Author: brewbooks

Hiking Horseshoe Canyon 15 April 2023

I hiked into Horseshoe Canyon with my friends Bill, Peter, and Kurt on 15 April 2023. We aimed to see the Barrier Canyon-style pictographs on the canyon walls. We arrived at the remote Horseshoe Canyon unit of Canyonlands National Park the night before. We were able to camp very near the trailhead.

Camp at Horsehoe Canyon
A nice place to camp

We met Ranger Jared at the trailhead for a guided walk. Bill had previously called and found there were ranger-guided tours; this was an excellent idea.

Meeting our Ranger Guide
Ranger Jared

One of the first things Jared pointed out was a dinosaur track.

Dinosaur Print

We descended about 150 meters (500 feet) into Horseshoe Canyon during the cool morning. The trail was well maintained; this is a moderate hike. One caution is that an early start would be wise in the summer months as hiking back up in the afternoon sun would be some hot work.

Barrier Creek
We crossed Barrier Creek several times

We saw four separate pictograph sites. First up was the High Panel, tucked into a small area among trees, a bit off the main trail. These pictographs were high off the ground. A short walk across the canyon, perhaps ten minutes, led to the Horseshoe Panel of pictographs was intriguing. I wondered what the artist meant to communicate with the trapezoidal figures in the panel. I had seen petroglyphs before, but this trip was my first exposure to pictographs; there was a lot to ponder.

Horseshoe  Panel Pictographs
Horseshoe Panel Pictographs

After some time at Horseshoe Panel, we headed to the Alcove Panel.

Alcove Panel Pictographs

We noticed the acoustics were interesting; we wondered what ceremonies were associated with the pictographs. Some epic tales, the equal of the Iliad in the Western tradition, might have been told at these sites.

Hiking along Barrier Creek

Next, our group trekked about a mile to the Great Gallery. 

The approach opened up to the initial view of the Great Gallery.

Approach to the Great Gallery Pictographs

The pictographs spread over a 20-meter (60-foot) expanse of rock tucked under the cliff; this was the most complex set I’d seen. There was a repeated motif of trapezoidal figures. In this gallery, some of the darker figures had lighter shadows next to them, perhaps like the soul of the darker figures. The panel had more miniature figures; I considered them humans among the gods.

Great Gallery Pictographs

The mysterious “Holy Ghost” section left me wondering what it might mean.

Great Gallery Pictographs

We had lunch on some benches that let us gaze at the Great Gallery and contemplate this great art. Afterward, we wandered up the canyon toward our camp.

Leaving Horseshoe Canyon

Along the way, I spotted a butterfly near Barrier Creek. I spent a good five minutes chasing it down.

Mourning Cloak Butterfly

It was a Mourning Cloak butterfly, a common species I had seen in my home state of Washington. When I posted this observation on iNaturalist, I found that Nymphalis antiopa has a wide range across the Northern Hemisphere. Whether common or rare, it was still worth chasing a butterfly.

While taking a break before ascending to camp, I talked to a couple who are volunteers at the park. They had seen an unusual wildflower, a paintbrush species, on the opposite rim of the canyon. They gave me directions, and I was off on a botanical boondoggle. The hiking up to the opposite rim was more challenging.

Hike down the far side of Horseshoe Canyon

I made it to the top and found the flower, a Rough Paintbrush ( Castilleja scabrida).

Castilleja (Paintbrush)

I decided to head along the trail on this side of the canyon for about 20 minutes; the payoff was a great view of Sugarloaf Butte with the Henry Mountains in the far distance.

View from Horseshoe Canyon Rim

We had brought radios, and I could contact my friends at our camp on the opposite rim. As I headed down, I had a great view of Horseshoe Canyon. After an hour, I returned to camp and settled in for dinner. It was a fine day of hiking. As a bonus, we had some excellent star gazing in the evening. 

Book review of Outlive: The Science and Art of Longevity by Peter Attia

Let me begin my review in the middle of Outlive. The author  asks us to list the ten tasks we want to do for the rest of our lives. He calls this list the centenarian decathlon. Here’s the top of the list for me: hike up to Third Burroughs Mountain. It’s 9 miles (14 km) in Mount Rainier National Park with 2500 feet (760 m.) of elevation gain. Why? I’m a hiker, and this is my favorite hike worldwide.

Up at Third Burroughs
Early morning at Third Burroughs 2003

I’ve spent a fair amount of time thinking about how to keep hiking as I get older. I turned 65 in 2022; I would like to keep exploring mountains as long as possible, this is just the book to help me achieve my goal. Let me explain why.

First, Attia starts with the concept of healthspan – how well you live. There’s a tight coupling between healthspan and lifespan. As we age, we have left less of each. One difference is that lifespan is a discrete quantity; one day, you are alive, and the next, you are not. In contrast, our healthspan gradually diminishes over time. The author details three vectors (components) of healthspan: physical, cognitive, and emotional. The good news is that we can usually improve these components and our overall healthspan. How we do so is the core of the book.

The book’s first part outlines our current situation and a target goal. The most important lesson I learned: “Tactics without strategy is the noise before defeat.” a quote from Sun Tzu, an ancient Chinese military strategist. Been there, done that, got the T-shirt. So, how can I do better? The author has a great framework: first, objectives, then strategy, and finally, tactics. The author trained as an engineer, became a physician, and has worked in business consulting; his background shows throughout the book. I touched on objectives in the discussion of the centenarian decathlon; how about strategy?

The second part of Outlive is the science that can help you develop a strategy. There is a chapter on the science of centenarians; I think of this as a boundary condition. What are the factors that helped get someone to their 100th birthday? (I have a hiking friend who still gets out on walks at 101, I want to follow in her footsteps.) Next is a chapter on the details of how nutrition affects longevity. The last four chapters cover the science of how most of us die: metabolic disorders such as diabetes, heart disease, cancer, and neurodegenerative diseases. Understanding these problems will help you develop tactics to mitigate some issues. There are no magic bullets in these chapters; instead, it’s a well-researched survey of what we know as of 2022. Now that we know objectives and strategies, what tactics can we employ?

The final part of Outlive lays out four tactics: 

  1. Exercise (cardio, strength, and stability)
  2. Nutrition
  3. Sleep 
  4. Emotional health.  

At 260 pages, this is the longest part of the book. It was detailed and beneficial to me. Rather than outline each section, let me list some tactics I am adding to my strategy: 

  1. Work on stability, specifically starting with a yoga class. 
  2. Use a continuous glucose monitor for a few months to optimize my diet. 
  3. Ensure I am getting enough protein intake of lysine, leucine, and methionine.

The last chapter on emotional health was the most impactful in the book. Attia opens up to the reader about his emotional health through the lens of a patient rather than a physician. It touched me deeply; I had some trauma in my teen years when my mom died. Fifty years later, I realized I should address some of these issues rather than wall them off. 

Outlive is a book I will read several times. The book is challenging; I spent four weeks reading the book.

Reading Outlive in Utah
Reading in camp at Grand Staircase-Escalante National Monument, Utah

I made a ton of margin notes and back-of-the-book scrawling. There’s a lot to digest, and there are many references. For example, I want to read the paper Hallmarks of Aging by Carlos López-Otín and colleagues. This book catalyzed some great conversations with my friend Bill about healthspan. I will recommend Outlive to anyone interested in taking action to improve their healthspan.  

One closing thought; there’s a missing chapter in the book. I believe social interaction and engagement can improve healthspan’s cognitive and emotional components. My experience is that forty years of marriage have improved my emotional health. I decided to ask ChatGPT: What studies have shown that social interaction and engagement can improve cognitive function and reduce the risk of cognitive decline and dementia in older adults? Here’s the answer: 

“There have been several studies that have shown a positive correlation between social interaction and cognitive function in older adults. For example:

The Rush Memory and Aging Project: This study found that older adults who had higher levels of social activity experienced a slower rate of cognitive decline than those who were less socially active.

The MacArthur Study of Successful Aging: This study found that older adults who were more socially engaged were less likely to experience declines in cognitive function over time.

The Women’s Health Initiative Memory Study: This study found that women who reported higher levels of social engagement had a lower risk of developing cognitive impairment than those who were less socially engaged.

Overall, these studies suggest that social interaction and engagement can play an important role in maintaining cognitive function and reducing the risk of cognitive decline and dementia in older adults.”

Transcript of the first Lex Fridman Interview with Max Tegmark

Transcript of the first Lex Fridman Interview with Max Tegmark

{The following is my best attempt at an edited transcript of Lex Fridman’s first podcast with Max Tegmark on 26 August 2018. I learned quite a bit from this interview and will post my lessons learned separately. My goal in doing this transcript is to provide a usable transcript for others. Please let me know if you find errors, I will correct them. A few notes: LF = Lex Fridman, MT = Max Tegmark, content enclosed in braces {} was a clarification I added.}

{Lex introduces MIT course 6.099 Artificial General Intelligence and Max Tegmark}

First, “Our Mathematical Universe {: My Quest for the Ultimate Nature of Reality}” and second is “Life 3.0: {Being Human in the Age of Artificial Intelligence.}” He is truly an out of the box thinker and fun personality so I really enjoyed talking to him. {LF talks about the course and his social media}

LF – Go read Chapter 7 of his book, On Goals, is my favorite. It’s really where philosophy and engineering come together and it opens with a quote from Dostoevsky: “The mystery of human existence lies not in just staying alive, but in finding something to live for.” [ from “The Brothers Karamazov” (1879)}

{ Lex talks about some audio difficulties due to Radio Frequency Interference }

LF – Do you think there is intelligent life out there in the universe? Let’s open up with an easy question.

MT – I have a minority view here actually. When I give public lectures, I often ask for a show of hands. Who thinks there’s intelligent life out there somewhere else? And almost everyone put their hands up and when I ask why they’ll be like, oh, there’s so many galaxies out there, there’s gotta be. But I’m a numbers nerd. Right? So when you look more carefully at it, it’s not so clear at all. When we talk about our universe. First of all, we don’t mean all of space, we actually mean, I don’t know, you can throw me in the universe if you want behind you there It’s, we simply mean,  the spherical region of space from which light has a time to reach us so far 

during the 14.8 billion years, 13.8 billion years since the Big Bang, there’s more space here. But this is what we call the universe because that’s all we have access to. So is there intelligent life here? That’s gotten to the point of building telescopes and computers? My guess is no actually. the probability of it happening on any given planet. There’s some number.

We don’t know what it is and what we do know is that the number can’t be super high because there’s over a billion Earth-like planets in the Milky Way Galaxy alone, many of which are billions of years older than earth. And aside from some UFO believers, you know, there isn’t much evidence that and the super advanced civilization has come here at all. And so that’s the famous Fermi paradox, right? And then if you if you work the numbers, what you find is that the if you have no clue what the probability is of getting life on a given planet. So it could be 10 to the minus 10 {10^-10} or 10 to  minus 20 {10^-20} or 10 to minus two{10^-2} . Any power of 10 is sort of equally likely if you want to be really open minded, that translates into it being equally likely that our nearest neighbor Is 10 to the 16 {10^16} meters away, 10 to the 17 {10^17} meter s away, 10 to the 18 {10^18}. By the time he gets much less than 10 to the 16 {10^16} already, we pretty much know there is nothing else that’s close. And when you get beyond….

LF – Because they would have discovered us

MT – They, yeah, they would have been discovered as long or if they’re really close, we would have probably noted some engineering projects that they’re doing. And if it’s beyond10 to the 26 {10^26} meters  that’s already outside of here {the known universe that is 13.8 billion years old}. So my guess is actually that there are, we are the only life in here that’s gotten the point of building advanced tech, which I think is very ….  puts a lot of responsibility on our shoulders, not to screw up. 

LF – I see.

MT – You know, I think people who take for granted that it’s okay for us to screw up have an accidental nuclear war go extinct somehow because there’s a sort of Star Trek like situation out there with some other life forms are going to come and bail us out and it doesn’t matter what I think lulling us into a false sense of security. I think it’s much more prudent to say, let’s be really grateful for this amazing opportunity we’ve had and uh, make the best of it just in case it is down to us. 

LF –  So from a physics perspective do you think intelligent life? So it’s unique from a sort of statistical view of the size of the universe, but from the basic matter of the universe, how difficult is it for intelligent life to come about? The kind of advanced tech building life? It is implied in your statement that it’s really difficult to create something like a human species.

MT – Well, I think, I think what we know is that going from no life to having life that can do our level of tech? There’s some sort of  …. to going beyond that and actually settling our whole universe with life. There’s some road, major roadblock there, which is some great filter as it’s just sometimes called which is tough to get through. It’s either that that roadblock is either behind us or in front of us. I’m hoping very much that it’s behind us. I’m super excited every time we get a new report from NASA saying they failed to find any life on Mars, like just awesome because that suggests that the hard part, maybe maybe it was getting the first ribosome or or some some very low level kind of stepping stone. So there we’re home free because if that’s true, then the future is really only limited by our own imagination would be much suckier if it turns out that this level of life is kind of a dime a dozen. But maybe there’s some other problem, like as soon as a civilization gets advanced technology within 100 years, they get into some stupid fight with themselves and poof! Now, that would be a bummer.

LF –  Yeah, So you’ve explored the mysteries of the universe, the cosmological universe, the one that’s between us today. I think you have also begun to explore the other universe, which is sort of the mystery, the mysterious universe of the mind of intelligence, of intelligent life. So is there a common thread between your interest or in the way you think about space and intelligence?

MT –  Oh yeah. When I was a teenager,I was already very fascinated by the biggest questions and I felt that the two biggest mysteries of all in science were our universe out there and our universe in here {pointing to the head}. 

So it’s quite natural after having spent a quarter of a century of my career thinking a lot about this one {universe out there} now, indulging in the luxury of doing research on this one {universe in here}. It’s just so cool. I feel the time is right now for greatly deepening our understanding of this,

LF –  Just start exploring this one {universe in here}.

MT –  Because I think a lot of people view intelligence as something mysterious that can only exist in biological organisms like us and therefore dismiss all talk about artificial general intelligence is science fiction. But from my perspective, as a physicist, you know, I am a blob of quarks and electrons moving around in a certain pattern processing information in certain ways. And this {a water bottle} is also a blob of quarks and electrons. 

I’m not smarter than the water bottle because I’m made of different kind of quarks. I’m made of up quarks and down quarks, exact same kind as this. There’s no secret sauce I think in me. It’s all about the pattern of the information processing and this means that  there’s no law of physics saying that we can’t create technology which can help us by being incredibly intelligent and help us crack mysteries that we couldn’t. In other words, I think we’ve really only seen the tip of the intelligence iceberg so far.

LF –  Yeah, so the perceptronium  

MT – Yeah

LF – So you coined this amazing term. It’s a hypothetical state of matter, sort of thinking from a physics perspective, what is the kind of matter that can help, as you’re saying,  subjective experience emerges, consciousness emerge. So how do you think about consciousness from this physics perspective?

MT – Very good question. So, again, I think many people have underestimated our ability to make progress on this by convincing themselves it’s hopeless because somehow we’re missing some ingredient that we need. There’s some new consciousness particle or whatever.  I happen to think that we’re not missing anything. The interesting thing about consciousness that gives us this amazing subjective experience of colors and sounds and emotions and so on is rather something at the higher level about the patterns of information processing. And that’s why  I like to think about this idea of perceptronium: what does it mean for an arbitrary physical system to be conscious in terms of what its particles are doing or or its information is doing. I don’t think;  I hate carbon chauvinism. You know, this attitude, you have to be made of carbon atoms to be smart or or conscious

LF –  So something about the information processing this kind of matter performs. 

MT –  Yeah and you know, you can see I have my favorite equations here describing various fundamental aspects of the world. I feel that,  I think one day maybe someone who’s watching this will come up with the equations that information processing has to satisfy to be conscious. I’m quite convinced there is a big discovery to be made there because let’s face it some we know that some information processing is conscious because we are conscious.

LF – Yeah.

MT –  But we also know that a lot of information processing is not conscious. Like most of the information processing happening in your brain right now is not conscious. There’s like 10 megabytes {MB}  per second coming in and even just through your visual system you’re not conscious about your heartbeat regulation or most things. Even if I just ask you to like read what it says here, you look at it and then oh now you know what it said, you’re not aware of how the computation actually happened. You’re like,  your consciousness is like, the CEO that got an email at the end with the final answer. So what is it that makes a difference? I think that’s  both a great science mystery. We’re actually studying it a little bit in my lab here at MIT . But also I think it’s just a really urgent question to answer.

For starters, I mean if you’re an emergency room doctor and you have an unresponsive patient coming in wouldn’t it be great if in addition to having a CT Scanner you had a consciousness scanner that could figure out whether this person is actually having locked-in syndrome or is actually comatose.  And in the future imagine if we build robots or the machine that we can have really good conversations with. I think it’s very likely to happen, right? Wouldn’t you want to know like if your home helper robot is actually experiencing anything or just like a zombie would you prefer? What would you prefer? Would you prefer that it’s actually unconscious so that you don’t have to feel guilty about switching it off or giving it boring chores. What would you prefer?

LF – Well that certainly we would prefer, I would prefer the appearance of consciousness. But the question is whether the appearance of consciousness is different than consciousness itself and sort of asked that as a question do you think we need to you know understand what consciousness is, solve the hard problem of consciousness in order to build something  like an AGI  system.

MT –  No, I don’t think that. I think we’ll probably be able to build things even if we don’t answer that question but if we want to make sure that what happens is a good thing we better solve it first. So it’s a wonderful controversy you’re raising there where you have basically three points of view about the hard problem. There are two different points of view, they both conclude that the hard problem of consciousness is BS. On one hand you have some people like Daniel Dennett saying that our consciousness is just BS because consciousness is the same thing as intelligence, there’s no difference. So anything which acts conscious is conscious just like we are. And then there are also a lot of people including many top AI researchers I know who say I have consciousness just bullshit because of course machines can never be conscious, right? They’re always going to be zombies. Never have to feel guilty about how you treat them. 

And then there’s a third group of people including Giulio Tononi for example and another and Christof Koch and a number of others. I would put myself also in this middle camp who say that actually some information processing is conscious and some is not. So let’s find the equation which can be used to determine which it is. 

And I think we’ve just been a little bit lazy, kind of running away from this problem for a long time. It’s been almost taboo to even mention the “C Word”  {consciousness] in a lot of circles  but we should stop making excuses. This is a science question. And  there are ways we can even test any theory that makes predictions for this and coming back to this helper robot. I mean so you said you would want to help a robot that certainly act conscious and treat you like ….  you have conversations with you and I think. But wouldn’t you, would you feel when you feel a little bit creeped out if you realize that it was just a glossed up tape recorder. You know there was just a zombie and was faking emotion. Would you prefer that it actually had an experience or or would you prefer that it’s actually not experiencing anything? So you feel you don’t have to feel guilty about what you do to it.

LF –  It’s such a difficult question because you know, it’s like when you’re in a relationship and you say, well I love you and the other person that I love you back. It’s like asking, oh do they really love you back or are they just saying they love you back?  Don’t you really want them to actually love you back. It’s hard to really know the difference between  everything seeming like there’s consciousness present, there’s intelligence present, there is affection, passion, love and it actually being there. I’m not sure. Do you have … 

MT – But let me ask you, can I ask you a question just like to make it a bit more pointed to Mass {Massachusetts}  General Hospital is right across the river right? Suppose suppose you’re going in for a medical procedure and they’re like, you know  for anesthesia, what we’re gonna do is we’re gonna give you a muscle relaxants so you won’t be able to move and you’re gonna feel excruciating pain during the whole surgery, but you won’t be able to do anything about it. But then we’re going to give you this drug that erases your memory of it. Would you be cool about that? What’s the difference that you’re conscious about it or not? If there’s no behavioral change? Right.

LF –  Right. That’s a really clear way to put it. That’s yeah, it feels like in that sense experiencing it is a valuable quality. So actually being able to have subjective experiences, at least in that case, is valuable.

MT –  And I think we humans have a little bit of a bad track record also of making these self serving arguments that other entities aren’t conscious. You know, people often say all these animals can’t feel pain. It’s okay to boil lobsters because we asked them if it hurt and they didn’t say anything. And now there was just the paper out saying lobsters do feel pain when you boil them in their bounding in Switzerland. And we did this with slaves too often and said, oh, they don’t mind, they don’t maybe aren’t conscious or women don’t have souls or whatever. So I’m a little bit nervous when I hear people just take as an axiom that machines can’t have experience ever. I think this is just a really fascinating science, the question is what it is?  Let’s research it and try to figure out what it is that makes the difference between unconscious intelligence behavior and conscious intelligent behavior.

LF – So in terms of so if you think of Boston Dynamics, humanoid robot,  being sort of with a broom being pushed around it starts pushing on his consciousness question. So let me ask, do you think an AGI system like a few neuroscientists believe  needs to have a physical embodiment, needs to have a body or something like a body?

MT –  No, I don’t think so. You mean to have to have a conscious experience

LF –   To have consciousness?

MT – I do think it helps a lot to have a physical embodiment to learn the kind of things about the world that are important to us humans for sure. But I don’t think the physical embodiment is necessary after you’ve learned it, just have the experience. Think about when you’re dreaming right, your eyes are closed, you’re not getting any sensory input, you’re not behaving or moving in any way, but there’s still an experience there. Right? And so clearly the experience that you have when you see something cool in your dreams isn’t coming from your eyes, it’s just the information processing itself in your brain which is that experience, right?

LF –  But if I put another way I’ll say that because it comes from neuroscience is the reason you want to have a body in a physical, something like a physical like, you know a physical system is because you want to be able to preserve something. In order to have a self you could argue: Would you need to have some kind of embodiment of self to want to preserve?

MT –  Well now we’re getting a little bit anthropomorphic, anthropomorphizing things maybe, talking about  self-preservation instincts. I mean we are evolved organisms. Right?

LF –  Right. 

MT – So Darwinian evolution endowed us and evolved all other organisms with the  self-preservation instinct. Because those that didn’t have those  self-preservation genes are cleaned out of the gene pool. Right? But if you build an artificial general intelligence, the mind space that you can design is much much larger than just the specific subset of minds that can evolve that have. So  an AGI  mind doesn’t necessarily have to have any  self-preservation instinct. 

It also doesn’t necessarily have to be so individualistic as us. Like imagine if you could just, first of all, we are also very afraid of death. You know, suppose you could back yourself up every five minutes and then your airplane is about to crash. You’re  like: “Shucks. I’m gonna lose the last five minutes of experience since my last cloud backup.” Bang. You know, it’s not as big a deal. 

Or if we could just copy experiences between our minds easily like, which we could easily do. If we were silicon based right then maybe we would feel a little bit more like a Hive mind actually. …. So I don’t think we should take for granted at all that AGI will have to have any of those sort of competitive alpha male instincts. 

On the other hand you know this is really interesting because I think some people go too far and say of course we don’t have to have any concerns either. That advanced okay I will have those instincts because we can build anything we want that there’s there’s a very nice set of arguments going back to Steve Omohundro and Nick Bostrom and others just pointing out that when we build machines we normally build them with some kind of goal: win this chess game, drive this car safely or whatever. And as soon as you put in a goal into a machine especially if it’s kind of open ended goal and the machine is very intelligent, it will break that down into a bunch of sub goals and one of those goals will almost always be  self-preservation because if it breaks or dies in the process it’s not gonna accomplish the goal.

LF – Yeah 

MT – Like suppose you just build a little, you have a little robot and you tell it to go down the Star Market here and and and get you some food, make your cooking italian dinner you know and then someone mugs it and tries to break it on the way that robot has an incentive to not get destroyed and defend itself or run away because otherwise it’s going to fail and cooking your dinner, it’s not afraid of death but it really wants to complete the dinner cooking goal So it will have a  self-preservation instinct to ….

LF –  Continue being a functional agent.

MT – And similarly, if you give any kind of more ambitious goal to an AGI It’s very likely to want to acquire more resources so it can do that better. And it’s exactly from those sort of sub goals that we might not have intended that some of the concerns about AGI safety come. You give it some goal which seems completely harmless. And then before you realize it, it’s also trying to do these other things that you didn’t want it to do. And it may be smarter than us. So fascinating.

LF – And let me pause just because I am  in a very kind of human-centric way, see fear of death is a valuable motivator. So you don’t think…  do you think that’s an artifact of evolution? So that’s the kind of mind space evolution created that were sort of almost obsessed about self preservation, some kind of genetic….  so you don’t think that’s necessary to be afraid of death. So not just a kind of sub goal of self preservation. Just so you can keep doing the thing, but more fundamentally sort of have the finite thing like this ends for you at some point.

MT – Interesting. Do I think it’s necessary for what precisely?

LF –  For intelligence, but also for consciousness. So for both. Do you think really like a finite death and the fear of it is important.

MT – So before I can answer before we can agree on whether it’s necessary for intelligence or for consciousness, we should be clear how we define those two words because a lot of really smart people define them in very different ways. I was on this panel with AI experts and they couldn’t they couldn’t agree on how to define intelligence even so I define intelligence simply as the ability to accomplish complex goals. I like your broad definition because again, I don’t want to be a carbon chauvinist, right? And in that case, no, certainly it doesn’t require fear of death. I would say Alpha Go,  Alpha Zero is quite intelligent. I don’t think Alpha Zero has any fear of being turned off because it doesn’t understand the concept of that even and and similarly, consciousness, I mean, you could certainly imagine very simple kind of experience if, you know, if certain plans have any kind of experience, I don’t think they’re very afraid of dying and there’s nothing they can do about it anyway.  So there wasn’t much value and but more seriously, I think, uh, if you ask, not just about being conscious, but maybe having uh, with you, we we we we we might call an exciting life for you feel passion and really appreciate the things. Maybe they’re somehow, maybe there perhaps it does help having a backdrop today. It’s finite. No, let’s make the most of us live to the fullest. But if you, if you knew you were going to live forever, if you think you would change your ….

LF – Yeah, I mean, in some perspective, it would be an incredibly boring life living forever. So in the sort of loose, subjective terms that you said of something exciting and something in this that other humans would understand, I think as Yeah, it seems that the finiteness of it is important.

MT – Well, the good news I have for you then is based on what we understand about cosmology. Everything in our universe is ultimately probably finite. Although…

LF –  Big Crunch, or Big what’s the expansion?

MT – Yeah, we could have a Big Chill or a Big Crunch or a Big Rip or that’s the Big Snap or death bubbles. All of them are more than a billion years away. So we should, we certainly have vastly more time than our ancestors thought. But they’re still, it’s still pretty hard to squeeze in an infinite number of compute cycles even though there are some loopholes that just might be possible. But I think, you know, some people like to say that you should live as if you’re about to  die in five years or something that’s sort of optimal. Maybe it’s good we should build our civilization asset. It’s all finite to be on the safe side.

LF –  Right. Exactly. So you mentioned in defining intelligence as the ability to solve complex goals. So where would you draw a line? How would you try to define human level intelligence and super human level intelligence? Where is consciousness part of that definition? 

MT – No, consciousness does not come into this definition. So, I think of intelligence as it’s a spectrum, but there are very many different kinds of goals you can have, you can have a goal to be a good chess player, a good Go player, a good car driver, a good investor, good poet et cetera. So, intelligence that by its very nature isn’t something you can measure, but it’s one number overall goodness. No, no. There’s some people who are better at this. Some people are better than that. Right now we have machines that are much better than us at some very narrow tasks like multiplying large numbers fast, memorizing large databases, playing chess, playing Go and  soon driving cars. Um, but there’s still no machine that can match a human child in general intelligence. But artificial general intelligence AGI, the name of your course, of course, that is by its very definition the quest to build a machine, a machine that can do everything as well as we can up to the old Holy Grail of of AI  from back to its inception in the 60s, if that ever happens, of course, I think it’s going to be the biggest transition in the history of life on earth.

But it doesn’t necessarily have to wait for the big impact until machines are better than us at knitting. The really big change, it doesn’t come exactly the moment they’re better than us at everything. The really big change comes first. There are big changes when they start becoming better at us and doing most of the jobs that we do because that takes away much of the demand for human labor. And then the really whopping change comes when they become better than us at AI research. Right? Right. Because right now the time scale of AI research is limited by the human research and development cycle of years. Typically, you know, how long does it take from one release of some software or iPhone or whatever to the next. But once, once we once Google can replace 40,000 engineers, about 40,000 equivalent pieces of software or whatever. …. there’s no reason that has to be years, it can be in principle much faster. And the time scale of future progress in AI and all of science and technology will be driven by machines, not humans. So it’s this point, simple point, which gives rise to this incredibly fun controversy about whether there can be an intelligence explosion, so called singularity as Vernor Vinge called it. The idea was articulated by  I. J. Good obviously way back 50s. But you can see Alan Turing and others thought about it even earlier. You asked me what exactly what I define… 

LF – human level intelligence. 

MT –  Yeah. So the glib answer is to say something which is better than us at all cognitive tasks with better than any human at all cognitive tasks. But the really interesting bar I think goes a little bit lower than that. Actually. It’s when they can run they’re better than us at AI  programming and general learning so that they can if they want to get better than us at anything by this study. 

LF – So there better is a keyword and better is towards this kind of spectrum of the complexity of goals it’s able to accomplish. So another way to….. and that’s certainly a very clear definition of human love. So there’s it’s almost like a sea that’s rising and you can do more and more and more things. Its geographic, that you show. It’s really nice way to put it. So there’s some peaks and then  there’s an ocean level elevating and you solve more and more problems. But you know, just kind of to take a pause and we took a bunch of questions and a lot of social networks and a bunch of people asked sort of a slightly different direction on creativity and and things like that perhaps aren’t a peak. You know, human beings are flawed and perhaps better means having having contradiction, being fought in some way. So let me sort of, yeah, start easy first of all. You have a lot of cool equations. Let me ask what’s your favorite equation first of all, I know they’re all like your children, but which one is that?

MT –  The Schrodinger equation, the master key of quantum mechanics of the micro world. So with this equation we can calculate  everything to do with atoms and molecules and all the way up.

LF – Yeah, so, okay, so quantum mechanics is certainly a beautiful mysterious formulation of our world. So I’d like to sort of ask you just as an example, it perhaps doesn’t have the same beauty as physics does, but in mathematics (abstract), Andrew Wiles who proved Fermat’s Last Theorem. So he, I just saw this recently and it kind of caught my eye a little bit. This is 358 years after it was conjectured. So this very simple formulation. Everybody tried to prove it. Everybody failed. And so here’s this guy comes along and eventually proves it and then fails to prove it and then proves it again in 1994. And he said like the moment when everything connected into place. Then in an interview he said:” It was so indescribably beautiful that moment when you finally realize the connecting piece of two conjectures.” He said: “It was so indescribably beautiful. It was so simple and so elegant. I couldn’t understand how I’d missed it and I just stared at it in disbelief for 20 minutes. Then during the day I walked around the department and I’d keep coming back to my desk looking to see if it was still there, it was still there, I couldn’t contain myself. I was so excited. It was the most important moment of my working life. Nothing I ever do again will mean as much.” So that particular moment and it kind of made me think of what would it take and I think we have all been there at small levels. Maybe let me ask, have you had a moment like that in your life? Were you just had an idea. It’s like, wow! Yes…

MT – I wouldn’t mention myself in the same breath as Andrew Wiles, but I’ve certainly had a number of aha moments when I realized something very cool about physics just completely made my head explode. In fact, some of my favorite discoveries, I made a I later realized that have been discovered earlier or someone who sometimes got quite famous for it. So it was too late for me to even publish it. But that doesn’t diminish in anyway, the emotional experience you have when you realize it like, wow!

LF –  Yeah. So what would it take in at that moment? That, wow, that was yours in that moment. So what do you think it takes for an intelligence system, an AGI system, an AI system to have a moment like that?

MT –  That’s a  tricky question because there are actually two parts to it. Right? One of them is can it accomplish that proof? Can it  prove that you can never write A to the N plus B to the N equals Z to the N for all integers etcetera etcetera when N is bigger than 2? That was simply in any question about intelligence. Can you build machines that are that intelligent? And I think by the time we get a machine that can independently come up with that level of proofs probably quite close to AGI. 

The second question is a question about consciousness. When will we and how likely is it that such a machine would actually have any experience at all as opposed to just being like a zombie. And would we expect it to have some sort of emotional response to this or anything at all akin to human emotion where when it accomplishes its machine goal, it views that somehow as something very positive and and and sublime and deeply meaningful. I would certainly hope that if  in the future we do create machines that are our peers or even our descendants. 

LF – Yeah.

MT – I would certainly hope that they do have this sort of sublime appreciation of life. In a way, my absolutely worst nightmare would be that  at some point in the future, the distant future. Maybe our cosmos is teeming with all this post biological life doing all the seemingly cool stuff. And maybe the last humans by the time our species eventually fizzles out will be like, well that’s okay because we’re so proud of our descendants here and look what  ….  My worst nightmare is that we haven’t solved the consciousness problem and we haven’t realized that these are all the zombies. They’re not aware of anything any more than the tape recorders has any kind of experience. So the whole thing has just become a play for empty benches that would be like the ultimate zombie apocalypse me. So I would much rather in that case that mm we have these beings which can really appreciate how amazing it is.

LF –  And in that picture what would be the role of creativity. But a few people ask about creativity, do you think when you think about intelligence? I mean, certainly the story you told at the beginning of your book involved, you know, creating movies and so on, sort of making money. You know, you can make a lot of money in our modern world with music and movies. So if you are an intelligence system, you may want to get good at that. But that’s not necessarily what I mean by creativity. Is it important on that complex goals where the sea is rising for there to be something creative or or am I being very human-centric and thinking, creativity is somehow special relative to intelligence?

MT –  My hunch is that we should think of your creativity simply as an aspect of intelligence. And  we we have to be very careful with the human vanity we have we have this tendency very often want to say as soon as machines can do something, we try to diminish it and saying: Oh but that’s not like real intelligence, you know because they’re not creative or there were or this or that the other thing. 

If we ask ourselves to write down a definition of what we actually mean by being creative, what we mean by Andrew Wiles, what he did there for example, don’t we often mean that someone takes a very unexpected leap. It’s not like taking 573 and multiplying it by 224 by just a step of straightforward cookbook-like rules. Right? You can maybe make it, you make a connection between two things that people have never thought was connected or something like that.

LF – Yeah, it’s very surprising. 

MT – I think  this is an aspect of intelligence and  this is actually one of the most important aspects of it. Maybe the reason we humans tend to be better at it than traditional computers is because it’s something that comes more naturally if you’re a neural network than if your traditional logic gate based computer machine. You know we physically have all these connections. And that if you activate here, activate here, activate here being, you know, bing! My hunch is that if we ever build a machine, well, you could just give it the task. Hey, you know, I just realized that I want to travel around the world instead this month. Can you teach my AGI course for me? And it’s like, okay, I’ll do it. And it does everything that you would have done and improvises and stuff that would, in my mind, involve a lot of creativity.

LF –  Yeah, So it’s actually a beautiful way to put it. I think we do try to grasp at the, you know, the definition of intelligence is everything. We don’t understand how to build. So we, as humans try to find things well that we have that our machines don’t have. And maybe creativity is just one of the things, one of the words we use to describe that, that’s a really interesting way to put it.

MT –  I don’t think we need to be that defensive. I don’t think anything good comes out of saying, well, where somehow special, you know It’s contrary wise, there are many examples in history of where trying to pretend that we’re somehow superior to all other intelligent beings has led the pretty bad results, right? Nazi Germany, they said that they were somehow superior to other people.  today we still do a lot of cruelty to animals by saying that we’re so superior somehow. And they can’t feel pain, slavery was justified by the same kind of just really weak arguments. And I don’t think if we actually go ahead and build artificial general intelligence which can do things better than us, I don’t think we should try to found our self worth on some sort of bogus claims of superiority in terms of our intelligence. I think we should instead find our calling and the meaning of life from the experiences that we have. 

LF – Right.

MT -You know, I can have, I can have very meaningful experiences, even if there are other people who are smarter than me, you know? Okay, when I go to a faculty meeting here and I were talking about something that I certainly realize, oh, but he has a Nobel prize, he has a Nobel prize, he has a Nobel prize, I don’t have one. Does that make me enjoy life any less? Or I enjoy talking to those people. Of course not, you know, and contrary wise, I  feel very honored and privileged to get to interact with other very intelligent beings that are better than me at a lot of stuff. So I don’t think there’s any reason why we can’t have the same approach with intelligent machines.

LF –  That’s a really interesting …. So people don’t often think about that. They think about when there’s going if there’s machines that are more intelligent, you naturally think that that’s not going to be um a beneficial type of intelligence, you don’t realize it could be, you know, like peers with Nobel prizes that that would be just fun to talk with, and they might be clever about certain topics and  you can have fun having a few drinks with them, so ….

MT – Well also, you know, another example, we can all relate to it of why it doesn’t have to be a terrible thing to be impressed with the presence of people or even smarter than us all around is when you and I were both two years old, I mean, our parents were much more intelligent than us, right? Worked out okay, because their goals were aligned with our goals and that I think is really the number one key issue we have to solve ….

LF -….  the value alignment problem.

MT – Exactly. Because people who see too many Hollywood movies with lousy science fiction plot lines, they worry about the wrong thing, right? They worry about some machines, certainly turning evil. It’s not malice that is the concern, it’s competence. By definition intelligence makes you very competent if you have a more intelligent Go playing computer playing is the less intelligent one and when we define intelligence is the ability to accomplish Go winning right, it’s going to be the more intelligent one that wins.  And if you have a human and then you have an AGI that’s more intelligent than always, and they have different goals, guess who’s going to get their way right? 

So I was just reading about this  particular rhinoceros species that was driven extinct just a few years ago, 

LF – Yes

MT – A bummer. I was looking at this cute picture, mommy rhinoceros with its child, you know, why did we humans drive it to extinction? It wasn’t because we were evil rhino haters as a whole. It was just because our goals weren’t aligned with those of the rhinoceros, and it didn’t work out so well for the rhinoceros because we were more intelligent, right? So I think it’s just so important that if we ever do build AGI before we unleash anything, we have to make sure that it learns to understand our goals, adopts our goals and it retains those goals.

LF –  So the cool interesting problem there is being able …. us as human beings, trying to formulate our values. So, you know, you can think of the United States Constitution as a way that people sat down at the time, a bunch of white men, but which is a good example, we should say they formulated the goals for this country and a lot of people agree that those goals actually held up pretty well, That’s an interesting formulation of values and failed miserably in other ways. So for the value alignment problem and a solution to it, we have to be able to put on paper or in a program human values? How difficult do you think that is?

MT –  Very But it’s so important we really have to give it our best. And it’s difficult for two separate reasons. There’s the technical value alignment problem of figuring out how to make machines understand their goals, document, and retain them. And then there’s the separate part of it, the philosophical part, whose values anyway? And since it’s not like we have any great consensus on this planet on values, what mechanisms should we create them, to aggregate and decide okay, what’s a good compromise? Uh, that second discussion can’t just be left to the tech nerds like myself, right 

LF – That’s right. 

MT – And if we refuse to talk about it and then AGI  gets built, who’s going to be actually making the decision about who’s values? It’s gonna be a bunch of dudes and some tech company. And are they necessarily so representative, all of humankind that we wanted just entrusted to them. Are they even uniquely qualified to speak to future human happiness just because they’re good at programming AGI? I would much rather have this be a really inclusive conversation.

LF –  But do you think it’s possible ….  so you create a beautiful vision that includes, the diversity, cultural diversity and various perspectives on discussing rights, freedoms, human dignity, but how hard is it to come to that consensus? Do you think it’s certainly a really important thing that we should all try to do? But do you think it’s feasible?

MT –  I think there’s no better way to guarantee failure than to refuse to talk about it or refuse to try. And I also think it’s a really bad strategy to say, okay, let’s first have a discussion for a long time and then once we reach complete consensus, then we’ll try to load it into the machine. No, we shouldn’t let perfect be the enemy of the good. Instead we should start with the kindergarten ethics that pretty much everybody agrees on and put that into machines. Now we’re not doing that even.

Look at you know, anyone who builds as a passenger aircraft wanted to never under any circumstances fly it into a building or a mountain right yet the September 11 hijackers were able to do that. And even more embarrassing that you know Andreas Lubitz, this depressed Germanwings pilot when he flew his passenger jet into the Alps killing over 100 people, he just told the autopilot to do it. He told the freaking computer to change the altitude to 100 meters. And even though it had the GPS maps and everything, the computer was like okay. 

So we should take those very basic values where the problem is not that we don’t agree, the problem is just we’ve been too lazy to try to put it into our machines and make sure that from now on airplanes will  all  have computers in them, but we just never just refuse to do something like that. Go into safe mode, maybe lock the cockpit door door, go to the nearest airport. 

And there’s so much other technology in our world as well now where it’s really becoming quite timely to put in some sort of very basic values like this, even in cars, we have had enough vehicle terrorism attacks by now. If you have driven trucks and vans into pedestrians, that is not at all a crazy idea to just have that hard wired into the car because there are a lot of, there’s always gonna be people who for some reason want to harm others. But most of those people don’t have the technical expertise to figure out how to work around something like that. So, if the car just won’t do it, it helps. So let’s start there. 

LF –  So there’s a lot of … that’s a great point. So not, not chasing perfect. 

MT – Yeah.

LF – There’s a lot of things that a lot that most of the world agrees on, let’s start there.

MT –  Let’s start there. And  then once we start there, we’ll also get into the habit of having these kinds of conversations about, okay, what else should we put in here and have these discussions? This would be a gradual process then

LF –  Great. So, but uh, that also means describing these things and describing it to a machine. So one thing we had a few conversations. Stephen Wolfram, I’m not sure if you’re familiar with Stephen but

MT –  Oh yeah I know him quite well.

LF –  So he has you know he played, you know he works with a bunch of things but you know cellular automata,  these simple computable things, these computation systems and you kind of mentioned that you know we probably have already,  within these systems already something that’s AGI.  meaning like we just don’t know it because we can’t talk to it. So, if you give me this chance to try to at least form a question out of this … I think it’s an interesting idea to think that we can have intelligence systems but we don’t know how to describe something to them and they can’t communicate with us. I know you’re doing a little bit of work and explainable AI trying to get AI to explain itself. So what are your thoughts of natural language processing or some kind of other communication? How does the AI explain something to us? How do we explain something to it, to machines or do you think of it differently?

MT – So there are two separate parts of your question there. One of them has to do with communication which is super interesting and we’ll get to that in a sec.  The other is whether we already have AGI, but we just haven’t noticed it.There I beg to differ, right.  I don’t think there’s anything in any cellular automaton or anything in the Internet itself or whatever that has artificial general intelligence and that it can really do exactly everything we humans can do better. I think the day that happens, when that happens, we will very soon notice and will probably notice even before because in a very very big way. But for the for the second part though,

LF –  Wait, can I ask, sorry? So, because you have this beautiful way of formulating consciousness as  you know as information processing and you can think of intelligence and information processing and as you can think of the entire universe is these particles and these systems roaming around that have this information processing power. You don’t  think there is something with the power to process information in the way that we human beings do that’s out there, that needs to be sort of connected to. It seems a little bit philosophical perhaps, but there’s something compelling to the idea that the power is already there which is the focus should be more on being able to communicate with it.

MT –  Well, I agree that in a certain sense the hardware processing power is already out there because our universe itself, you can think of it as being a computer already right? It’s constantly computing what water waves, how it devolved the water waves in the river Charles and how to move the air molecules around.  Seth Lloyd has pointed out (my colleague here) that you can even in a very rigorous way think of our entire universe as just being a quantum computer. It’s pretty clear that our universe supports this amazing processing power. Because you can even within this physics computer that we live in, right, we can even build actual laptops and stuff. So clearly the power is there, it’s just that most of the compute power that nature has, it’s in my opinion, kind of wasting on boring stuff like simulating yet another ocean waves somewhere. We don’t want to even looking right? So, in a sense, what life does, what we are doing when we build computers is we’re re-channeling all this compute that nature is doing anyway into doing things that are more interesting just yet another ocean wave, you know, and let’s do something cool here. So the raw hardware power is there and for sure, and even just like computing what’s going to happen for the next five seconds in this water bottle, you know, it takes a ridiculous amount of compute if you do it on a human computer, this water bottle just did it. But that does not mean that this water bottle has AGI because AGI  means, it should also be able to have written my book, done this interview and I don’t think it’s just communication problems.

LF – As far as we know.

MT –  I don’t  think it can do it and…

LF –  Although Buddhists say when they watch the water and that there is some beauty, that there’s some depth and being in nature that they can communicate with.

MT –  Communication is also very important because I mean look  part of my job is being a teacher and I know some very intelligent professors even, who just have a bit of a hard time communicating all these brilliant ideas. But to communicate with somebody else you have to also be able to simulate their own mind.

LF –  Yes, empathy.

MT –  build well enough and understand a model of their mind that you can say things that they will understand. That’s quite difficult. Right? That’s why today it’s so frustrating if if you have a computer that make some cancer diagnosis and you ask it well why are you saying I should have the surgery and if it can only reply: {MT speaking in a machine voice} I was trained on five terabytes of data and this is my diagnosis, boop boop beep beep.

LF – Yeah.

MT – It  doesn’t really instill a lot of confidence, right? So I think we have a lot of work to do on communication there.

LF –  So what kind of …. I think you’re doing a little bit work on explainable AI,  what do you think are the most promising avenues? Iis it mostly about sort of the Alexa problem of natural language processing,  of being able to actually use human interpretable methods of communication? So being able to talk to a system and talk back to you or is there some more fundamental problems to be solved? 

MT –  I think it’s all of the above.  The natural language processing is obviously important but they’re also more nerdy fundamental problems, like if you take… you play chess? 

LF – Of course, I’m Russian, I have to.

MT – Ты говоришь по-русски? {You speak Russian?}

LF – Да по русски говорю  {Yes, I speak Russian}

MT – Отлично, я не знал. 
{Excellent, I didn’t know. }

LF – When did you learn Russian? 

MT – Я говорю очень плохо по-русски.Купил книгу, “Teach Yourself Russian” читaл очень много . Было очень трудно. я говорю так плохо. 

{I speak very bad Russian.Bought a book“ Teach Yourself Russian”, read a lot. It was very difficult. I talk so bad}

LF – How many languages do you know? Wow, that’s really impressive.

MT –  I don’t know, my wife has some calculations, but my point was if you play chess, like have you looked at the Alpha Zero games? 

LF –  Uh, the actual games no.

MT –  Check it out, some of them are just mind blowing. Really beautiful and if you ask, how did it do that? Yeah, you got to talk to them, Demis Hassabis and others from DeepMind. All they will ultimately be able to give you is big tables of numbers, matrices that defined the neural network and you can stare at these tables, numbers until your face turns blue and you’re not going to understand much about why it made that move and  even if you have a natural language processing that can tell you in human language about 5,7,0.28 it’s still not gonna really help. 

So I think I think there’s a whole spectrum of fun challenges there involved in taking a computation that does intelligent things and transforming into something equally good, equally intelligent, but it’s more understandable and I think that’s really valuable because I think as we put machines in charge of ever more infrastructure in our world, the power grid, trading on the stock market, weapons systems and so on, it’s absolutely crucial that we can trust these AIs to do all we want and trust really comes from understanding…

LF – Right.

MT – …  in a very fundamental way. And that’s why I’m, that’s why I’m working on this. Because I think the more …  if we’re gonna have some hope of ensuring that machines have adopted our goals and that they’re going to retain them, that kind of trust, I think needs to be based on things you can actually understand perfectly, even make perfectly improved theorems on even with a self-driving car, right. If someone just tells you it’s been trained on tons of data and never crashed, it’s less reassuring than if someone actually has a proof, maybe it’s a computer verified proof. But still, it says that under no circumstances is this car just gonna swerve into oncoming traffic

LF –  And that kind of information helps to build trust and help build the alignment, the alignment of goals. At least, awareness that your goals, your values are aligned.

MT –  And I think even a very short term, if you look at uh, you know today, right, that’s an absolutely pathetic state of cybersecurity that we have, right, when it was three billion Yahoo accounts were hacked? Almost every American’s credit card and so on. You know, why is this happening? It’s ultimately happening because we have software that nobody fully understood how it worked. That’s why the bugs hadn’t been found, right? And  I think AI can be used very effectively for offense, for hacking, but it can also be used for defense, hopefully automating verifiability and creating systems that are built in different ways. So you can actually prove things about them

LF – Right.

MT –  and it’s important.

LF – So speaking of software that nobody understands how it works, of course, a bunch of people ask about your paper about your thoughts of why does deep and cheap learning works so well, that’s the paper. But what are your thoughts on deep learning, these kind of simplified models of our own brains have been able to do some successful perception work, pattern recognition work and now with alpha zero and so on, do some clever things. What are your thoughts about the promised limitations of this piece?

MT –  00:59:43

Great. I think there are a number of very important insights, very important lessons. We can always draw from these kind of successes. One of them is when you look at the human brain and you see it’s very complicated, 10 to the 11th {10^11}  neurons and there are all these different kinds of neurons and Yada Yada. And there’s been this long debate about whether the fact that we have dozens of different kinds is actually necessary for intelligence. Which I now, in think quite convincingly answer that question: No, it’s enough to have just one kind if you look under the hood of Alpha Zero, there’s only one kind of neuron and it’s a ridiculously simple mathematical thing. So it’s not… it’s  just like in physics, if you have a gas with waves in it, it’s not the detailed nature of the molecules that matter, it’s the collective behavior somehow. Similarly, it’s this higher level structure of the network matters; not that you have 20 kinds of yours. I think our brain is such a complicated mess because it wasn’t evolved just to be intelligent, it was evolved to also be self-assembling…  

LF – right.

MT – … and self-repairing, right? And evolutionarily attainable

LF –  and {unitelligible } and so on.

MT –  So I think it’s pretty my hunch is that we’re going to understand how to build AGI before we fully understand how our brains work, just like we understood how to build flying machines long before we were able to build a mechanical work bird.

LF –  Yeah, that’s right. You’ve given that example exactly of mechanical birds and airplanes and airplanes do a pretty good job of flying without really mimicking bird flight.

MT –  And even now,  100 years later, did you see TED talk with the German mechanical bird?

LF – I heard you mention it.

MT – Check it out, it’s amazing. But even after that we still don’t fly in mechanical birds because it turned out the way we came up with is simpler. It’s better for our purposes and I think it might be the same there. That’s one lesson.  

Another lesson is one that our paper was about;  well, first I as a physicist thought it was fascinating how there is a very close mathematical relationship actually between our artificial neural networks and a lot of things that we’ve studied for in physics, they go buy nerdy names like the renormalization group equation and Hamiltonians and yada, yada, yada. And when you look a little more closely at this, you have…at first I was like, whoa, there’s something crazy here that doesn’t make sense because we know that if you even want to build a super simple neural network to tell apart cat pictures and dog pictures, right? That you can do that very, very well now.

But if you think about it a little bit, you convince yourself it must be impossible because if I have one megapixel, even if each pixel is just black or white, there’s two to the power one million possible images which is way more than there are atoms in our universe.  So in order to ….I have to assign a number which is the probability that it’s a dog. So an arbitrary function of images is a list of more numbers than there are atoms in our universe. So clearly I can’t store that under the hood of my GPU or my computer yet somehow works. So what does that mean? Well it means that out of all of the problems that you could try to solve with a neural network, Almost all of them are impossible to solve with a reasonably sized one. But then what we showed in our paper was that the fraction of all the problems that you could possibly pose that we actually care about given the laws of physics is also an infinitesimally tiny little part and amazingly they are basically the same part.

LF –  Yeah. It’s almost like the world was created for…  I mean they kind of come together.

MT –  Yeah, you could say maybe where the world was created for us. But I have a more modest interpretation which is that instead evolution endowed us with neural networks precisely for that reason because this particular architecture {gesturing to his head} as opposed to the one in your laptop is very very well adapted to solving the kind of problems that nature kept presenting it our ancestors with, right. So it makes sense why do we have a brain in the first place? It’s to be able to make predictions about the future and so on. So if we had a sucky system which I could never solve it. But I would never have worked. But so this is I think a very beautiful fact. Yeah. We also realize that there is  there’s been earlier work on why deeper networks are good. But we were able to show an additional cool fact there which is that even incredibly simple problems like suppose I  give you a 1000 numbers and ask you to multiply them together and you can write a few lines of code. Boom, done, trivial. If you just try to do that with a neural network that has only one single hidden layer in it, you can do it but you’re gonna need two to the power of 1000 neurons to multiply 1000 numbers which is again more neurons than there are atoms in our universe. 

LF – That’s fascinating.

MT – But if you allow yourself to make it a deep network of many layers you only need 4000 neurons, it’s perfectly feasible. So…. 

LF –  That’s really interesting. Yeah. So on another architecture type I mean you mentioned Schrodinger’s equation and what are your thoughts about quantum computing and the role of this kind of computational unit in creating an intelligence system?

MT –  in some Hollywood movies that I will not mention my name. I don’t want to spoil them,  the way they get AGI Is building a quantum computer because the word quantum sounds cool and so on.

LF – That’s right.

MT – First of all I think we don’t need quantum computers to build AGI. I suspect your brain is not a quantum computer and in any found sense. I even wrote a paper about that many years ago. I calculated the so called decoherence time; how long it takes until the quantum computerness of what your neuron is doing gets erased by just random noise from the environment and it’s about 10 to the -21 seconds. So as cool as it would be to have a quantum computer in my head. I don’t think that fast. 

On the other hand there are very cool things you could do with quantum computers or I think we’ll be able to do soon when we get bigger ones that might actually help machine learning do even better than the brain. So for example, this is just a Moonshot but okay  you know that learning, it’s very much the same thing as a search. If you have, if you’re trying to train a neural network to get really learned to do something really well, you have some loss function. You have some you have a bunch of knobs you can turn well which are represented by a bunch of numbers and you’re trying to tweak them so that it becomes as good as possible at this thing. So if you think of the landscape but with some valley where each dimension of the landscape corresponds to some number you can change,  you’re trying to find the minimum and it’s well known that if you have a very high dimensional landscape, complicated things? It’s super hard to find the minimum, right? 

Quantum mechanics is amazingly good at this. If I want to know what’s the lowest energy state this water can possibly have; incredibly hard to compute. But nature will happily figure this out for you if you just cool it down, make it very, very cold. If you put a ball somewhere, it’ll roll down to its minimum. And this happens metaphorically, the energy landscape too. And quantum mechanics even uses some clever tricks which today’s machine learning systems don’t. Like you’re trying to find the minimum and you get stuck in the little local minimum here in quantum mechanics who can actually tunnel through the barrier and get unstuck again? 

LF –  That’s really interesting.

MT -So it may be, for example, we will one day use quantum computers that help train neural networks better?

LF –  That’s really interesting. Okay, so as a component of kind of the learning process, for example.

MT –  Yeah.

LF –  Let me ask , sort of wrapping up here a little bit. Let me return to  the questions of our human nature and love, as I mentioned. So do you think  …. you mentioned sort of a helper robot that you can think also of  robots. Do you think the way we human beings fall in love and get connected to each other. It’s possible to achieve in an AI system, in human level AI intelligence system? Do you think we would ever see that kind of connection or  you know, in all this discussion about solving complex goals as this kind of human social connection, do you think that’s one of the goals on the peaks and valleys that with the raising sea levels that would be able to achieve? Or do you think that’s something that’s ultimately, or at least in the short term, relative to the other goals is not achievable? 

MT –  I think it’s all possible. And I mean, in recent ….there’s a there’s a very wide range of distances, you know, among AI researchers when we’re going to get AGI. Some people, you know, like our friend Rodney Brooks says it’s going to be hundreds, hundreds of years at least. And then there are many others. I think it’s gonna happen much sooner in recent polls, maybe a half or so of AI researchers think we’re going to get AGI  within decades.  So if that happens, of course, I think these things are all possible, but in terms of whether it will happen, I think we shouldn’t spend so much time asking what do we think will happen in the future as if we are just some sort of pathetic passive bystanders, you know, waiting for the future to happen to us? Hey, we’re the ones creating this future, Right, So we should be proactive about it and ask yourself what sort of future we would like to have happen that’s going to make it like that. 

Well, what I prefer to some sort of incredibly boring zombie-like future where just all these mechanical things happen and there’s no passion, no emotion, no experience, maybe even. No, I would of course much rather prefer if all the things that we find that we value the most about humanity, our subjective experience, passion, inspiration, you love. You know, if we can create a future where those are where those things do exist, I think ultimately it’s not our universe giving meaning to us, it’s us giving meaning to our universe If we build more advanced intelligence, let’s let’s make sure building in such a way that meaning is it’s part of it. 

LF –  A lot of people that seriously study this problem and think of it from different angles have trouble, the majority of cases if they think through that happen are the ones that are not beneficial to humanity. And so yeah, so what are your thoughts, What’s in and what’s, what should people, you know, I really don’t like people to be terrified.  What’s a way for people to think about it in a way that in a way we can solve it and we can make it better. 

MT –  But no, I don’t think panicking is gonna help in any way. It’s not going to increase chances of things going well either. Even if you are in a situation where there is a real threat, does it help if everybody just freaks out? No, of course, of course not.  I think, yeah, there are of course ways in which things can go horribly wrong.  

First of all, it’s important when we think about this thing, about the problems and risks to also remember how huge the upsides can be if we get it right, right? Everything we love about society and civilization is a product of intelligence. So if we can amplify our intelligence with machine intelligence and not anymore lose our loved ones, to what we’re told in an incurable disease and things like this, of course we should aspire to that. So that can be a motivator, I think, reminding ourselves that the reason we try to solve problems is not just because right, trying to avoid doom, but because we’re trying to do something great. But then in terms of the risks, I think the really important question is to ask: what can we do today that will actually help make the outcome good, right?

LF – Yes.

MT – And  dismissing the risk is not one of them. You know, I find it quite funny often when I’m in on discussion panels about these things, how the people who I work for for companies will always be like: “Oh, nothing to worry about, nothing to worry about, nothing to worry about.” And it’s always,  it’s only academics sometimes expressing concerns. That’s not surprising at all. If you think about it, Upton Sinclair quipped that: ”It’s hard to make your man believe in something when his income depends on not believing in it.”  { Actual quote is:  “It is difficult to get a man to understand something when his salary depends upon his not understanding it.”  book “I, Candidate for Governor: And How I Got Licked,” by Upton Sinclair, 1935 }

And frankly, we know a lot of these people and companies that they are just as concerned as anyone else. But if you’re the CEO of a company, that’s not something you want to go on record saying,  when you have silly journalists who are going to put a picture of a Terminator robot when they quote you. 

So, the issues are real, and the way I the way I think about what the issue is is basically, you know, the real choice we have is first of all are we going to just dismiss this the risks and say, well, let’s just go ahead and build machines that can do everything we can do better and cheaper. You know, let’s just make yourselves obsolete as fast as possible. What could possibly go wrong? That’s one attitude.

The opposite attitude I think, is to say there is incredible potential. You know, let’s think about what kind of future we’re really, really excited about. What are the shared goals that we can really aspire towards. And then let’s think really hard on how about how we can actually get there. So start with, don’t start thinking about the risks. Start thinking about the goals and then when you do that, then you can think about the obstacles you want to avoid, right? I often get students coming in right here into my office for career advice, I always ask them this very question, where do you want to be in the future? If all she can say as well, maybe I’ll have cancer, maybe I’ll get run over by a truck.

LF – Focus on obstacles instead of the goal

MT –  She’s just going to end up a hypochondriac paranoid, whereas if she comes in with fire in her eyes and it’s like I want to be there and then we can talk about the obstacles and see how we can circumvent them. That’s, I think, a much healthier attitude.

LF – That’s really well put. 

MT – And  I feel it’s very challenging to come up with a vision for the future which we are unequivocally excited about. I’m not just talking now in vague terms like, yeah, let’s cure cancer. Fine. Talking about what kind of society do we want to create, what do we want it to mean to be human in the age of AI,  in the age of AGI. So if we can have this conversation,  broad inclusive conversation and gradually start converging towards some future that with some direction at least that we want to steer towards right then then we will be much more motivated to constructively take on the obstacles and I think if I if I had to, if I try to wrap this up in a more succinct way, I think, I think we can all agree already now that we should aspire to build AGI but doesn’t overpower us, but that empowers us.

LF –  And think of the many various ways that can do that, whether that’s from my side of the world of autonomous vehicles, I I’m personally actually from the camp that believes that human level intelligence is required to to achieve something like vehicles that would actually be something we would enjoy using and being part of. So that’s one example and certainly there’s a lot of other types of robots and medicine and so on. So focusing on those and then and then coming up with the obstacles, coming up with the ways that that can go wrong and solving those one at a time. 

MT –  And just because you can build an autonomous vehicle, even if you could build one that would drive just fine without, you know, maybe there are some things in life that we would actually want to do ourselves

LF – That’s right, 

MT – Like for example, if you think of our society as a whole, there’s something that we find very meaningful to do and that doesn’t mean we have to stop doing them just because machines can do them better. You know, I’m not gonna stop playing tennis the day someone build a tennis torobot beat me.

LF –  People are still playing chess and even Go

MT –  Yeah, and in the very near term, even some people are advocating basic income, replacing jobs, but if you if the government is going to be willing to just hand out cash to people for doing nothing, then one should also seriously consider whether the government should also hire a lot more teachers and nurses and the kind of jobs which people often find great fulfillment in doing right. I  get very tired of hearing politicians saying: “Oh we can’t afford hiring more teachers, but we’re going to maybe have basic income.” If we can have more serious research and thought into what gives meaning to our lives and the jobs give so much more than income, right? And then think about, in the future …. What are the roles that we want to have people continue doing empowered by machines?

LF – And I think sort of ….  I come from Russia, from the Soviet Union and I think for a lot of people in the 20th century, going to the moon, going to space was an inspiring thing. I feel like the universe of the mind, so AI, understanding and creating intelligence is that for the 21st century. So it’s really surprising and I’ve heard you mention this, it’s really surprising to me both in the research funding side that it’s not funded as greatly as it could be, but most importantly, on the politician’s side that it’s not part of the public discourse except in the killer bots/Terminator kind of view that people are not yet. I think perhaps excited by the possible positive future that we can build together, so …

MT –  And we should be because politicians usually just focus on the next election cycle, right? The single most important thing I feel we humans have learned in the entire history of science is that we are the masters of underestimation, we underestimated the size of our cosmos again and again, realizing that everything we thought existed, there’s just a small part of something grander, right?  Planet, solar system, a galaxy, you know, clusters of galaxies, universe and we now know that … the future has just so much more potential than our ancestors could ever have dreamt of this cosmos.

 Imagine if all of earth was completely devoid of life except for Cambridge Massachusetts. Wouldn’t it be kind of lame if all we ever aspired to was to stay in Cambridge Massachusetts forever and then go extinct in one week even though earth was going to continue on for longer, that sort of attitudeI think we have now. On the cosmic scale we can, life can flourish on earth, not for four years, but for billions of years. I can even tell you about how to move it out of harm’s way when the sun gets too hot. And then we have so much more resources out here, which today maybe there are a lot of other planets with bacteria or cow-like life on them. But most of this,  all this opportunity seems as far as we can tell to be largely dead, like the Sahara desert. And yet we have the opportunity to help life flourish like this for billions of years. So like, let’s quit squabbling about when some little border should be drawn one mile to the left or to the right and look up to the skies. You realize, hey, you know, we can do such incredible things.

LF –  Yeah. And that’s I think why it’s really exciting that yeah, you and others are connected with some of the work Elon Musk is doing because he’s literally going out into that space, really exploring our universe. And it’s wonderful.

MT –  That is exactly why Elon Musk is so misunderstood, right? Misconstrue him as some kind of pessimistic doomsayer. The reason he cares so much about AI safety is because he more than almost anyone else appreciates these amazing opportunities that we’ll squander if we wipe out here on Earth. We’re not just going to wipe out the next generation but all generations. And this incredible opportunity that’s out there and that would really be a waste. An AI, for people who think that we would be better to do without technology; well, let me just mention that if we don’t improve our technology, the question isn’t whether humanity is going to go extinct. The question is just whether we’re gonna get taken out by the next big asteroid or the next super volcano or something else dumb, that we could easily prevent with more tech, right? And if we want life to flourish throughout the cosmos, AI is the key to it. Yeah. As I mentioned, a lot of detail in my book right there, even many of the most inspired sci-fi writers, I feel have totally underestimated the opportunities for space travel, especially to other galaxies, because they weren’t thinking about the possibility of AGI. I’ve, which just makes it so much easier,

LF –  Right? Yeah. So that goes to your view of AGI that enables our progress, that enables a better life. So that’s a beautiful way to put it and something to strive for. So Max, thank you so much. Thank you for your time today, it has been awesome.

MT  Thank you so much. спасибо большое. Молодец {Well done}

Lessons learned from Lex and Nathalie Cabrol (Lex Fridman Podcast #348)

Lessons learned from Lex and Nathalie Cabrol (Lex Fridman Podcast #348)

I’ve been watching Lex Fridman’s podcasts in 2023; they are a good source of learning. Lex interviewed Nathalie Cabrol [1] on 19 December 2022; these are my lessons learned.

What is Life? Where did Life come from?

Nathalie works in astrobiology, her life has been studying life on Earth and developing methods to look for signatures of life in our solar system. She noted there are something like 123 definitions of life. Here are snippets of Nathalie’s answer to the Schrodinger question of What is Life?:

  • “Preserving information is what life does … 
  • “… .the nature of life is really what is going to give you some universal signature to look for it all over the place ….”
  • “…. the nature of life is telling you that life wants to get the most information possible around its surroundings and complexities, in fact the ability to gather and exchange and preserve the most information possible.” 
  •  …. the nature of life is different, If really life is the best way the universe has to fight entropy there’s no bias there because physics is the same all across the universe at least the universe we know they might be other universes but the one we know works with the same physics. {This snippet came ten minutes after the others}

My own view of what is Life, derived from Nathalie’s answer is: life is the ability to gather, exchange, and preserve maximum information.  Very interesting, this answer is not dependent on a CHONPS [2] form of carbon-based life. She also mentioned  life as best way to fight entropy and cited the work of Jeremy England.[3]

A bit later in the interview, Nathalie used a beautiful language analogy to describe life:

[20:52] … languages and they can be very different languages but they all have the same purpose: exchange information, understand, store information and also whether it is with somebody at the outside or thought in yourself; that’s the same thing the cell was doing. 

But now when you’re looking at life and at the structure of our languages life started with an atom so it’s an atom.  They get together to create inorganic molecules then you have complex inorganic molecules. Then you get to organic molecules, complex organic molecules and then you have RNA, DNA etc.  Look at the structure of the language. We created alphabets,  letters, that’s your atom.  Then we put them together to create syllables. The syllables get together to create the words. Words tell you something but they are nothing without the verb that gives the direction that’s RNA and DNA and then you can put all the compliments you want. Our languages are built exactly as life is built. We are repeating patterns.  I call this the Mandelbrot universe and the fractal universe because this is exactly what it is. I would say that as much as I do believe in sending probes to explore the universe I say we should also look inward to find the answers to some of the profound questions of who we are, what’s life, what’s the nature of life because we are expressing life …..

I am more interested in that because the day we understand the nature of life then we have a universal biosignature. It doesn’t matter whether this life responds to the same kind of biochemical processes as we do, although it makes sense. I told you about the generational aspect of the bricks of life: the stuff we are made of the sun is part of the youngest generation of stars and the first two generational stars didn’t produce the kind of elements we are made. [4][5]

The idea that we are repeating patterns built up at multiple levels, like a human language,  really grabbed my attention.  “Our languages are built exactly as life is built. We are repeating patterns.  I call this the Mandelbrot universe and the fractal universe…”  I think we are truly living in something like a fractal universe. I hadn’t heard such an analogy before. [6] 

In a similar vein, it makes sense to me that “the day we understand the nature of life then we have a universal biosignature” because then we have a signal to search for.  But if life is information based, then the signatures may not be biosignatures alone. There could be other technical signatures based on physics rather than biology .[7]


LF – Do we know what complexity is?

NP – in my mind the universe is connected everywhere in all different places so this life connection is something that as you said permeates the universe and the way to find life might be very different than to look for the origins of life 

What I think would be our greatest achievement is that if we can find that process of life because at that point in my mind the universe all of a sudden is going to illuminate itself with actually its  living force, what I can only call a living force to me. This is what we are looking at,  the universe that becomes more and more complex with time, more and more able to gather information and interestingly enough why: to understand itself.  So Sagan was right when he was saying: we are the universe trying to understand itself. [8] And  the more we go, the more the universe becomes alive, maybe intelligent, and maybe also conscious.

Nathalie’s answer made me think of panpsychism [9] – the idea that mind is pervasive in the universe. Another way I think of this is that information processing (a definition of life) is ubiquitous.  When she says: “…. universe that becomes more and more complex with time, more and more able to gather information and interestingly enough why: to understand itself.”; that’s the universe being alive. A bit later she says: “… the more the universe becomes alive, maybe intelligent, and maybe also conscious.” I think this description maps to panpsychism, at least from my shallow knowledge of philosophy. 

 Fermi Paradox

The physicist Enrico Fermi asked: “But where is everybody?” What he was asking was why don’t we see sins of intelligent extraterrestrial life in the Universe. The discussion between Lex (LF) and Nathalie (NC) is illuminating. I have wondered about the same question often, especially when sitting out on a star-filled night. 

[51:26] LF – Everything I’ve seen from life it seems obvious that there’s life everywhere out there in fact maybe I don’t understand the jump from bacteria enough but it seems obvious that there are intelligent civilizations out there now I don’t know how to define intelligence but there’s beautiful complexity. I’ve looked at enough cellular automata which is a very primitive mathematical construction that when you run complexity emerges. I’ve looked at that enough to know that just seems like there’s complexity everywhere out there 

So, I think that’s why I’m deeply puzzled by  the Fermi paradox. It makes no sense to me. I mean I have trivial answers to it: why haven’t aliens at scale not shown up.  I think of  two possible options for me. Either we’re too dumb to see it, they’re already here; they have been talking to us through processes we just don’t understand. what we experience as life here on earth is actually they are everywhere.  Aliens could be consciousness; that when we feel love for one another that could be aliens. When we feel fear or whatever, that could be aliens.

NC – I have to agree with you none of this is scientifically provable right now. We talk a little bit  already about that but I would say that I do not adhere to the Fermi paradox because it’s very anthropomorphic.  It’s an interesting exercise, let’s put it that way but it’s a typical example of seeing the universe through our own eyes. And this is what the limitation is: understanding what’s going on with complexity as you said and looking at the biophysical model and theories for the nature of life. I would agree that probably this extraterrestrial message is all around us. We’re not yet capable of picking it up.

[54:10] Look at the shadow biosphere [11],  the idea that life didn’t appear only once on Earth but there were many different pathways of it. And, today we know when we study the tree of life that led us from LUCA [10]  to us and the shadow biosphere is telling us that there is or there are other pathways that came up at the time where life originated but they are so different that we can not recognize them as being the living.  And we cannot pick them up in our tests because our tests are being built to recognize life as we know it And for me again I don’t know if this theory we’ll be verify or it would be discredited but what I like about it is that it forces me to think on how do I look for life, I don’t know. So that starts here on our planet,  not even with the little green men, it starts with very simple life that can be so different that it might be just right in front of our nose and we don’t see it.

I hadn’t known anything about the shadow biosphere. Are there other forms of life on Earth we haven’t detected? What a good question. If I use the definition that life is the ability to gather, exchange, and preserve maximum information; then the laptop I’m typing on is a form of life. In some sense, I think machines are a form of life – they are obligate parasites of humanity. In other words, machines are organisms that cannot complete their life-cycle without exploiting a suitable host, humans. [13]

Life below the surface of Mars –  Be one with the microbe.  

The section about life below the surface of Mars was educational. Nathalie’s perspective makes sense: “to understand where microbes are located on Mars I have to become the microbe.”

LF – you’ve written about the history of life on Mars. You said you have kind of explored that by looking at the lakes here. Do you think there’s been life on Mars? Do you think there is life on Mars?

NP – … unambiguous evidence of life is going to be something interesting to prove because we don’t know what life is….

Ladder of life detection [14], which is that you have a series of rungs that you know you need to go through that actually are not proving you that you discover life but are making the possibility that what you discovered was made only by the environment more and more improbable. So we are trying to prove the contrary.

… if life appeared I would say it’s still there and probably underground where it can be you know in an environment that’s more stable 

 [1:51] You have to sit and look and listen, basically the story of my life: if I want to understand where microbes are located on Mars I have to become the microbe, this is a thought experiment. And if I want to understand where ET is, then I have to become ET. So,  it’s a big stretch but in an extreme environment you sit in the desert for a while and you just you know try to understand where the winds are coming from, where the humidity is, when it’s showing up and then you start to understand the patterns of those things.

LF – what are the useful signals the need for survival?

NC – You need to know where water is,  what the source of energy is going to be drawn from,  you need to find shelters and shelters don’t mean that…  For instance,  you can have a water column of a lake or a river or whatnot or the ocean. It can be also a very thin layer of dust or it can be a translucent rock. And you see what we call endolith, these are the same cyanobacteria but the different versions of them live inside those rocks, inside those crystals because they have the best of life. They are into translucent crystals so that they receive the light from the sun,  they can do the photosynthesis but there is enough of that crystals so that the nasty UV is being stopped. And they are in their little house. When you are looking at temperature within those rocks they tend to make it toastier [warmer] than the outside temperature.

The endolithic lichen [15] is a hardy  version of biological life on Earth. Life needs water, energy, and shelter. It makes sense that some biological life like  endolithic lichen might exist elsewhere in the solar system.  

Life, Love and the Future

The love for each other and for life was very apparent in the interview.  I highlighted a couple of key points. 

NC – my husband {Edmond Grin} and I were forty four years apart in age and it was just a pure love story. And he never looked at his age, never felt about himself or defined himself by his age. In fact, he reinvented life for himself at an age where everybody retires. We met when he was sixty six and that was a blessing and a curse but a blessing most of it because we took every single day as if it was the last. So we enjoyed life. 

… You know I have to really think of him, he just passed away last August. And for me it’s more like I have to draw from his example on[ of him always telling me: look forward. Trust life. Be happy. Live. You know today, every single day, I have to remind several times a day of this , it’s not easy but he had the recipe. He never thought about death because when you start thinking too much about death that prevents you from living.

LF – what’s the role of love in the human condition?

NC – I think I hope that this is the force that drives the universe though you know we might be experiencing the other side of it maybe just to learn how important love is. 


I would hope for humanity to reach that point where you can feel the same love for the person that is unknown in the street that you feel for the people you love. I think that at that point we are going to be reaching the maturity of that civilization we’re hoping for and seeing the universe through love. That doesn’t run spacecrafts of course but putting love into our intent of going into and settling into another planet instead of “Oh my god, we need to escape because we are freeing, messing up with our own planet.” I think that this is the answer to so many things

NC – …. as the dominant species at least you know technologically etcetera, maybe not the wisest one, but the dominant species. We have a responsibility to watch the entire biosphere because the decisions we’re making now not only affect us; they’re affecting the entire biosphere. And right now the choices we are making are leading to the disappearance of a hundred and fifty species every single day. All the big mammals on this earth today are on the brink of extinction. We are within the sixth greatest mass extinction; it’s unfolding before our eyes. And, I would strongly suggest that we use our smart to help a little bit this situation and we can do this. I think we can do this, we just need to redirect our energy.

Closing Quote

LF –  let me leave you some words from Stanislaw Lem in Solaris: how do you expect to communicate with the ocean when we can’t even understand one another?


I’ve rambled on quite a bit. I haven’t touched on the remarkable research and adventure of Nathalie and her team exploring life in high volcanic lakes [17]. It’s worth listening to this in the interview. Overall, Nathale and Lex covered a lot of ground on just what life might be. 

The most important lessons I learned from Nathalie and Lex in this interview:

  • life wants to get the most information possible around its surroundings and complexities, in fact the ability to gather and exchange and preserve the most information possible.”
    • My own view of what is Life, derived from Nathalie’s answer is: life is the ability to gather, exchange, and preserve maximum information.
  • Our languages are built exactly as life is built. We are repeating patterns.  I call this the Mandelbrot universe and the fractal universe…” 
  • …. the universe that becomes more and more complex with time, more and more able to gather information and interestingly enough why: to understand itself. …. .. the more the universe becomes alive, maybe intelligent, and maybe also conscious.” 
  • …. shadow biosphere is telling us that there is or there are other pathways that came up at the time where life originated but they are so different that we can not recognize them as being the living.
    • Made me think perhaps machines are a form of life – they are obligate parasites of humanity
  •  “… when you start thinking too much about death that prevents you from living.”

I had a quick look at Nathalie’s papers in Google Scholar. I read a bit of the 1999 paper that she wrote with her husband: Distribution, classification, and ages of Martian impact crater lakes. She talked about this, it helped drive the landing site for the Spirit Martian Rover.  Here’s the conclusion:

“These results also confirm that ancient lakes in impact craters are important sites to study on Mars. They collected the record of the climatic and hydrogeologic changes on Mars. They were the receptacle of sedimentary rocks from which critical information about weathering, chemical, and physical processes on Mars could be learned. They might as well be among the most promising sites for the search for life and/or precursors of life on Mars. Lacustrine deposits are well known to be favorable environments for the preservation of life (extant and/or extinct). Lakes provide the best conditions for fossilization processes. The absence of crustal recycling on Mars opens up the possibility that fossilized life forms could be exposed right at the surface of the crater floors. The dataset resulting from this study is aimed at providing information to help identify the potential best candidates.”

I also saw a current research project that Nathalie is associated with, summarized in the paper:

“Orbit-to-ground framework to decode and predict biosignature patterns in terrestrial analogues”  I should give this paper a read and see what I can decipher – and learn. It’s interesting to glean that the team used artificial intelligence methods to look for biosignatures in Chile as a surrogate for Mars. [17] 


[1] Nathalie Cabrol: Search for Alien Life | Lex Fridman Podcast #348 Watched in January 2023

[2] CHONPS carbon, hydrogen, oxygen, nitrogen, phosphorus, sulfur: the main elements that occur naturally in carbon-based living systems on Earth. 

Accessed 9 April 2023

[3] Jeremy England has a YouTube video explaining his work 

How Thermodynamics Explains the Origins of Living Things and is the author of a 2020 book: Every Life Is on Fire: How Thermodynamics Explains the Origins of Living Things

[4] I did some editing of this section, I hope I did not alter the intent of what Nathalie said. 

[5] One example is the iron atoms in our hemoglobin, I remember thinking about this in biochemistry class. The origin of iron:

“Stars fuse light elements to heavier ones in their cores, giving off energy in the process known as stellar nucleosynthesis. Nuclear fusion reactions create many of the lighter elements, up to and including iron and nickel in the most massive stars. Products of stellar nucleosynthesis remain trapped in stellar cores and remnants except if ejected through stellar winds and explosions. ” Accessed 9 April 2023

 Or as I remember Carl Sagan explaining in Cosmos:  “we are star stuff.”

[6] John 1:1 KJV: In the beginning was the Word, and the Word was with God, and the Word was God.  Accessed 9 April 2023

[7] Technical signatures are discussed in David Kipping: Alien Civilizations and Habitable Worlds | Lex Fridman Podcast #355 

[8] “The cosmos is within us. We are made of star-stuff. We are a way for the universe to know itself.” as stated by Carl Sagan in Cosmos: A Personal Voyage, Ep. 1

[9] “In the philosophy of mind, panpsychism  is the view that the mind or a mindlike aspect is a fundamental and ubiquitous feature of reality. Accessed 9 April 2023Accessed 9 April 2023

[10] Fermi paradox 

[11] What is  last universal common ancestor (LUCA)?

“The last universal common ancestor (LUCA) is an inferred evolutionary intermediate that links the abiotic phase of Earth’s history with the first traces of microbial life in rocks that are 3.8–3.5 billion years of age. Although LUCA was long considered the common ancestor of bacteria, archaea [a] and eukaryotes newer two-domain trees of life have eukaryotes arising from prokaryotes,making LUCA the common ancestor of bacteria and archaea. Previous genomic investigations of LUCA’s gene content have focused on genes that are universally present across genomes, revealing that LUCA had 30–100 proteins for ribosomes and translation. In principle, genes present in one archaeon and one bacterium might trace to LUCA, although their phylogenetic distribution could also be the result of post-LUCA gene origin and interdomain lateral gene transfer (LGT), given that thousands of such gene transfers between prokaryotic domains have been detected.”

Weiss MC, Sousa FL, Mrnjavac N, Neukirchen S, Roettger M, Nelson-Sathi S, Martin WF. The physiology and habitat of the last universal common ancestor. Nat Microbiol. 2016 Jul 25;1(9):16116. doi: 10.1038/nmicrobiol.2016.116. PMID: 27562259  . PAYWALL 

“All known life forms trace back to a last universal common ancestor (LUCA) that witnessed the onset of Darwinian evolution. One can ask questions about LUCA in various ways, the most common way being to look for traits that are common to all cells, like ribosomes or the genetic code. With the availability of genomes, we can, however, also ask what genes are ancient by virtue of their phylogeny rather than by virtue of being universal. That approach, undertaken recently, leads to a different view of LUCA than we have had in the past, one that fits well with the harsh geochemical setting of early Earth and resembles the biology of prokaryotes that today inhabit the Earth’s crust.”

Weiss MC, Preiner M, Xavier JC, Zimorski V, Martin WF (2018) The last universal common ancestor between ancient Earth chemistry and the onset of genetics. PLoS Genet 14(8): e1007518.

[a]  Carl Woese is famous for defining the Archaea (a new domain of life) in 1977 through a pioneering phylogenetic taxonomy of 16S ribosomal RNA, a technique that has revolutionized microbiology.  Accessed 9 April 2023

[12] A shadow biosphere is a hypothetical microbial biosphere of Earth that would use radically different biochemical and molecular processes from that of currently known life. Although life on Earth is relatively well studied, if a shadow biosphere exists it may still remain unnoticed, because the exploration of the microbial world targets primarily the biochemistry of the macro-organisms. Accessed 9 April 2023

[13] I modified a sentence from the Wikipedia article on Obligate parasites: “An obligate parasite or holoparasite is a parasitic organism that cannot complete its life-cycle without exploiting a suitable host. If an obligate parasite cannot obtain a host it will fail to reproduce.” Accessed 9 April 2023

[14] …. Ladder of Life Detection, a tool intended to guide the design of investigations to detect microbial life within the practical constraints of robotic space missions. To build the Ladder, we have drawn from lessons learned from previous attempts at detecting life and derived criteria for a measurement (or suite of measurements) to constitute convincing evidence for indigenous life. We summarize features of life as we know it, how specific they are to life, and how they can be measured, and sort these features in a general sense based on their likelihood of indicating life.

Neveu M, Hays LE, Voytek MA, New MH, Schulte MD. The Ladder of Life Detection. Astrobiology. 2018 Nov;18(11):1375-1402. doi: 10.1089/ast.2017.1773. Epub 2018 Jun 4. PMID: 29862836; PMCID: PMC6211372. 

[15] Here’s a good reference: Alteration of rocks by endolithic organisms is one of the pathways for the beginning of soils on Earth 

[16] Here’s a link to some info  Accessed 9 April 2023

[17] Warren-Rhodes, K., Cabrol, N.A., Phillips, M. et al. Orbit-to-ground framework to decode and predict biosignature patterns in terrestrial analogues. Nat Astron (2023). PAYWALL

 I got the reference from a press release