors called TNF receptors or whatever. They can have a survival signal or a death signal, suicide signal, depending on the context of the cell. So that is very, very critical. That how, as you pointed out, how these genes and proteins, in a network fashion, in a sort of a topological network, what do they do if I interfere? Probably we'll talk about that. These things called Yamanaka factors, where you can generate a stem cell from a normal cell, complete regeneration. But the problem is that they can also cause cancer because they only need to be active in certain time. If they're active all the time, they can cause teratomas and things like that. So that part is so complex that we absolutely going to need AI to simulate that for us. If I have this gene in the context of all the other things at certain age, with these epigenetic programs, plus all the metabolites and so on, because those are constantly signaling the cell and letting the proteins do something and so on. What would happen if I interfere with that particular gene or how can I improve that? If you have a. Because you have to consider the other genome too. Like your gene therapy might be very different than somebody else because you might have some great genes that are synergistic with that other person might have not so great genes. Even if you try to improve it, that would actually work worse or it wouldn't help. So it's just a matter of complexity. There's so much information that the AI has to not only put that together, but have sort of almost a temporal simulation of the models. Like that's a very important point because right now the models are kind of static. They have a good understanding, but they don't know what would happen. If a cell comes next to a tumor just two minutes earlier, the cell next to it, what that context affects, There's a behavioral issue. It's the same problem with the robotics, right? So kind of the physical intelligence or the biological intelligence. Once those models are evolved with a lot of data, I think we will be able to simulate this and AI will be able to decide this is the gene therapy you should get. So you need a new copy of immune system, but let me design it for you.

What people who reach 110+ reveal about Human 2.0

Rhonda Patrick: It's so exciting because not only are we talking about extending our lifespan and curing disease, but we're talking about like getting rid of side effects in a way. I mean, you know, people all respond to different foods and treatments and everything differently, right? Some people have a terrible response to perhaps, maybe a vaccine and others don't. And so it's really exciting to think

Derya Unutmaz: about that, which I by the way, call Human 2.0. And maybe we'll get to Human 3.0, which will happen at this Biosingularity moment. What that means is that we kind of re engineer ourselves. I always think about like most scientists or most doctors think, like what's wrong with this person or patient. I always think the opposite. There are certain people, I'm saying, what's right about them. Like this person has smoked for 50 years, never got a lung cancer or, or you know, had a terrible diet or whatever. This one lived to be 110 for, you know, whatever reason. And so what is good about those people? Why can't we take what's good about all of those people and then re engineer those that are not so lucky to be born with what's so good and then, you know, even make it better. So that's the Human 2.0.

Rhonda Patrick: Right? I mean, that's exciting to me as well. Right? I mean, we do know, like you said, we can live. Humans are capable right now of living. To be is the whole. I think the oldest was like 121, maybe 123.

Derya Unutmaz: French woman Calment.

Rhonda Patrick: I mean, the fact that right now in 2026, we know that humans can at least live to be 123 is exciting.

Derya Unutmaz: 115, I mean, 115, 116. That's considered sort of the current limit. But you know, only 300 people in the world are 110 and older. Why is that? Why not the rest of the 8 billion?

Rhonda Patrick: Right? Yeah, it's fascinating and I'm so excited for Having this super computing power to help us figure that out.

From Dolly to Yamanaka factors—the case for cellular age reversal

Rhonda Patrick: What did you think when the Yamanaka factors were discovered by Shinya Yamanaka? And all of a sudden you could take this old cell and completely revert it to essentially induced, you know, pluripotent stem cell. Do you remember? Like, is that. Was that something. Did aging come into your mind at that point where you're thinking, well, that's the youngest almost you could get?

Derya Unutmaz: I mean, yeah, of course. In fact, at the time, I was part of some aging groups. I think like an hour after the paper was published, I was, you know, typing there, you know, like, this is. This is it. This is amazing. So I should say that there were two moments for me that I thought that aging was going to be reversible or curable. However you call it kind of like the ChatGPT moment of biology. The first moment was the sheep that's called Dolly. You probably know, it was the first cloned sheep. It was 1993, 6, 7 or something like that. I can't remember the exact date, but it was in 90s. And so basically the, the scientists took a cell from, you know, from one sheep and then recreate exact copy of that sheep, you know, by. By cloning. Was. It was at the embryo level, but it was sort of like exact copy of it. So that means that there was enough information that you could just recreate the same person again and again and again. Then the second, of course, the Yamanaka factors, in 2016, I think. And that was the moment that we knew that we could completely erase the age of the cell on a cellular level and then bring it back to a pluripotent stem cell level and then use that to recreate the whole biological organism. So it means that we have unlimited supply of regenerative capacity. Like, there's no limit to it. In fact, we already know that. Like, so our DNA just keeps. For billions of years. It keeps going. And the fact that you could do that in the lab and you could generated was, was. Was amazing. But of course, the, the problem was, okay, so then how do you apply that? In fact, I think there was just a recent study that started in Japan using the Yamanaka factors in clinical trials, because, you know, it was not a very controlled system. Like, you didn't know if those cells would develop tumors—in my state, they did some of them tumors—you know, whether you can control them or importantly. I think there's going to be a trial started by David Sinclair soon. Can we do like partial reprogramming because most of the time you don't want the pluripotent cell. All right. You just want your skin cells to go early enough to their sort of more stem like level. Like, I work in immune system, and for us, I can divide immune cells into naive memory and effector and differentiate it. So the naive cells are kind of the young guys. They have huge potential to expand and make memory and effector population. And the other ones constantly die and get older. Can we actually revert the cells towards the naive? And I actually spent a long time trying to do that. So maybe this partial programming will, will, will, will enable that. And, and that's. That will be revolutionary because then you can. If you can also deliver those, then you can make most of your old skin cells turn into a younger version. I think the trial is going to be for eye with David Sinclair. Yeah. So. But again, it's, it's. These things show us that we can reverse aging. But when people say, oh, that's impossible, you can't reverse aging, this entropy, whatever. But we do it in the lab all the time. Why not do it in a total

Rhonda Patrick: organism level

Why full-body rejuvenation is an engineering problem

Rhonda Patrick: with this partial cellular reprogramming, as you mentioned, you. You're basically taking an old cell and putting these four different proteins. I think they can do it with fewer now, but putting them on for a shorter period of time on the cell. And it's changing the epigenetic program and in a way that the cell still keeps its identity. It doesn't become a stem cell, but it seems to be more youthful. I know there's been some work, and I haven't followed all this literature since some of the first studies that came out. But I think it was like Juan Carlos Izpisua. He's now, I think, at Altos Labs, but he at the time was at the Salk Institute. And he had done this in mice. I think they were even maybe perhaps progeria mice or some sort of accelerated aging model. And there was some reversal of certain organs seemed to be rejuvenated in a sense, and the life expectancy was extended in those animals. But what's interesting is that not all of the 12 Hallmarks of Aging go away. Yeah, right. And so you would hope that you would reverse aging totally.

Derya Unutmaz: Right.

Rhonda Patrick: But there's genomic, you know, somatic mutations are still there. I think telomere don't get reset. Difficult mitochondria. So do you think, first of all, I don't. I'd love to understand why that is. So what is it about? If you're if you're essentially, you know, wiping out the epigenetic current, epigenetic program and reverting it back, why does not everything change? I don't know if you have any ideas, but do you think AI is going to help us understand that?

Derya Unutmaz: Definitely. I mean, I should also point out that we do need to generate lots of data. So I think whenever I talk about AI, people say, okay, well why can't AI do it now? For two reasons. One is that we don't have enough data. So we probably know maybe 10, 20% of all the biology we still have lots of data to generate.

Rhonda Patrick: The second is we're talking about scientists.

Derya Unutmaz: Yeah, scientists or automated lab, whatever it is. So, I mean, right now we're able to generate millions of data points in one experiment, but even that's not enough. Like we need to generate billions of data points and so on. But of course, to handle that, we also need super intelligence and super compute. So we have to have compute that's thousands of times than what's available. And people say, okay, well why are they building all these data centers? Isn't this enough? And so on. Well, we're going to need it. If you want to cure all diseases and reverse aging, we're going to need, probably we're going to need data centers in the space and a lot more because so much data has to be in real time, sort of simulated. And we might get much more efficient doing that as we learned algorithms. So that's one issue. The other is that, as you pointed out, something very important. I mean, this partial reprogramming or total reprogram, they're super exciting, but they don't solve, they don't completely solve the aging problem. They will make your eyes see better for certain periods if you're 80 years old or your skin gets better. But will it work on your heart muscle or on your brain cells, neurons, which is the critical point, because if you can have a perfect body, but if your brain is aging, then, then that's it. So will it modify the sort of the microbiome that has now the environment of an old person? Because if, if that happens, if your metabolism is in old person's metabolism and microbiome is old person's metabolism, and your, your DNA has accumulated a bunch of mutations and mitochondria has bunch of mutations, you can reverse that a bit, have some regenerative capacity, but they will quickly become old again.

Rhonda Patrick: Right.

Derya Unutmaz: You know, because the environment is not, is not great. Right. So like if you live in a bad neighborhood and you created this beautiful house. You know, it's. But it's very bad neighborhood. Your house is not going to last very long there. So your neighbors has to be clean as well. So I think it's a great thing. And that's probably going to add certain years to lifespan and the quality of life, for sure. But we, we have to push that much, much further and then really understand where there's 12 hallmarks. Actually, I asked ChatGPT recently came out with another four or five hallmarks.

Rhonda Patrick: What were they?

Derya Unutmaz: I can't remember exactly. It was. One of them was related to immune system. Just this was recently. But yeah, it was quite interesting trying to remember one had to do with metabolism because we kind of classify hallmarks based on what we can measure and see. And I think AI can see a little bit more than we can. So anyway, this is going to be a serious engineering problem. I would be very surprised if we have like one pill you take and then you suddenly become young again. That seems very unrealistic to me.

Rhonda Patrick: I mean, you know, and then the other question is in the lab, where the way we're delivering these treatments is like an adenovirus, right? And then it's like, well, is that going to cause cancer? Because the adenovirus, is it going to go to the right cell? Exactly. I mean, there's definitely a lot of engineering we have to develop.

Derya Unutmaz: So one of the things that I like doing with AI models is to develop some new methods, new technologies. They have a bit too much guardrail, so they don't allow me to go too deep in it. But, you know, because I don't think we have enough tools. Like, of course we have CRISPR now, but actually Doudna's lab just came out with something even better for bacteria, for genome editing. So imagine there's probably all kinds of other tools that we can build that will make this localization, the editing, much more perfect and has to be programmable. You have to literally create circuits. We can program immune cells in culture. Like we can give a drug, it will shut down their response. Or we can create and. Or gates and not gates. If they see two molecules, then they respond. If they see one they don't like, you can literally program the biology. So we have to develop these new tools that are better than viruses, maybe generate lots of data sets and be able to manipulate the organs and so on. It could be that for some organs, when they're too old, it might be just too difficult to repair them. So you Might consider just putting a new one. It might be a point of no return. Your, your kidneys or whatever. Then you'll have these organ factories, 3D printed. 3D printed. And actually we, we did a lot of collaboration with a colleague of mine. You know, he can print, you know, small tissues, lungs and, and pieces like that. So some of them will be kind of transplanting new organs, some of them would be pre-engineering.

Rhonda Patrick: And then the digital twin, the analysis and simulation will be able to figure out are you going to.

Derya Unutmaz: Yeah.

Rhonda Patrick: Reject this or what do you need to not reject it?

Derya Unutmaz: That's right.

What happens when AI reasons longer about biology?

Rhonda Patrick: Right. What do you think of the new data that came out using this model called GPT-4b micro? GPT-4b micro where I guess there's this model that was used to figure out how to make certain mutations in the four different Yamanaka factors to make them more effective. So they were able to basically 50-fold more be more effective or efficient at increasing this induced pluripotency. How do you interpret that data?

Derya Unutmaz: So I don't think that model is any better than what we have right now. Probably current models are much better. I think probably there might have been two differences and I don't know all the details but one is that they probably removed the guardrails because there's a lot of biosecurity guardrails in the current models. If you ask the Same question to GPT-5.5 it will refuse to do it. It will say, oh, this is a biohazard, like what if you mutate and create a new virus or new cancer, whatever. So that might be one reason. And then the other is like if you let these models think longer. So like GPT-5.5 Pro and the thinking and instant model is the same pre training but pro model can think two hours, thinking can take two minutes. So the longer they can think, the more they can iterate. They can run these scenarios again and again and again. So my speculation is that that model probably ran for a long period of time. Of course you need a lot of compute and a lot of tokens. Not a problem for OpenAI. Then you will probably come up with a solution that even a more intelligent model couldn't come up in a shorter period of time because that particular case is really running experimental scenarios like okay, if I do this mutation, what would be the potential outcome? Like it's running all the simulation. Oh yeah, okay, so what if I change that mutation to here and then what if I add another mutation and running the experiment again and again and again. So you're constantly making the, the solution better and better and better as, as you think longer so, and this will get better. So if you have much more compute, much more intelligence, and you say, okay, GPT 7 or 6, whatever is, go and think for a month, you know, find the perfect molecule that will bind to this receptor and this will cause that. It'll probably figure that out.

The biosecurity dilemma of powerful AI

Rhonda Patrick: What is it? It sounds like we're going to need to do a lot of this type of simulation. And by we, I mean researchers and scientists, what is it going to take to remove some of those guardrails in that environment for researchers to be able to make these new discoveries? And what sort of, I guess, I mean, how do we protect from a new crazy biohazard or biosafety issue?

Derya Unutmaz: Well, I mean, I think like OpenAI is partnering with trusted people, so you have to be approved by them. So I think then whether it's a company or something like that, it's the same problem with cybersecurity. So Anthropic has this new model called Claude Mythos and they decided not to release it because they said it's too dangerous for cybersecurity. Because this model can just crack into any, can find all these things that others cannot see. So in fact, even the government thought that that was important, that they should. I don't know if they're exaggerating if it's true or not, but so you have to put that guardrail if you release it to the world because somebody can use that model and then hack into your bank account or somebody can use it to create a new virus gene or something like that. So I think that will be made individual purses or institution basis that hopefully these AI companies will share that because they might decide not to share it, might say, well, okay, why don't we just develop all the drugs internally and not release any of these models. Some might be doing that, for example. I don't think that would be a good thing because what you really need is, as I said, you need a lot of data. You need a lot of scientists putting all that data into the models, but not only the data, but their experience in a way, let's call it the wild or the world. You're actually training those models. Even if it's super intelligence, it's going to be so hungry for data that you're going to have to collaborate or release it to others. Also, I think this will be important to democratize healthcare because one question everybody asks, okay, well, if you find the treatment for aging this is only going to be available for the super rich. I'm never going to be able to afford, afforded or treatment for cancer. I say the opposite, actually, thanks to AI. It will be super affordable. Because if you can create a drug, like a startup, let's say, can now compete with a big pharmaceutical company, they can find a drug using AI 100 times cheaper. And if you can do the clinical trial using digital twin, that's where all the money goes. You could develop a drug for a couple of million dollars rather than a couple of billion dollars. So the cost of drug development or treatment development will be magnitudes lower, and that will give a huge number of people access to that. But of course, AI has to be shared. I think it's a product of all humanity and it should be the possession of all humanity. That's how I view it.

Rhonda Patrick: Except for going back to the thing that you mentioned at the beginning of this podcast, which is that humans is in the wrong hands. That is the problem, and that is something that needs to be taken very seriously.

Derya Unutmaz: But the solution to that is also AI. So right now I hear that Claude Mythos basically finds all these loopholes in cybersecurity issues that people couldn't figure out for decades. They didn't even know they existed. So it's just patching all those, all these security bugs. So it will create almost a perfect secure systems. Like it will be unhackable because Claude Mythos is actually preventing that. So to prevent that from happening, you still need AI. You might still have some bad actor trying to develop a virus that will cause a pandemic. To prevent that, you also need AI. So the AI should be able to predict it and already create the vaccine ready. We'll say, well, somebody might make this virus, so let's get ready for it. So AI is the solution to all.

Rhonda Patrick: Interesting perspective. You always seem to have a positive outlook.

What should we actually measure to track aging?

Rhonda Patrick: I wanted to ask you another question about. We're talking about these simulations and how we're going to using AI to essentially run these clinical trials cheaper because we're going to do this, you know, these simulations and have, you know, biomarker data, and it'll just be, you know, shorter and cheaper and easier. The question is always, what do you measure? Right? What is the biomarker? What are, what's the end point? Right? And in aging, you can now see, I mean, every study, almost a new study every day coming out looking at these epigenetic aging clocks. And that's, you know, so as most people listening to this podcast know, I've had Steve Horvath on a couple of times. And he's sort of the pioneer in these epigenetic aging clocks. And they've now developed over you know, the last decade or so and become much more of a biological marker of age, like your biological age, not just to be able to predict your actual chronological age. And so you'll find now studies that are looking at treatments and whether or not it can reverse, quote, unquote, reverse biological aging or epigenetic aging. But it's not clear that that's necessarily, you know, if that's really reversing aging. Right. So what do you think from your perspective? What should we be looking at in terms of some of these functional outputs?

Derya Unutmaz: Yeah, I mean, the, those epigenetic markers are very useful, but I don't believe that they are terribly useful as sort of as predicting true aging. I mean, there's a very significant problem with those markers. Usually they're done through blood analysis, but in the blood you have like, you know, I work with T cells, so you have these cells that we call effector cells that have lots of epigenetic change because they differentiate it and they continue to accumulate in old age. And then you have these naive cells that have, you know, more pristine kind. So it's a combination. So depending on what that combination is, is going to affect the output. So you can actually just look at the proportion of your T cell differentiated T cells and you'll probably get the same kind of information. And it doesn't tell you, like, what's happening in the skin or the brain or the heart. You know, it doesn't mean that if the immune cells are getting younger or the young ones are expanding and the old ones are dying. That doesn't mean that your skin is getting younger or your liver is getting younger. So it has a very limited use in my opinion. But we really don't need that because, like, aging is probably the easiest way to measure. We know exactly what goes wrong in, in old age. Right. So like, you can't breathe that well, your heart doesn't work that well. Your muscles don't work very well. You can only, you know, race so much because your weakened muscles or your VO2 max is, is, is lower. These are all phenotypic. Like, you don't even have to probably withdraw a blood. Just measuring the ability of, of an elderly person. Can they walk better, you know, 100 meters than they used to? Like, because that's looking at the total biology, like, you know, your cells, your metabolism or whatever muscle. To me, that's.

Rhonda Patrick: Or Your cognitive abilities, but those can't be simulated.

Derya Unutmaz: I mean, they, they, eventually they can be. Right now they can't, they can't be simulated because as I mentioned, the AI is missing that behavioral, physical intelligence in the real world because that's a, that's. Most things are happening in real life, but I think, I think they can be simulated. But more importantly, I think eventually you have to, whatever the AI comes up with, you need to try it on the humans. Right? So my point is that you don't have to do anything too fancy or wait decades to see the effect. If I give this treatment to, I don't know, 80 year old and they're suddenly able to breathe well, you know, their VO2 max went up, they're sharper, they can think better, they can remember better. You can look at their immune system and we can see that the cells are, we know which cells are younger or worse. Or you can look at their skin like, oh, wow, the skin is getting young. You see it, you don't even have to do anything. So, so there are so many features, phenotypic features of aging that could be objectively measured actually and not just subjectively. You will see the effect very, very quickly. Like this partial reprogramming trial they're doing. It's, it's done for glaucoma patients, I guess, because glaucoma, that happens in old age, right? So your, your cells are aging. So I mean, if these people start to see it works, right, Their cells got regenerated. You don't need to look at their epigenetic. So I think it will be a combination of those measurements. Probably we will come up with, and I will probably come up with this set of biomarkers. I don't think we know because it's going to be a set of biomarkers like, you know, your glucose, your cholesterol might be high when you're 30 and it will be high or low when you're 80. I mean, there's not a very specific marker that will tell you your age, for example, just looking at that. But the combinatorial effect, AI probably will be able to predict your age looking at all kinds of data sets and say, oh, this guy must be 52 years old based on this.

Rhonda Patrick: You know,

How old immune cells distort aging clocks

Rhonda Patrick: I know we have that model clock based, that's looking now at a variety of small molecules that might reverse epigenetic aging. And now there are some data sets showing that you, if you reverse epigenetic aging, there is some functional correlation with some functional improvements like pre frailty things like that, you know, like improve. But at the end of the day, you know, I think it'll be interesting to see if there's going to be companies that come out trying to sell some sort of drug to claiming it reverses aging when they're really just looking at one biomarker, which is reversing.

Derya Unutmaz: It's mostly, as I said, it's mostly the immune aging that they're looking at or sort of maybe getting rid of the terminally differentiated immune cells. Like, for example, in old age, you accumulate these CMV-specific T cells. CMV is a virus that you can't really get rid of. So the immune system constantly have to keep it under check. And those immune cells, they kind of become like missionaries. They should retire, but they keep on expanding. And some individuals might have like 20, 30% of all their T cells just dedicated to like one peptide of this CMV. And they're not helpful, but they become harmful because those guys are old. They should retire. They don't. And they cause inflammation because they're active and, and they don't give place for the young guys to come in. And they are epigenetically closed because they're differentiated. Their telomeres are shorter. So you might be getting rid of some of those cells with certain treatments, which is great, but then you have the indirect effects. If you can control the immune system and inflammation, that's going to have huge effect all over your. That doesn't mean your skin got just regenerated, but it will, it will help

Rhonda Patrick: clean up aging and.

Derya Unutmaz: Yeah, yeah, exactly.

Rhonda Patrick: Also, the other thing I was thinking about is like, you know, you're mentioning VO2 max and you know, muscle strength, muscle mass. We have all these markers that sort of like decrease with age, and yet we don't know necessarily that they cause aging in a way. So the question is, like, will AI be able to take all this correlational data, like we have all this, you know, all these different functional endpoints that we look at and be able to differentiate it from like personalized, you know, this personalized data set versus like actually like, how do you cure aging? Like, what do you change that's going to drive, you know, reverse the aging? I mean, there's a. There's a lot of questions.

Why reversing brain aging is uniquely difficult

Rhonda Patrick: You mentioned something interesting that had to do with the brain. And that is something that I've been thinking about as well because, you know, we have a lot of repair processes in our body, right? We can repair a lot of DNA damage and, you know, mitochondrial function and, you know, all these things. But in the brain we could grow new cells, replace the old cells. In the brain, it's not as robust. There's some parts of the brain that can, you can grow new neurons, neurogenesis, there's neuroplasticity, that's a big part of the repair process in a way. But it's not like a big. You're not totally replacing the brain and you don't want to, as you mentioned, because then memories go away and your identity and it gets very complicated. How do you see AI intervening in that? Like, everything's great. If we can reverse our heart aging and all this, but our brains, that's so important now, is it just going to be a, you know, delay, age related disease, neuroinflammation, all that stuff? We can fix that. But like, are we going to be able to really reverse brain aging?

Derya Unutmaz: You know, I would have to ask AI to figure that out. But you know, I can think of several scenarios how that might happen. First of all, you know, neurons or the brain overall must have some very good maintenance policy, right? So, so there are neurons that live for decades, maybe 70, 80 years. And not just neurons, but there are other cell types that can live for very long. They don't divide very much. There is some regeneration. It's not like zero. And that's very important because that means that if you, let's just do a total experiment, let's just say that you replace 0.01% of your neurons every month or every year or something like that. I don't think that's going to make a huge difference in your brain structure. Because what they're doing is that they're probably, you know, there's some neuron somewhere interacting with a bunch of other neurons, synapses, and then it gets replaced. And the new neurons might have a few other synapses other than that, but that's going to replace that network anyway because they have that capability. So if you do this slowly, I think you won't lose a lot. In fact, we still lose memories, right? So we can't remember everything or we hallucinate all the time. Talk about hallucination. Imagine that this happened to me. No, no, it didn't happen. No, no, I remember that. So that's like brain, brain. Maybe part of it is new neurons that they just didn't know, so they just made it up. Right? So that's one thing. The other thing is that these neurons probably have some internal abilities to regenerate. What I mean by that is that you Know, the cell can maintain itself if it has, you know, sort of a great way to clean up internally. Like autophagy is a very important mechanism, as you know, or it has some really special DNA damage correction ability. Like stem cells have that, right? So pristine stem cells, they don't get old. You know, even in 100 years old, they're still like, like a young person. So. And then you have all these other cells, like glial cells and so on that are there to prevent all the other stuff that happens, the inflammation, you know. Glial cells of course are part of the immune system in a way, but they, they are like the immune system is not allowed into the brain in very rare cases, it's like a protected area because the immune system causes too much damage. And if you can't replace it quickly, that's, that's a huge problem. But they have their own network of cleaning up and they probably have some sort of like a lymphatic system and so on. So if we can figure that out, or if AI can figure that out, we might be able to really maybe not completely regenerate, but extend it quite significantly, maybe another 10, 10 years, 20 years, 30 years, whatever. And then we might come to a point and this goes into a little bit of a science fiction now, you know, let's say in 50 years time, AI might be able to figure out all of the synaptic connections in your brain, like every single neural network and the neurotransmitters and everything else. So eventually might be able to like literally simulate your, your brain, you go into the matrix level. So that might allow AI to like say, okay, I'm going to replace all these neurons, but I'm going to make sure that they reconnect all these synapses so that you don't lose your identity. Or alternately, I can keep a copy here and then we can create a new brain and then transfer it to that new brain, that exact state that I found. I'm not saying that this is possible right now. That's really science fiction era. But you can imagine that it's some point we might get to that level. So I'm not too worried. I think if you can pass this couple of decades and then keep the brain healthy and self preserving for maybe age 100, 120, 130. And in fact, people actually who live to age 100, they have very sharp minds, right? Because if you don't have sharp mind, you don't live very old. So that's like super correlated. So if you can keep it For a couple of more decades and we'll probably find some other solutions.

Rhonda Patrick: So if we can, if we can keep the neuroinflammation low, if we can increase brain-derived neurotrophic factor, some of these things that we know does play a role in improving neuroplasticity and, you know, and growing new neurons and to do all the things that we can, at least in some predictable way.

Derya Unutmaz: And we can have like chips for the, for the memory part, you know, we could always supplement that. So.

Rhonda Patrick: Yeah, increase the capacity and hopefully AI will help us figure out how to deliver these therapies to the brain.

Derya Unutmaz: Yeah, delivery is always the biggest problem.

Rhonda Patrick: Right.

The ultimate prompt for extending lifespan

Rhonda Patrick: Well, this has been such a fascinating and exciting conversation. Derya. I have a couple of more questions, closing questions for you, and I really kind of was just wanting to know if you had access, let's say there was no guard rails and you had access to all this data in aging biology. You know, the T cell, you know, all the T cell repertoire, long, you know, longitudinal, longitudinal, longitudinal cohorts, centenarian data, like everything, just anything you can imagine. You had it all. And you had this model that was amazing that you could.

Derya Unutmaz: You're describing heaven for me.

Rhonda Patrick: Yes, yes. What would be the prompt? What would be the question you would ask it? I mean, there'd be more than one, but would be the first.

Derya Unutmaz: Yeah. Hoping that the AI won't answer 42 as an answer. So the first thing I would probably ask is not saying that, just go figure out aging or whatever, because I think there has to be, there has to be certain sequence. So imagine that you have all this data. What would be the most practical, quickest way you can develop an intervention to an elderly person, say, age 70, 80 years old, that will immediately add five years to their lifespan? So to me, that would be the most critical, immediate question to ask because that population doesn't have a lot of time. And so we have to develop these technologies extremely quickly and should have even two years, three years extend so that I can come up with the next prompt after that. So I guess that would be the, the first prompt I would ask.

Rhonda Patrick: That's great.

What data does a true digital twin need?

Rhonda Patrick: Okay. There's another question. So this one is there's no money. Money's no object. Okay. There's no, like, you have complete, like, access.

Derya Unutmaz: You're describing so many heavens now.

Rhonda Patrick: I know, I'm just, I'm curious what your answer is. You're going to personally build your own digital twin, which I plan to right now. What test would you prioritize? Like what data sets would you prioritize? How can a person get them? How often would you take these tests? How would you organize this information into the AI to really get the biggest bang, you know, benefit from the information it's going to give you.

Derya Unutmaz: Right, but you said money is not.

Rhonda Patrick: Money's not an issue. Right, okay, money's not an issue.

Derya Unutmaz: So, so I would divide it into two parts. One part is that we have to. So what I would do is set up a huge lab, you know, partially automated lab, where I would generate enormous amount of data on the cells, on the tissues in the lab. Because we have to go by the first principles to understand what's going on. Let's say in an individual T cell, all these thousands of proteins, metabolites, what are they doing then that will enable me to create what's called the virtual cells and then eventually virtual tissues and your half cells are in a special temporal manner, are behaving and so on. So that would probably be the most expensive part of it. And I'll need a lot of money. You said no limit. Right? Okay. But the second part would be sort of what we talked earlier, kind of the behavioral data from the humans. And that data is not just, of course, all kinds of plasma levels of proteins, metabolites, your full microbiome, your full genome sequencing, and all of these things are possible, by the way, if the cost is not an issue. You can easily, like UK Biobank has done it for 500,000 people, you can do it for million people. And I think if you did in a million people, that would pretty much cover all the possible humanity. I mean, it's not like everybody's perfectly different. We share a lot of things. And so from the humans collect lots of biological data, but very importantly, behavioral data. I think this is something that's totally missing in a digital twin, like we were talking earlier, ability of someone to walk certain distance, ability to raise some weights. These don't show up in any biomarker sets, but they could be extremely important or ability to, to think, you know, their, their cognitive level, that, that could be directly brain, brain aging related. And I mean lots of things. And you know, what happens when humans are in certain environments. You know, in certain environments, you, even if you, if you are having a very sort of healthy lifestyle, that may not help you much. For example, you know, I lived in New York City for a decade. You know, my stress level was so high, and that stress level is so harmful for you because the immune system is constantly thinking there's a threat out There and then it's causing a lot of inflammation. In fact, I think people who live in New York has twice as much heart attack risk or something like that. You know, that your environment, your emotional states and how you interact with other people, all of these things will impact your aging process, your. Your resilience to the life, your optimistic level. By the way, being optimistic is one of the best things you can do for, for aging. And study after study show that. So being able to absorb bad things that happen to you and then keep, keep going. So resilience. So but these are behavioral data that's not available in, in the biological set. So, yeah, I would do that for a million people all over the world, different parts. And then on the lab, every single cell type that I can find, decode those, put them all together to the super intelligence, and voila, we have digital twin.

How to build a mini digital twin today

Rhonda Patrick: Okay, Derya. So let's say someone wants to build their little mini digital twin right now using the models we have access to today, the type of data that we can aggregate at the consumer level today. Biometric data that we can, that we can put in. How would you build that mini digital twin today?

Derya Unutmaz: Yeah, great question. I mean, in fact, it is possible to build sort of a mini digital twin that doesn't have to be as sophisticated as I described because that one is more sort of clinical trials and developing treatments. But going back to the example of the UK Biobank, they didn't have trillions of data sets. They only used a few hundred data points from each person and they were able to predict a lot of diseases. So that means that we can have a lot of predictive power with the data that we're collecting today. Another example is this glucose meter that I have. You know, every five minutes it shows my glucose level and then I take that data and of course I put it to ChatGPT and once you add additional data set, that becomes very, very valuable because let's say that you have your lab values, your cholesterol, your glucose, your everyday, the steps that you took and your sleep and so on. So these are actually very rich data on their own because they're accumulation of lots of under biology that results in that. But also that puts AI into a context, your mini digital twin. So my suggestion would be to provide the AI as much data as they can and on a daily basis and keep it in the same context so same window so the model can remember that. Actually there are some tricks to do that as well. You can keep it as like a database and tell the AI model, go check my database and see what my new, based on my new data, how things have changed, what suggestions you could give. I for example, provide all the supplements that I take, you know, the type of food that I eat, all of these things will make, will make a big difference. So the model start to really personalize, you know, sort of the style. It will know your style and will make suggestions for you rather than giving blanket statement like you should walk 10,000 steps. Well, you know, knows that Derya cannot walk 10,000 steps every day, but I think 3,000 would be enough for him.

Rhonda Patrick: And what kind of model are we talking about? Would you be using the GPT-5.5 Pro? And then what about these agents and Codex and how does that come into helping analyze that database that you're creating?

Derya Unutmaz: Yeah, I think these models are becoming more agentic all the time. I know OpenAI, for example, they integrated agents into their Codex model, the coding model, and soon I'm sure it will be part of all of ChatGPT. I don't think you need very sophisticated models for that. What is important is that really maintaining that context. So hopefully the models will have a larger memory and they can remember. So ChatGPT can keep certain memories about you, but it's still kind of limited. It's not just ChatGPT. Like you can use Gemini for example, which has a longer context windows or Claude for that matter. I think most of the models can handle that information. They don't have problem dealing with large data sets. As I mentioned, I can put millions of data sets and they're able to analyze that. What they need is that they need to remember how things were a month ago because that's before and after. Before and after is extremely valuable. So the model will know he started taking vitamin D3 oh, these things changed after that that you may not notice or is glucose looks better because of, you know, when that's that change happened. So it starts to make those links. And that's I think the critical point because you need all of that context in the AI model to give you a sort of a better prediction on what to use and what not to use. Okay, you were using that. Well, maybe that was not a great idea. So change it or change the dose or whatnot.

How to give AI a long-term memory of your data

Rhonda Patrick: Yeah, that's interesting. It kind of reminded me of a question that I did want to ask you about these AI models and future AI advances. When you think about these qualities. So like persistent memory, expanded context handling, it seems like those seem to be more important.

Derya Unutmaz: Absolutely. I think for me, memory which brings the context. So the models are now able to think for quite long time and they don't. Because previously the models would just, even in the same context window, if you had a million context windows, after a while they would just fall off because they would forget even what they were thinking about. Now they have this ability to constantly go and check on it. So I think in the next few months this is going to happen. So that, that will, that will have a tremendous impact.

Rhonda Patrick: Oh, that's.

Derya Unutmaz: Memory is everything.

Rhonda Patrick: So, so you think. So how long are we talking? Like let's say, you know, you started a vitamin D supplement six months ago, put that you have the same window and you start in that window, you have that, you know, entry point that the date. And then you keep adding about, you know, you add your data in. It's got all the data right now. Can it go back that far or how far can it go back?

Derya Unutmaz: And if you have that data somewhere in your database. For example, I adapted a technique that Karpathy, who's a famous AI researcher described so you can create your own wiki, sort of Wikipedia, kind of a thing like personal. If you have all your data somewhere, you can ask AI, just pull all that and put it into a Wikipedia, like you can do it daily or weekly depending on the environment, whatever. And so now you're building your own database, health database, which AI can help you update it. If you have that data, it can go years, doesn't matter. Like you can have 10 years of data, it will analyze all of that,

Rhonda Patrick: but it has that memory. It can like.

Derya Unutmaz: Yeah. So in the same context, if you provide all of that, I mean it's still limited with you know, maybe a million tokens or something, but no one's going to have million token data set even if you, if you calculate 10 years, so that's not a problem. The problem is like, if you want this to be continuous, like you just give AI, okay, here's the data today that it should be able to remember what was yesterday, what was two months ago. So you don't have to give, you know, all of the, you don't have to keep your own database and give all that again and again because you have to do that every time. Right. So the whole, your whole, and that will spend a lot of tokens and stuff like that. So, but, but I think this is, this is going to be, this is going to be solved.

Why personal baselines matter for AI advice

Rhonda Patrick: How do you not bias, how do you lower the, the ability of yourself to bias? What GPT-5.5 Pro is going to feed you back based on what you're asking it? I find sometimes I might be able to bias it a little bit. Do you know what I'm talking about?

Derya Unutmaz: Sure. That's why I think we are in sort of the experimental phase in a way. Everyone has to do their own kind of validation as the models are getting better. What I mean by that is that again, you know, of course, don't try harmful things and then, you know, don't go into risk. But you know, for daily, daily use you might be taking vitamin D and then you stop taking vitamin D so that you're just doing an experiment like before and after and then you collect that data before and after and then AI gives you one solution, says well, you know, taking this dose of vitamin D I think is important, so then you can start that dose again and then see, see what happens if, if you reach the same level as before means that AI made a good prediction like you need to see after, you have to have that record before and after so that you, you are the judge. Well, what, this was a good idea. So I'm glad that I listened to ChatGPT. Well, if it wasn't a good idea, it didn't kill you, it didn't make you sick. So that's, that's also fine, right?

Rhonda Patrick: Yeah, I guess for someone that's already taking a lot of supplements, for example, they're not going to have that before and after. Then also you have to know, like, how long do you wait, you know, for example, to, for the washout period?

Derya Unutmaz: And yeah, the hope is that if you provide that very frequently. In fact, I can mention one thing. For example, the, the lab values, like you go and measure your cholesterol, glucose, sodium, whatever, they always give you a range. Right? So if it's within this range, it's normal. Well, how do you know that? Because you can be at the top of the range. That might be your abnormal. Somebody else's normal. Somebody might be a little bit over the normal and might still be okay. Or vice versa, because we don't know the level on a personalized level. So we calculate population based. Okay. So this range is good for this population. So in a way, if you have three or four measurements, let's say every few months, you can develop your own set point normal. You know, the AI will know your normal for glucose is 90, not 70, not 100 or not 105. Somebody else might be 102. So it knows that based on that. That measurements. So then. Then it starts to give you advice based on your data set your set points. Because if yours is 100 and suddenly dropped to 70, maybe that's not a good thing. I'm just giving an example. So that's why that continuous data collection is so important. With glucose meter, I collect it every five minutes. The more data, the better.

Outro

Rhonda Patrick: Well, Derya, thank you so much for sitting down with me today and talking about this exciting, I mean, frontier that we're exploring. You know, curing disease, extending human life expectancy, obviously, health span, reversing aging, perhaps getting to Human 2.0 where we're enhancing, you know, genetic, you know, features as well. Very exciting time to be in. And if we cannot die in the next 10 to 15 years. Yes, it may be even more exciting.

Derya Unutmaz: Yes, yes, absolutely. Because the last thing I will say, this is so unique in human history because a decade ago, if you said someone, well, you should be very healthy, do this, do that, they can say, well, it's only going to extend my life, maybe two years or three years. I just want to live my life and I don't care about living a few more years as an old age. And that was perfectly relevant. That's not the case now. Living an extra one year could make you reach that threshold where there's going to be the ability to treat many diseases and reverse your aging and give you another decade, give you another 20 years. And then once you reach that, you get another 10 years, another. Like even every day counts now, in my opinion. So that's why don't die.

Rhonda Patrick: Well, people can find out more about your research and they can follow you. I follow you on X. Maybe you can tell people how to follow you, what your user, your Twitter follower, sorry, your X user handle is, and where else they can find you.

Derya Unutmaz: Yeah, my main account is on X. It's @DeryaTR_. If they write Derya Unutmaz, I think I'll show up. That's where I do most of My communication. I have a LinkedIn account, but I don't post that often there. I've been planning to start up sort of a YouTube channel, but I don't think I'll ever do that because I'll never have the time. You know, it's really amazing what you're doing because video takes a lot of. A lot of effort. So for me, the fastest way. In fact, I even had a substack account, but just couldn't find the time to write long messages. So X is the best way.

Rhonda Patrick: Well, I really encourage people to follow you on X. You post. I mean, just every day there's something interesting that you're posting on X. And so I highly recommend that people do follow you.

Derya Unutmaz: Thank you.

Rhonda Patrick: As many already do. So thanks again for the research you're doing and for. I'm excited to see what's going to happen in the next couple of months.

Derya Unutmaz: Looking forward to it. Very optimistic. Thank you. Thank you very much. It was great.