Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas - AMA | February 2023

Episode Date: February 6, 2023

Welcome to the February 2023 Ask Me Anything episode of Mindscape! These monthly excursions are funded by Patreon supporters (who are also the ones asking the questions). We take questions asked by Patreons, whittle them down to a more manageable number — based primarily on whether I have anything interesting to say about them, not whether the questions themselves are good — and sometimes group them together if they are about a similar topic. Enjoy! Support Mindscape on Patreon. The big news this month is the successful awarding of the first ever Mindscape Big Picture Scholarship. Congratulations to Lyat Melese and Rehman Hassan! We continue to collection donations for next year's scholarship contest.

Struggling to see up close, make it visible with Viz. Viz is a once daily prescription eye drop to treat blurry near vision for up to 10 hours. The most common side effects that may be experienced while using Viz include eye irritation, temporary, dimmer, dark vision, headaches, and eye redness. Talk to an eye doctor to learn if Viz is right for you. Learn more at Viz.com. Wellness looks different at every stage. The right support makes all the difference. Shake up your routine with vital proteins, collagen peptides.

The 20 grams of collagen source from grass-fed, pasture-raised bovine. It helps support healthy hair, skin, nails, bones, and joints. Made with no artificial sweeteners, a clean way to fuel your body. So your wellness stays effortless wherever the day takes you. Vital Proteins. Stay vital. Visit Vital Proteins.com and get started. These statements have not been evaluated by the Food and Drug Administration.

These products are not intended to diagnose, treat, cure, or prevent any disease. Hello, everyone. Welcome to the February 2020 edition of the Mindscape Podcast. I'm your host, Sean Carroll. As usual, we skipped January, Ask Me Anything. So we've accumulated quite a bunch of questions here for this. February one, I had to be a little severe, a little harsh in cutting down the questions to a reasonable size. So I do apologize to all the people who ask perfectly good questions who are

going to get ignored. The other thing to mention is that we've been doing the AMAs for a while now. And as a result, there are questions that I've answered more than once, or very, very similar questions. And I'm torn by this, because on the one hand, not everyone has listened to every single AMA or was not there in the early days. On the other hand, the people who are don't want to hear the same discussion over and over again. So I kind of pick and choose. If there's a question that I'm pretty sure I've talked about before, I will be less likely to answer it. But if there's something I can say that might be new or interesting or whatever, then I will nevertheless consider it. So don't be completely discouraged from doing that. I do have one piece of very good news to

share with everyone. You might remember that we had a scholarship competition at bold.org. You can see what was going on there at bold.org slash scholarships slash mindscape. We had the Mindscape, big picture scholarships, which give $10,000 to the winners to help defray the costs of going to college and studying something in science or philosophy or math or whatever it is that constitutes thinking about the biggest ideas in the universe, broadly speaking. And I was very happy that We raised so much money for this that we were able to give two $10,000 scholarships, and we've chosen the winners. And I'm very, very happy to announce that the winners are incredibly deserving students who are in

high school now. We'll be going to college. One is Raymond Hassan, who wants to be studying biophysical sciences, different kinds of biology. Both students are more biological than physics. That's okay. That still counts as a big picture in my book, as we know. from the fact that we have lots of biologists on the podcast. Anyway, Raymond is an amazing student

who is the founder of IQ Health, which has now over 30 international chapters that have helped 45,000 people to ensure everyone has access to quality public health knowledge and preventative care services. And this is while they were in high school. And they've become an adolescent champion of the World Health Organization and a whole bunch of other wonderful accomplishments, wrote a wonderful essay and is a very deserving winner here. The other winner is Liot M-A-L-M-E-E-S-E. I'm not actually sure that I'm pronouncing her name correctly, M-E-L-E-S-E, who is also interested in studying neurobiology and cognitive science kinds of things.

And again, extremely impressive high school resume, working at Virginia Tech in the lab, designing studies to study how impulsive neurological behavior, behaviors, play a role in diabetes, self-regulation, a published author in the New York Times. I don't know. I don't know what I was doing back in my high school days, but not stuff that was nearly that impressive. So I'm very, very happy to announce both of those winners of the Mindscape Big Picture Scholarship

and extraordinarily thankful to all the Mindscape listeners who have donated. You don't have to be a Mindscape listener to donate, but you are the primary target audience for my solicitations. And we're doing it again next year. So we already have enough money in the scholarship fund to give away at least one more scholarship next year. And we're going to continue to remind you that you can donate and maybe more and more students will win. And that will maybe help someone who might not have been able to study these kinds of things in college. So that's bold.org slash scholarships slash mindscape.

Anyway, that was the big announcement I wanted to make. Remember that these AMAs are funded by Patreon supporters of Minescape, and you can be a Patreon supporter if you want. All you have to do is go to patreon.com slash Sean M. Carroll, pay a dollar or $2 or $5, whatever you want per episode. And then you get ad-free versions of the episodes as well as the ability to ask questions for the AMAs. I do try to eventually hit everyone who asks the question, but as I just said, can't get to all the questions these days. Too many good things to say. And with that, let's go. First question is from Peewee Munster, who let me talk a little about what the question is before I ask it.

So the big news that has happened in our kinds of interesting questions around the world in the past month or so has been a dramatic leap forward in these artificial intelligence programs that have been going into the public domain so anyone can play with them. There was Dolly that was making images. Chat GPT is one that will respond to prompts that you give it and give back text responses that will more or less sound like what do you want to do. The great thing about chat GPT is not only can you say, you know, explain to me the many worlds interpretation of quantum mechanics, but you can do so in different styles, right? You can say, explain to me the many worlds interpretation of quantum mechanics in the style of Ernest Hemingway. And chat GPT will do that. And it's really an incredible kind of thing to play with and to learn what it will do. And there's been some controversy, but both excitement and controversy.

The excitement is clear because this is a step forward in artificial intelligence and where will it go? What will it be used for, right? Is it going to replace a lot of people who have jobs that, you know, don't require heavy lifting. If you can just do them by artificial intelligence, professors, of course, immediately panicked that students are just going to use this to write their essays, and that's going to make evaluating essays a lot harder, a lot papers and things like that. I don't know about that.

I don't know whether I'm going to worry about that too much. But certainly there are going to be tremendous ramifications of this. One ramification is, at what point do we declare the Turing test to have been won, right? The Turing test proposed by Alan Turing was that an artificial computer intelligence would be conscious by human standards once it can fool. a human being into thinking that it really is a human being. I'm not sure if that's the best test, to be honest, but it gets across some of the thing that we would want out of artificial intelligence to sound human enough to pass for human. And in some sense, things like these large language

models constructed by machine learning techniques like chat GPT pretty clearly could pass a test like that. So the question is, you know, do they count as conscious or aware? And there are some people who want to argue that they do. They clearly don't, by the way. That's the answer. They are not. They're certainly not conscious. And this question that Pee-Wee Munster asks actually gives a wonderful way of illustrating that. So what Pee-wee says is, I was going to ask the obligatory question on chat G-PT, but then realize I don't have to, I can just ask chat G-G-T. So what Pee-B did was asked ask chat GPT three different questions and asked the computer to answer them in my voice, right, in the voice of Sean M. Carroll. And so let me just read you the three questions and the three

answers because I think they do together a remarkably good job of illustrating both the impressive and not so impressive aspects of this kind of technology. So one question is, this is a prompt to the chat GPT. Okay, so the prompt is, you are the renowned physicist Sean M. Carroll, and you are hosting the Ask Me Anything episode of the Mindscape podcast. A listener asks you what you think of chat GPT.

As Sean M. Carroll, how would you respond? And then chat GPT responds. As a physicist, my primary area of expertise is not in artificial intelligence or natural language processing. However, I am aware of the recent advancements in GPT-based language models like chat GPT. I find it fascinating how these models are able to generate human-like responses to a wide range of prompts. However, I also recognize the limitations and potential dangers of these models,

such as the risk of them amplifying biases and misinformation. Overall, I think it's important to approach these models with a healthy dose of skepticism and critical thinking. So let me just very quickly say, before going on to saying other things, this is the real Sean now talking. What is real, anyway? This is the real host of the podcast talking. This is very typical of chat GPT's answers whenever you ask it to evaluate something. It's always pretty wishy-washy.

It's always like, well, I don't know, there's arguments one way or the other. You get that a lot. So let's think about that and keep that in mind while I read the next prompt. The next prompt is another listener asks, how did you meet your wife? As Sean M. Carroll, how would you respond? The response is, as Sean I'm Carol, I would respond to my wife and I met in graduate school at the University of Chicago. We were both studying physics and our paths crossed in various classes and research groups.

We quickly became friends and eventually started dating. It's been a wonderful and exciting journey ever since, and I'm grateful to have her by my side in both my personal and professional life. So whether you know or not, let me just be very clear, all of that is complete nonsense. That is utterly wrong. It's very convincingly said, and it's a very reasonable set of things, but no relationship whatsoever to reality. My wife, Jennifer, we did not meet at the University of Chicago. I was never in graduate school at the University of Chicago. I was a professor there. Jennifer was never affiliated with Chicago at all. Jennifer was never a graduate student in physics. Our paths did not cross in classes. This is all entirely made up, okay? No connection

to reality. The final question was, another listener asks, what is your favorite pizza? As Sean, M. Carroll, how would you respond? And the response is, as Sean M. Carroll, I would respond that my favorite pizza is a classic margarita pizza. I love the simplicity of the ingredients, with fresh mozzarella, tomatoes, basil, and a drizzle of olive oil. It's a pizza that really highlights the quality of the ingredients unless the flavors shine through. I also enjoy trying new and unique pizzas, but for me, the margarita will always hold a special place in my heart. You know, one impressive thing, by the way, that's actually very subtle here, is the consistency. of the answer from the beginning to the end, okay? So the answer is margarita pizza, and at the end,

you know, it's still margarita pizza. It's not just like a random collection of words. However, once again, entirely wrong. No connection to reality here. Margarita is not my favorite pizza. I have no problems with a good margarita, but my favorite kind of pizza would absolutely involve pepperoni in some way or another. And so that's why I love all of these answers here. None of them are right. None of them are what I would actually say. And it's weird to me to see a whole bunch of people online saying like, this replaces Google for me now.

This replaces Wikipedia. Just ask chat GPT my questions. Chat GPT is very good at constructing sentences that sound cogent and human made. It's not good at all at telling you the truth. It is, I admit that when you use a large language model like this, It can seem really, really impressive and almost as if it has a mind of its own. It can seem very human. Why is that?

Well, the way that these things work, to hugely oversimplify a very complicated thing, is large language model means you feed it a lot of language. You have a machine learning algorithm, and you just feed it an enormous amount of text, okay, of words that seem to fit together in certain ways. The large language model has zero understanding. It does not know what pizza is. It does not know what a margarita pizza is. It does not know what to be married is or a spouse or a graduate school

because it doesn't know anything because it doesn't have any concepts in its brain. And this is a fascinating philosophical question, of course. And that's why I think that these kinds of artificial intelligence attempts are really going to help us understand what we, mean when we talk about to know, to understand, to have concepts. But the point is that when you and I talk about a spouse, okay, that's a concept and it comes along with different associations, you know, like generally people have one spouse, not 20, people don't have negative numbers of spouses. There's no such set of information in chat GPT. What chat GPT is doing is looking at

what words tend to appear next to what other words or what other sentence structures appear next to other sentence structures. So if you go back to the How Did You Meet Your Wife question, as Sean M. Carroll, I would respond to my wife and I met in graduate school at the University of Chicago. We were both studying physics and our path cross in various classes and research groups. We quickly became friends and eventually started dating. That's no relationship to the truth of how I met my wife. But it all sounds very reasonable for how someone might be. meet someone's wife. And there's little details in there about studying physics and Chicago that are associated with me, but none of it fits together to tell the truth. Okay. It's just the

machine learning algorithm is noticing that these kinds of phrases and words fit together very frequently and it's doing its best job. By the way, there's some random numbers thrown in there. So if you ask the same question again, it wouldn't give you necessarily exactly the same answer. And that's a huge difference. This idea of looking at what words come together versus actually having a conceptual, symbolic understanding of the world, having a model of the world, and using that to better understand what is happening in the world is a vast gulf. So I think that things like this, chat GPT and its relatives are extremely, extremely important and extremely illustrative. I think that they're nowhere close to true artificial general intelligence,

but they're clearly super duper good at mimicking intelligence. That's the important thing. That's the important thing to notice about this. It's not that we're anywhere close to artificial general intelligence, but that we can trick you into thinking that we are. We could easily program these things to answer phones, to answer emails, et cetera, right, in ways that you would think you were getting a response from a human, much better than we're doing today. But not one right now in the state of the art where you would be confident they were telling the truth or be on the right track. And they don't know that they're making these very basic mistakes. I mean, there's lots of examples online that you can go search for where, you know,

chat GPT will say with absolute sincerity, exactly the opposite of the truth. So I think it is very important, very interesting. It's going to have huge ramifications for the future. I do not think it is a substitute for actually doing research on anything. Certainly not a substitute for true knowledge in any sense. But it's just very early days. The amount of progress that's going made is going to be considerable. Okay. And so I sort of buried from some other chat GPT questions that were there, thinking that that particular discussion would give you most of my opinions about these things. Nikola Ivanov has a priority question. So you remember, again, if you're a longtime listener, there's something called the priority question. So if you

have a question that you really, really want to answer, once we instituted the idea that I'm not going to answer all the questions. For every Patreon supporter, you have once in your life the ability to ask a priority question, and I will answer it. I will do my best to answer it. Look, I might misunderstand the question. You don't get to keep asking the same question over and over again. You get a one priority question, I do my best to answer it. That's how it goes. So Nicholas' priority question is, in your podcast with Penrose, when discussing the low entropy hypothesis for the beginning of our universe, you commented that the fact that the CMB spectrum matches that of a black body, i.e. already has maximum entropy, does not violate this hypothesis because there's already a gravitational

entropy, which was low, and that was not taken into account. My question is, what is this gravitational entropy at the time of the Big Bang? It can't be the entropy of primordial black holes, since they also have very high entropy. And should we understand the low entropy hypothesis that relating only to the gravitational entropy and not the thermodynamic one? Let me emphasize that there is no clear, rigorous division of entropy into gravitational and other forms, okay? This is a very, very loose way of talking that gives some physical insight. The point is that the correct absolute thing to say about the early universe is that the entropy was low.

Full stop. That's the correct thing, okay? There's no sense in which the entropy was high. But then we do try to give some understanding to that true statement. You know, in what way is the entropy? low. There's only one way for entropy of a system to be very, very high. You're in equilibrium, and there's a unique sort of equilibrium state. But once the entropy is low, there's many different ways for the entropy to be low. So we have to ask about the early universe, what is this

specific kind of low entropy state in which it started? And for what it's worth, for whatever reason that we don't know, the specific way that the early universe started is that the space time was nearly flat. Sorry, I shouldn't say space time because it was rapidly explaining, but space was nearly flat. It was extremely smooth. It was extremely homogeneous, okay? And that's, and the stuff inside, at least at the moments when we have observational access to it, the matter that was populating that nearly flat space was thermal at a black body radiation. So this is very specific and very provocative to physicists, okay? It's low entropy. because in a universe with gravity, like ours,

densely packed material will be high entropy when it's lumpy, not when it's smooth, okay? You know, black holes surrounded by empty space or a collection of black holes with empty space in between them, that's what high entropy would be like, and the early universe was nothing like that at all. It was very, very low entropy. However, weirdly, interestingly, if you think about a situation where, is not that important, like a box of gas in a container here on the surface of the earth. Gravity is pulling it down, of course, but the internal gravity of the gas inside is just not that big a deal, right? There's just not that much stuff, and gravity is a weak force.

If you have that very different kind of situation and you ask what the high entropy equilibrium state would look like, it would be a thermal distribution. It would be black body radiation being emitted by thermal distribution of particles. So the weird thing about the early universe, there's two weird things. One is that it has low entropy. I mean, there's many weird things, but in this question, one, it has low entropy. Two, the specific way in which it has low entropy seems to be what would look like high entropy if it weren't for gravity. Okay? What does that mean? I don't know. We don't know. We don't know why the early universe had low entropy. We don't know why it takes that specific form. It's provocative, and you know, there's sort of

some obvious things to try. One thing to try is, can you just imagine turning off gravity in the early universe so that it went to a high entropy state that looked thermal, and then you turn gravity back on. Brian Green and some of his collaborators, Brian was a former Minescape guest, tried that. They actually wrote a paper literally about that possibility, so you can check that out. I don't really think it works, that specific scenario, but, you know, it's a natural thing to try. Roger Penrose has his own ideas about how to specify it. To me, Penrose's ideas are more about, once again, characterizing the way in which the early universe has low entropy

and less hopeful in actually providing an explanation for why. So it is the entropy that is low, and there's no different kinds of entropies, but there's some rough explanation, some intuition that we get by thinking about a separation between gravitational and non-gravitational entropy. Hey, everyone. It's Cal Penn.

I'm the host of Earsay, the Audible and I Heart audiobook club. This week on the podcast, I am sitting down with Ray Porter, the narrator of Andy Weir's audiobook Project Hail Mary, massive sci-fi adventure about survival and science, and what happens when you wake up alone very far from Earth? I really had to make a decision because I caught myself getting that frog in my throat and starting to get teary

as I'm narrating some of these sections, and it's like, okay, yo, yeah, yo, is this indulgent? And I really thought about it. I was like, no, at this point, it would kind of be betraying the trust the author and the listener have in telling this story if I don't go through it. But there's places in this book that deeply emotionally affected me. And I left it on the mic. That's great. Because it served the story.

People will say like, oh, my God, I cried at the end. It's like, yeah, dude, me too. Listen to EIRSA, the Audible and IHeart Audio Book Club on the IHeart Radio app or wherever you get your podcasts. My best skin ever at 45? Give me a theme song and a best skin care award because it feels like this. Right there. That's farmhouse fresh skin, all right? I'm glowing and everyone asks how.

The best skincare is farmhouse fresh and the award is you, your best you. Visit farmhouse fresh skin care.com and use code radio for a free starter routine with any purchase. Larry Rossi says, I must confess that I sometimes listen to the Mindscape podcast when I cannot sleep. This is not to say they are boring. The exact opposite is true. My brain is distracted and spinning through many worlds, the arrow time, or whatever the topic is,

and I'm out. Do you ever struggle to sleep? And if so, what helps you? So, I mean, I need to comment on the listening to Mindscape when you go to sleep stuff. That's fine. I love it. People have said many, many times that they listen to Mindscape while going to sleep or they listen to the biggest ideas in the universe videos or something like that. I mean, I don't get it.

I don't understand because if I were doing that, the things I was listening to, I would start thinking about and that would prevent me from going to sleep. If I can't get to sleep, it's because I'm thinking about something and I can't stop thinking about it. Now, having said that, you know, it's well known. I'm not to give breaking any psychological growth. ground here, but you can fall into a rut thinking about something, right? I mean, you can think about something and maybe your thoughts are not that productive. Maybe you're not really making any progress, but you just can't stop thinking about the same thing over and over again, right? You had a conversation, you said something dumb, and you're replaying the conversation in your mind, and in your replaying

of the conversation, you are brilliant and witty and everything that you say is not embarrassing at all, right? So that's the kind of thing that just keeps your mind locked into a ruck. and then that makes it hard to sleep also. So it used to be that I did struggle to fall asleep, and then once I fell asleep, I was out. Still more or less true that once I fall asleep, I'm out. I'm a sound sleeper once I get to sleep. But, you know, and again, this is not any genius breakthrough.

I just realized that I was probably going to bed too early. Like, it works for me to just stay up until I'm super tired, and then I will fall asleep. So, you know, I'm working hard enough these days, and I go to bed late enough that I don't really have. trouble falling asleep anymore. I don't really have any more wisdom than that. This is certainly something where I suspect that the way to think about it is that different people are very different from each other. So if you read about a way to help you fall asleep and you try it and it

doesn't work, I wouldn't be too depressed by that or disappointed. I would just try other ways. I think different people are just different there. Brian Mapes. So I have two questions in a row here, both about the Lara Bouchak episode that we had on Minescape recently, but there's slightly different questions, so I'm going to not group them together. I'm just going to read them in order. So Brian says, from the utilitarian ethics of the Lara Buchak episode, to your discussion of fitness landscapes and the rise of machine learning and artificial intelligence, the very concept of optimal has started to seem problematic to me.

Because inequality only has meaning on the number line, there is always a single scalar ruling everything. Even if it is some complicated risk-adjusted, weighted some of multiple virtues or costs or penalty, so many worlds for this one thing. The question is, do you think this is a blind spot or weakness for science and rational ethics and so on? Could you imagine some sort of alternatives, some calculus of good enough, that isn't such a slippery slope to an optimum whose unitary nature cementes us into possibly dystopian hazards for a polyvocal multi-agent world full of uncertainties? So I think that there's actually two different things going on here that are both interesting and important, but worth teasing apart a little bit.

One is the existence of thinking of some decision procedure as optimizing some number. That can seem that kind of thing where you, you know, it's certainly what utilitarians do, right? Utilitarians say there is a number called the expected future utility of your actions and over the space of all possible actions. we would like to maximize that number. That's what we want to do. We want to optimize our actions to increase this particular number. But other moral strategies don't seem that way, right? In a deontological strategy, your idea is to follow certain rules,

not to calculate a certain number and optimize it. In a virtue-ethic strategy, your goal is to be virtuous in certain ways, again, rather than adding up a number. I think that that particular distinction is a bit fake, okay? It's true that utilitarians explicitly optimize a number, but I also think it's true that everyone optimizes a number. In other words, maybe they don't think that they're optimizing a number, but anything that you do, any procedure that you can invent for making decisions, can be thought of as maximizing some quantity, okay? If you're a utilitarian and you, or a deontologist,

rather, and you say, never lie. Okay, well then, attach a number one or number infinity to all the true things you say, a number minus infinity to all the false things you say, and you try to maximize that number, right? That's not a convenient or useful way of thinking about it, but you can always think about it that way. So I don't think that there's any inherent problem in the idea that we should optimize a number, that we should maximize a number, that we should optimize some strategy, anything like that. It may not always be the way we think, but we can always formally map the way that we do think onto that kind of strategy. The second aspect you're saying here is, okay, given that we're trying to maximize a quantity

or optimize a number, how strict should we be about actually optimizing it? Like you say, is there some calculus of good enough? And in fact, there absolutely is. This is something that people have very much put thought into. to. That is where the satisficing comes in, which I think I talked about with Lara. I've talked about on the podcast other times, though. By the way, parenthetically, one place I talked about that idea was with Herb Gintis, the economist, who sadly passed away recently. As far as I know, he's the first mindscape guest to have passed away since being on the show. So it was a really

great episode about game theory and evolution and human beings and how we construct our social lives using game theory kind of things. And Herb was very clear that we are constrained, or what is the technical term here? We're limited in our capacity to do reasoning and information processing, right? So it's not constrained, but there's some phrase that I'm forgetting. Sorry about that. Bounded computation, is that it maybe? We're bounded in our abilities to both collect information about the world and then to process that information. So in practice, even if we think that the right thing to do is perfectly well expressed by optimizing some number, in practice we never really do that. And, you know, if you go back to Carl Fristin's episode where we talked about the Bayesian brain and the free energy principle,

one of the big things in Fristin's approach is that in principle, the human brain would like to build the best possible model of the world. And the way to build the best possible model of the world, as we know, is to be a good Bayesian, to take the priors that we have and update them when information comes in. And you can write down Bayes' formula, and it's actually a very short, easy-to-remember formula. But calculating it carefully and in real time actually turns out to be very difficult. So the free energy principle that Fristin looks at is a way to get approximate Bayesian updating in a very rapid period of time. And I think that something like that satisfying good enough is always what we do. And so I think that you're right, your implication is correct, Brian, that we should be more admitting of that. We should be aware of it, right? The philosophy of how we should act, how we should be moral, what decisions we should make should do a better job. People do talk about this, but maybe not as much as they should, the fact that we are not perfect reasoners or in possession of perfect knowledge. about the world, I think, yes, we do need to take that into account.

I don't, I'm not quite sure what the possibly dystopian hazards are that you're, that you're referring to. You know, I think the dystopian hazards come more from having a bad thing that we're trying to optimize rather than trying to optimize something at all. Janice or Janice Funk says, in episode 220 with Laura Buchak, when considering from a many world's perspective, whether you would rather give a hundred future possible shans a million dollars, or give 98 of them a million dollars and giving one of them nothing, sorry, giving, oh yes, giving 98 of them a million, giving one of them nothing, and one of them 20 million. You seem to suggest that these different versions of shans need to be treated like a hundred strangers. While I agree that

you are not the same person as the shans in other branches, all these possible shans will remember having made that decision for themselves. Don't you think their complicity in the decision changes the moral situation compared to a scenario where you get to distribute money from non-complicit strangers, among non-complicit strangers? So I'm not exactly sure what to say here. I mean, I think you're on to something, but I'm not quite sure that it matters in this case. I might be misunderstanding or misreading here.

So let me just say what my thoughts are. So, again, just to be clear, because maybe I read it a little bit too quickly or awkward. We're trying to decide between two different ways of distributing money. You have 100 people give a million dollars each. That's one way of doing it. The other way is you have 100 people give 98 of them a million, one of them zero, and one of them 20 million. So there's more being given away in the second scheme, but it's a little bit more unequal, a little bit less fair, right, because someone's going to get nothing.

and the question is that I'm treating the different versions of myself like strangers and don't, I think, that the complicity and the decision changes the moral situation. So I'll absolutely confess I forget what I said in real time in the episode. So they're not, I don't think that strangers is the right way to put it. So I'm just going to try to say true things now. I'm not going to necessarily try to fix what I said then. they're different people and they're people who will never talk to each other, but you're certainly right in that they share memories, right? So the decision that was made that they need

to live with the consequences of is absolutely a decision that they made. That's very true. So if the question is, does it matter whether one makes a decision for oneself or for others, in principle, yeah, it absolutely could. I don't think it does very much in this case. So if you, because look, I don't think that the many worlds thing matters that much in this kind of analysis. I think many worlds is just a distraction. Just think of it in terms of probabilities. And I think it's exactly the same analysis, whatever that analysis is.

Okay. So if you say 98 people get a million dollars, one gets 20 million, one gets zero, to me, that's exactly equivalent to saying there is a 98% chance that I will get a million dollars, a 1% chance I get nothing and a 1% chance I get 20 million. Okay? Whatever the answer is in one of those cases, it's the same in the other one. And I forget what I said. I think that I would, I really don't know. I can see arguments for either way. I'm probably going to go for the 20 million,

that the 1% chance of the 20 million. I hope I'm consistent in what I said, but maybe not. Maybe I've updated my beliefs. I guaranteed 1 million is nice, but a 1% chance of winning 20 million versus 1% chance of zero, maybe I go for the 20 million.

If I were destitute and poor, maybe I would feel very differently about that, okay? So certainly in those kinds of questions, I think that if one has the chance to give the people who are getting the reward the ability to choose rather than me doing the choosing, then yes, you should do that. You should listen to what the people want. So I guess, and this is one of Laura's points, is that it is absolutely okay that different kinds of people have different risk tolerances. So the point about the question, 100% chance of 1 million versus 98% chance of a million, 1% chance of 20, 1% chance of

0, by the way, you could also contrast that with, forget about the people who get a million, they're all just the same, 100% chance of getting a million versus 50% chance of getting 20 and 50% chance of getting zero, right? That's another comparison you could do. But anyway, Laura's point is, it's okay to have different risk tolerances about this. There's not a one unique answer to which you should prefer on the basis of rational choice theory. It is okay to say my preference is not to risk it and go for the 100% guarantee of a million. It is also okay to say, let those dice roll and give me the 50-50 chance of 20 million versus zero. So therefore, yes, if I interpret the question as saying, does it matter that you give people their choice

about which bargain to accept? Yes, it does matter a lot because you know what their preference because they know what their preferences are. In the case of me doing it with, you know, my future selves in the multiverse, then I am doing it. And so that's okay. So I don't think that any of the future selves would have any right to complain. If that's, like, that's the bottom line, right? As long as I'm making the choice now, there's 100 future selves, I have to live with the consequences. None of them has a right to complain. And it's exactly the same with 100 real ones in the multiverse versus a 1% chance of a hypothetical one in a single universe with truly stochastic choices. Okay, Eric Dovigy says, the universe is 13.8 billion

years old. How much longer will Earth-like planets, and thus the possibility of Earth-like life, be able to form? If it is a very long time, isn't it remarkable to find ourselves alive at such an early stage of the universe? In other words, does the Copernican principle apply to where we are in the timeline of the universe or doesn't it? So I think the Copernican principle is pretty much nonsense, to be honest. Let's say that. I did a whole podcast episode about the philosophy of the multiverse where I talked about this a little bit. but I think there are good questions to ask about this because, you know, in exactly this case,

it's a very good question, by the way. So how do we think about the Copernican principle, which says we're not special in the cosmos, right? Does that mean that every year of the history of the universe is created equal, or does it mean every person in the history of the universe is created equal? by personally mean some very accepting notion that smart aliens count or whatever. What if they have a collective intelligence, though? So there's a trillion organisms, but they only have one intelligence.

Do they only count once? Or do they count a trillion times? It's a little ill-defined. It's more than a little ill-defined. It's utterly ill-defined. But putting that on the side, I just want to get that off my chest, but then try to answer the question. I believe, and I'm not, you know, despite appearances really professional astronomer, but my recollection is most stars that will ever form in the history of the universe have already formed.

I think maybe that's accurate, but I think the more accurate thing to say is the peak era of star formation is in the past, not the future. I mean, it's possible because there's an integral here, right? So it's possible that the rate of star formation has peaked, but nevertheless it will putter along at some low rate for a very, very low time, and we'll still get more stars in the future. So I'm not sure about that. But the point is that, to answer the impression that you have, that it's a very long time in which Earth-like planets are going to be able to form, probably not.

We don't think that that that is true. We don't think that there's going to be, you know, the universe is 13.8 billion years old. We don't think that Earth-like planets are going to be forming at this kind of rate that they have been for the next 100 or 1,000 billion years. That's not what we think. The universe is slowing down quite dramatically. Now, from some purely physics-based perspective, there's no reason to think that the universe won't just keep expanding forever.

And the fact that we're in the first 13.8 billion years of its life is very, very short, right? It's very, very early in the history of the universe. Not early in the history of star formation, but that's hard to take into account, as I just said. So I don't, I think it's maybe a little bit strong to say that it's remarkable. there certainly is plenty of opportunity to have had intelligent life already form. You know, in some sense, I think you could make the argument that we're pretty late in the likely to form life stage of the universe's history.

And this is part of the problem behind the Fermi paradox, right? Why haven't we met other intelligent aliens? Five billion years after the universe formed, I think that it would have been plenty of opportunity. to have intelligent life come along. And we're more than 8 billion years after that. So that is something to think about. So I think all these things are things to think about. I think the mistake would be to decide ahead of time

that you know what the distribution should be and think that it's remarkable that the reality doesn't fit it. I think that it's more sensible just to keep in mind how much we don't know about these questions and to note how different things could have been. Okay, so it is true that it's 13.8 billion years after the beginning of the universe or after the Big Bang anyway. So could life have started earlier? Could it start later?

Under what conditions could it have started? Those kinds of things it is worth looking at rather than just saying, well, we started 13.8 billion years after the Big Bang. And so that's a natural thing for it to be. I don't think it's at all natural. Our single data point is not enough. for us to draw those conclusions. Khoomah, sorry I don't know how to pronounce that, says, since I learned how contingent inflationary models are on supersymmetry,

it's been curious not to see much concern as the LHC results have eliminated the most likely models of supersymmetry. What can you say about the relationship between the two theories and what do you expect to happen to inflation if super symmetry is wrong? Well, I don't actually think it's true that inflationary models are very contingent on super symmetry. To be honest, I've not kept up in the most recent wrinkles of explorations of the space of possible inflationary models, so maybe the conventional wisdom has shifted a little bit. There is the following set of true facts. When you look at the perturbations in the cosmic microwave background that are temperature antisotropies that grew into density perturbations and galaxies and clusters and so forth, they're pretty small, right?

It's one part variation in the microwave background per 100,000, so 10 to the minus 5 fluctuation. And if you believe that those fluctuations came from inflation, you can translate that small amount of perturbation into statements about the shape and the slope of the inflationary potential. Also, by the way, in order to solve the traditional fine-tuning problems of the early universe, inflation has to persist for a long time. So if you think that the usual way to quantify it is think about e-folds of expansion. So you have the expansion parameter, the scale parameter of the universe, the scale factor A of T, and every time it gets multiplied by the number E, 2.71, etc., you call that an E-fold.

So, you know, E-squared multiplies it by E-squared, et cetera. two e-folds multiplied by e-squared. To do the job that inflation is supposed to do, you need 60 e-folds of inflation. And the idea that inflation would happen at all is actually pretty easy, pretty robust, easy to implement in a particle physics model. But the natural amount of e-folds for inflation to go on, there's two possible natural numbers. One e-fold. It happens a little bit and then it ends, or infinity e-folds. You just get stuck inflating forever. To get 60, and then to stop, is hard. And you need the slope with the potential to be very shallow in order to get the right density perturbations that we see in the microwave background. So together, these two facts say that

even though, you know, inflation is supposed to help us understand the fine-tuning of other early universe things, the inflationary potential itself does have to be fine-tuned in the sense that not fine-tuned for the existence of life, but there needs to be some small numbers in there that could have been of order one. They need to be much smaller than one. And Alan Gooth, who invented inflation or invented the most popular versions of it,

is very clear about this. He's written papers of quantifying exactly how fine-tuned it has to be. And supersymmetry is good at allowing small numbers to be small numbers, at allowing small numbers to survive the effects of quantum corrections, etc. I personally think that this whole discussion we have about naturalness and fine-tuning is a little bit sloppy, and not that we shouldn't do it,

but I don't think we do it well enough or careful enough, so I don't want to say exactly what I think about those things, but it is natural to imagine that supersymmetry plays a role in explaining why the infliton potential has the special properties that it does. Now, but it doesn't need to be. You can just do it without supersymmetry anyway. As far as I know, and again, not an expert on the most recent wrinkles here. As far as I know, this is completely unaffected by the fact that we have not seen supersymmetry at the Large Hadron Collider. There is something that is very strongly affected by that, which is the hierarchy problem. The hierarchy problem in particle physics is the idea that those same quantum corrections, quantum corrections that you would expect to be relevant for

the infloton potential, you also expect to be relevant for the potential of the Higgs boson, which breaks the Electroweak Symmetry. And therefore, you expect the mass of the Higgs boson and the expectation value of the Higgs boson to be pretty big numbers because they're driven up by quantum corrections. But they're not very big numbers. They're very small compared to the Planck scale or the grandinification scale or whatever. That's the hierarchy problem. And that was really what was purportedly going to be solved by discovering broken supersymmetry near the Electro-Weak scale or something that would do the same job as broken supersymmetry. And maybe we will.

Maybe we will tomorrow, you know, but we could have by now and we didn't. So a lot of the parameter space has been ruled out. It very easily could have happened that you turn on the LHC, and next week you've seen supersymmetric particles all over the place. That didn't happen. So that is a puzzle, okay? What is the, you know, our favorite explanations for the hierarchy problem didn't work. We need better ones or we need to rethink whether it's a problem at all.

We need to do some thinking. That's okay. That's why they pay us the big bucks. We need to do some thinking. But that, in order to be relevant to the hierarchy problem, supersymmetry needed to be broken and need to be broken near the Electro-Weak scale. That's not really the same for inflation. You could have supersymmetry broken at a much higher scale and still way up high at the inflation scale.

It's still unbroken and still important. So maybe not finding supersymmetry the LHC has decreased your credence in supersymmetry overall. That's perfectly fair. But it's not directly relevant to the question of inflation in a way that it's directly relevant to the hierarchy problem. My best skin ever at 45? Give me a theme song and a best skincare award because it feels like this. Right there. That's Farmhouse Fresh Skin, all right?

I'm blowing, and everyone asks how. The best skincare is Farmhouse Fresh, and the award is you, your best you. Visit Farmhousefreshskincare.com and use code radio for a free starter routine with any purchase. Okay, I'm going to group two questions together. One is from Charles Hertz, who says, I'm having trouble understanding the concept of a spinning black hole. This is prompted by the conversation we had with Andy Strominger in the beginning of January. And then Michael Kramer says, what does it mean to speak of a body, in particular a black hole,

spinning at or faster than the speed of light? So two questions here. The connection should be obvious. What is spinning black hole? And what does it mean to be spinning at or faster than the speed of light? So these are perfectly legitimate questions. And it's just an example of physicists talking. a little bit slobally, but they talk a little bit sloppily for good reasons, because the concepts

that they're describing are very mathematically, physically well-defined, but are not in the realm of language that we would think of having developed over the past several thousand years when we invented language, right? We don't have the words to describe these things. So can a black hole spin? Because a black hole, after all, forget about the stuff from which the black hole was made. The black hole is created, a bunch of matter falls in or whatever, you make a black hole. But after that happens, the black hole itself is nothing more or less than a region of space time. It's not a thing with stuff, with matter. The black hole right up to the eventorizing and even past the eventorizon can be essentially empty space time. Okay, there's nothing there other than

space time itself. So to ask what it means for a black hole to be spinning, is perfectly 100% fair. What does it mean? Well, it means that the black hole has angular momentum. That's really what it means. And how is that possible that a region of space time has angular momentum? Well, and actually, this is going to go to a question we're going to talk about later on also. But there's two things going on when we're talking about space time.

Okay? We talk about space time and it's curvature and things like that. But then again, we're being sloppy because there is space time, in the sense of of a set of locations, right? A set of points in space time or events, as we call them, located in space at a moment in time. And then there is the metric tensor field. If you want to read more about the metric tensor field, I can recommend to you my new book. The biggest ideas in the universe, space time in motion, where we talk about it in great detail.

It is the metric tensor field that defines the geometry of space time. So there's space time, and then it has something. It has a particular field, the metric tensor field, from which we can calculate its geometry. And so the thing that has angular momentum is really the value of the metric tensor field. And that by itself seems a little weird. How can a field have angular momentum or be spinning? A field has a value at every location in space, but this is a very common thing, right? Magnetic fields can have angular momentum, electromagnetic fields.

So the fact that the metric can also shouldn't surprise you. And operationally, what it means is if you start with a spinning star and it collapses to a black hole and you do it in such a way that it doesn't spit out any matter to the outside world, the angular momentum that the star had will be the same as the angular momentum that we calculate in the metric tensor defining the black hole. So that's really what we mean. By a spinning black hole, we mean the configuration of the metric tensor that defines the curvature of space time is associated with a certain angular momentum. And that association, that angular momentum, has physical effects. For one thing, it changes the shape of the black hole. A non-spinning black hole is perfectly spherical, okay, the short shield solution to general relativity. The spinning solution, what is called the cur metric to general relativity, is oblate, just like the earth. is a little bit obliate because it's spinning, likewise the black holes are. So it has a very well-defined North Pole, South Pole equator kind of thing. And it affects the motion of particles as they fall in.

If you fall into a black hole, again, that is stationary, you can fall in more or less in any direction, right? Like you can fall in just straight down, but you can also fall in spiraling to the left or spiraling to the right. Not true for a spinning black hole. The spin pulls you around, or really again, to be slightly more precise about it, what the metric does is it changes the geometry of spacetime and that includes the light cones of space time. That includes what the local definition of what it means to be moving slower than the speed of light.

So in general relativity, when spacetime can be curved, at every point in space time, there is something called what it would mean to move slower in the speed of light. So a set of trajectories you could possibly travel into the future. To travel in a space-like direction from that point in space time would mean to move faster the speed of light. You're not allowed to do that.

And that's true at every point in space time. But then globally, you need to knit these together. At every point, there might be a different notion of what it means to move forward in time, stay inside your light cone, okay? And what happens in the case of a spinning black hole is that from the perspective of outside, the light cones are tilting in such a way that if you're moving slower in the speed of light, it looks like you are being dragged around. So if you have a spinning black hole and you drop an object into it, it doesn't fall straight on through. It starts following the direction of spin

of the black hole and spirals in before it actually enters. Now, nothing goes faster in the speed of light. So there's no spinning faster than the speed of light. That's not allowed. But there are what are called extremal black holes that essentially in this understanding that I just tried to explain are spinning at the speed of light. We don't think that they can exist in the physical world, extremal black holes, but mathematically we can write them down. So I wouldn't worry about them too much, but they're a good little mathematical playground for theoretical physicists. Paul Cronin asks, if spacetime is emergent, what could it be emergent from? Would love your gut feeling on this.

So I kind of want to unask this question. I do that occasionally, maybe more than occasionally, because, I mean, I think by the structure of the question is pretty clear, it presumes there is something from which the space time is emergent. And I know why you would get that impression, because, you know, the classic examples we have of emergence are something like treating the air in the room as a fluid, obeying the fluid equations, rather than treating it as a set of atoms and molecules that have

individual positions in momentum. In some very real sense, in that case, the fluid description is emerging from the atomic description. So just parenthetically, let me say this. The word emergent is not a good word for this, in part because the word emergence has some connotations of a process happening in time, right? The thing was one way and something, it emerged into something else or something emerged from it, right? Like a chick emerges from its shell when it gets born. That's not what's going on. You know, the emergent description of the air in the room as a fluid is not something that didn't exist in the past and now exists. It always existed for all intents and purposes. For us, it simultaneously exists. We still have the way of describing the atoms and molecules, but we also have the

way of describing the air as a fluid, okay? So it's not emergent in time. But the other thing is, these examples are very clear examples of where there's one thing that we know and love, and its emergent description is a different thing that we know and love. And that might not be the case for space time. I mean, I could give the glib answer that it emerges from the quantum wave function. That's the answer, okay? But there's not a thing, it's not a stuff, not a substance, not a known, familiar kind of thing that I could point my finger at like, oh, strings or atoms or bits or, I don't know, brotherhood and sisterhood from which spacetime emerges. All that means is that the fundamental description of nature is a quantum state, a wave function, evolving in time, according to the Schrodinger equation, and there is some higher level description of that, some coarse-grained description, that looks like spacetime obeying the Einstein equations.

Okay? That's very analogous to there is a microscopic description of atoms and molecules bumping into each other, and there's an emergent higher-level coarse-grained description as fluid mechanics. That's what it means, but there's nothing that space-time is emergent from other than the quantum wave function. And if you want to ask what that is, it's the quantum wave function.

It's the best way we currently have of describing all of reality. There you go. Stuart Haynes says, culturally, what has struck you the most moving from the West Coast to the East, either within academia or outside of it? Yeah, I'm from the East Coast, right? I was born the suburbs of Philadelphia, spent eight years in Boston, college and postdoc, etc. So this is not a culture shock to me. And honestly, like, I want to be a little contrarian about these questions and say that there are differences between the East Coast and the West Coast, but they're much, much, much, tinier than the similarities. I even think this about going to other countries, right? And people say, oh yeah, it's so different in that other country. It always strikes me about going to other countries is how similar things are. The same basic way of doing things, you know, you always

have your convenience stores and your subways or your cars or your farms or whatever. Like the same basic structures of human life are not completely universal, but very, very common, okay? The East Coast and West Coast aren't that different. I think they kind of like to exaggerate their differences a little bit. There are differences. I mean, Caltech is a very unique place among institutions of higher education and research. So there are differences from Caltech to other places. You know, having been at various other universities, including MIT, which I think to the people

on the outside, probably they're going to think it's similar to Caltech. But Caltech is really unique in various ways for good and bad. Okay. You know, I've had parents and high school kids ask me about going to Caltech for undergrad, and I have to tell them it depends very, very, very, very strongly on who you are and what you want. Caltech is perfect for some people and not so good for many people. So you have to be right for it. And, you know, in many ways, it was not right for me.

That's one of the reasons why I left. You know, as good as it is, the thing that Caltech is good at is creating a space for brilliant creative people to go, especially sort of science and techie people, to go and do their research in their area. It's really, really good at that. And, you know, already like the increased bureaucracy at Johns Hopkins is getting to me. Caltech is just so easy to get things done compared to other places. Whereas at most universities, including Hopkins, you have to get like permission from certain people, et cetera, et cetera. So, but there's something missing there. There's not a lot of talking back and forth between people in different fields. There's not a sense at Caltech that we are

a university, right? I mean, it is a university in every realistic sense, but it's very dedicated to science and technology and math and engineering and those kinds of things. It's not trying to be more comprehensive. There are humanists and social scientists there at Caltech, but they're such a tiny minority that they're just not. very important to the life of the Institute. Whereas, you know, here at Johns Hopkins, there's a lot of different departments. You know, I already have more people I socialize with on the faculty at Johns Hopkins, having been here six months than I did at 16 years of being at Caltech.

I'm invited to be doing a whole bunch of different things. I'm involved with the Humanities Institute and the Democracy Institute, you know, and a whole bunch of things that didn't even exist at Caltech. So there's a big cultural difference between those two institutions. Hopkins makes it a lot easier to be interdisciplinary, to talk to people, to think outside of a box in different ways than Caltech encourages you to think outside of the box. West Coast, you know, Baltimore versus L.A., yes, those are two very different cities. L.A. just very, very car culture centered. I know that this is a cliche, but it is so true.

Every restaurant has valet parking. There's parking lots everywhere. There are car washes everywhere. It's hard to get a decent California quality car wash here in Baltimore, I got to say. But, you know, the people in Baltimore, this is the single, and this is very, very honest. I'm not just trying to shine you on here. But the single most surprising thing is how nice people are in Baltimore. Maybe this is because it's, you know, right at a sweet spot on the edge of the northeast and the south.

Southeast of the United States. It gets a little bit of both kinds of sides of the culture. But people are just really helpful, polite. You know, we moved a new house, people who did our floors and, you know, delivered our things and did our moving and the people who serve you in restaurants, et cetera. Everyone is really nice. It's very, very surprising and very, very pleasant. So I really like that aspect of it. Not to say there aren't nice people in Los Angeles, too, but Los Angeles is full of strivers trying to get ahead, and they look at you and judge you to see whether or not you can help them get ahead. And they measure you on that scale very, very quickly,

and that can get a little tiresome at times. Tyler Ogorek says, What are your thoughts on the current length of PhD programs? Back in the day, I hear that folks could reliably get out in about four years, but that number has been creeping up and up. For example, my school's average time to PhD just hit 5.7 years. I'm a little suspicious that it was ever four years. This is a number that the length that takes to get a PhD, length of time,

varies a lot from field to field. You know, in humanities, it generally takes substantially longer than in science. But my impression within physics and related sciences is always that the aspiration was five years. That's how long it takes to get a PhD. In the United States, in different systems, in the UK, it can be three years. But there's, again, pluses and minuses there. In the UK, you go and you start doing research and you're expected to know what you're doing.

In the U.S., very often the first two years are mostly, you're still taking classes and learning things and deciding what you want to do. And I kind of like that system better, to be perfectly honest, but there are definitely pluses and minuses there. I took five years. Most people I know took five years. Occasionally someone would take six.

very occasionally longer than that. But if you start taking more than six, people begin to look at you a little weird. I know that Princeton sort of started just, you would show up and you wouldn't have any funding if you took too long. But I think it depends a lot on the school. So I don't even know if it's creeping up and up. I don't think it's a big deal, honestly, one way or the other.

I don't think that there's certainly, I certainly don't think that, you know, professors are trying to keep students around longer or anything like that. Of course, I might have a very narrow view there because in theoretical physics, you don't have a big laboratory. You can't just plug people in. As an advisor of PhD students, there is a give and take, you know, especially in their early years, you are putting a lot more time into them than they are giving back to you in terms of useful research. In later years, they're giving back to you a lot more in useful research than you're putting into them, if all is going well. whereas in a more experimental lab-based area, the graduate student can learn enough to be useful in a lab very quickly.

And this is maybe even true in some areas of physics, but certainly in biology and chemistry. So there is in those areas maybe more of a feeling like the good grad students are useful. We want to keep them around. But I have no personal evidence of that or anything like that. So I think the issue is postdocs, honestly. The amount of time we take being a postdoctoral scholar, that's an issue that is weird and we have to face it. We're asking people to spend too much time as postdocs. That's what I would worry about, not the PhD programs.

T.O. Alexander says, if it is true that the Higgs field is responsible for mass, and if it is true that mass is responsible for the curvature of space time, then why is there the necessity for a gravity particle? since all objects are simply in free fall when no outside forces are present. Well, so I know that I, you know, I edit these questions because some of them, man, you just write very long. And this is not you, T.O. But I just edit for things I don't think are crucial. But I think the T.O. did disclaim that, you know, this is a non-expert question, which is fine. I absolutely love and encourage the non-expert questions. I encourage them more than the hyper-expert, you know, technical questions.

Because for those, you can just go somewhere on core or whatever to get, those kinds of answers. Anyway, let me say two things. It is not true that the Higgs field is responsible for mass, and it is not true that mass is responsible for the curvature of space time. Both statements are close, like they have some relationship to the truth. They're not blatant falsehoods, but it's an example where they're oversimplifications that get you into trouble when you think about them too hard. So for one thing, there's zero sense. in which the Higgs field is somehow necessary for the idea of mass to exist. Protons and neutrons, which are the particles that make up most of your mass as a human being,

get most of their mass from quantum chromodynamics, from the strong nuclear force. Nothing to do with the Higgs field at all. The Higgs field doesn't need to be there for things to have mass. Mass in relativity is simply the energy of an object that is stationary, that is not moving. It's the intrinsic energy that an object has just by existing. That's what mass is. Mass is rest energy divided by C squared, to quote a famous equation. So it turns out that in the standard model particle physics, most of the elementary particles,

the quarks, the leptons, and the W and Z bosons, they have similar. that if it weren't for the Higgs, would keep their mass zero. So when we say, and the Higgs boson, the Higgs field, gets an expectation value, breaks that symmetry, allows them to get mass, and gives it to them. So the Higgs field is responsible for the mass of certain elementary particles in the standard model of particle physics. that is a much narrower and more constrained statement than the Higgs field is responsible for mass. Okay?

So your electron needs the Higgs field to get its mass, but the proton doesn't. There's some contribution to the mass of the proton from the Higgs because the up and down quarks get their mass from the Higgs field, but the up and down quarks are a tiny fraction of the total mass of the proton. So the Higgs field is not exactly responsible for mass. It's a more specialized relationship. And then you say mass is responsible for the curvature of space time. Again, not quite true. The energy momentum tensor, and other things, by the way, are responsible for the curvature

of space time in general relativity. Energy is unified in relativity with mass, but also momentum and heat and pressure and all of those things, okay? and they all contribute to the curvature of space time. And their contribution does not define the curvature of space time because even when there is no mass or energy or anything, space time can still be curved. You can have a gravitational wave propagating through empty space.

So it's just not true that knowing energy momentum is enough to know the curvature of space time. You need to specify that in some independent way, and as we already talked about, the way to do that is through the metric tensor. All of this is explained in the book that I already told you to read, the biggest ideas in the universe,

so I encourage you to check that out. Jason and Richiardy says, since quantum computing is based on quantum mechanics, have you ever learned to code in Quiskit or another quantum computing language or is it a part of your job in any way? General impressions about the field in its direction are much appreciated.

Short answer, no. I had never even heard of Quiskit before your question. I googled it. So I did not ask chat GPT about it. But no, I've never used that. But I effectively have, I have, you know, written down quantum algorithms. So, you know, at my level of being a theorist, and I've taught the very, very basics of quantum computing, what I would be doing is sort of the quantum computing equivalent of assembly language, right,

of literally stringing together gates, you know, not gates and N gates and things like that at the quantum level, the quantum version of those things, that's what I know how to do, to make a very simple quantum algorithm out of a collection of gates, okay? And you can do this, by the way. And I occasionally mention this, but I just like to keep mentioning. There's something called the IBM Quantum Experience, which is a working quantum computer that you can go and get an account and write a little algorithm and run it on the quantum computer.

Now, that's less impressive than it sounds because there's only a few cubits. I forget how many there are, 10? I don't know. I'm making that number up, but a very small number. You're not going to crack any RSA encryption or anything like that or solve the traveling salesman problem. But you can practice. And in fact, it's such a small number of qubits that because we understand quantum mechanics in the Schrodinger equation, you could easily run that quantum algorithm on a classical computer much faster than you can run it on the quantum computer. So at the IBM quantum experience, it will literally allow you to test your algorithm by running it classically before you run. it quantum mechanically. And when you do run it quantum mechanically, either you get the same answer as you did in the classical version or you made a mistake somewhere. Okay? So the reason to run it on actual qubits is just for the thrill of knowing that you ran it on actual cubits, not for any result that's going to come out of the algorithm. But anyway, that's the level I will do it at. There's no reason for me in my professional life to program a quantum computer. I'm interested in the

foundations of quantum mechanics, not in solving particular well-defined calculations that a quantum computer would be useful for. That could always change. Who knows? You know, that's the great thing about being a theoretical physicist. What I'm doing five years from now might be unrelated. So I might have to learn Q-Quisket or, you know, quantum Python or whatever it is that exists out there in the future. Okay, I realized belatedly that I actually have more questions that are related to the Laura Bouchak podcast, which is great, by the way. I love it when questions have to do with recent or older podcasts. I like the idea that there are ideas and questions bubbling along in our minds.

So there are three questions here that I'm going to group two of them together, and then I'm just going to ask the third one separately. I forget why I did this, but we'll see if it works. So the first is from Jeffrey Seagal, who says, Your conversation with Laura Bouchak about many worlds and whether future Sean Carrolls are the same or different, inspire me to work. wonder about how differences accumulate between the present me at one particular point. Oh yeah, I'm sorry. I'm sorry. This is me talking to myself. These two questions that I'm grouping together

have nothing to do with the Laura Bucciak conversation. Jeffrey's question was inspired by it, but they're very different questions. So I'm grouping together two questions here. It's about many worlds. They're not about that particular podcast. So inspired me to wonder about how differences accumulated between the present me at one particular point of Hilbert space, and the future me that evolves from that point. You've noted before that quantum phenomena have extremely small likelihood of affecting human scale events unless, as you noted, a quantum random number generator is used to make decisions. Therefore, if I do not use a quantum random number generator, the wave function that represents my behavior may remain very tight. My decisions are driven by macroscale phenomena

such as neuronal membrane potentials, and those are in theory highly predictable and not affected by quantum phenomena. I'm assuming the quantum tunneling or the various radioactive decays in my body are also extremely unlikely to actually affect the firing of even one neuron. Has anyone estimated how long on average it might take before there is a change in my external behavior due to internal quantum variations? The other question is from Josh Charles, who says, while I was considering how many quantum branching events happen in my own body, I was struck by the notion that the vast majority of those events do not make any difference to the macro state of my body. And even if it made a difference in my body, it would not make a difference to the moon or to Jupiter or

the Andromeda Galaxy. It seems like the vast majority of quantum events would not be consequential in large-scale considerations. Are all multiverses actually pretty much the same? Is there an example of a quantum event that can domino up to measurable macro-state changes? So both questions have to do with the idea that there's a pretty good classical approximation to quantum. quantum mechanics, and to a very, very, very good approximation, we can think about the world in which we live macroscopically as obeying the rules of classical mechanics plus maybe some random tiny events, okay? And then the question is, can we quantify the effect of these random tiny events on the classical behavior that does most of the work? You know, so it depends.

The answer is it depends, and I actually am not going to be able to give you any or many quantitative insight here, but let me tell you how to think about these issues. If you're thinking about something like the Earth going around the sun, quantum perturbations have zero impact there, or essentially zero impact. You have such a big object moving in such a predictable, classical way that quantum fluctuations are not that big. But the reason why I bring up that example is because even within just the realm of large astrophysical objects, there are well known examples where quantum fluctuations do matter. So, and I've talked about this before, but the classic example is Hyperion, which is a moon of

Saturn. Hyperion is, you know, it's a moon now, but of course, like many of these moons, it was an asteroid that was captured. So it's a lumpy thing. It's not a spherical thing. It looks like a potato. And astronomers have calculated, when they, like, look at the shape of the lumpiness of Hyperion, that it tumbles in a way that is...

technically fits into the definition of chaotic behavior. That is to say, the different ways in which Hyperion Tumbles have the feature that a small variation in its initial position and orientation and speed leads to a large change in the orientation later on. So when that kind of behavior is present at the classical level, when there is classical chaotic behavior, then guess what? a tiny variation is really important, even a variation that is small enough just to be due to quantum effects. So, Voichek-Zurek, who is a pioneer of decoherence and pointer states and quantum mechanics and things like that, wrote a famous article, I think in physics today, where he points out that he ran the numbers. And Hyperion is chaotic enough that if you just leave it alone for a short period of time, when you look back at it, you should not see a potato.

By the rules of quantum mechanics, you should see just a big, smooth blob of wave function. Now, you don't. Of course you don't. Why not? Well, because Hyperion is not alone in the universe. It is constantly being monitored by the environment. Sunlight, cosmic microwave background, little microparticles, etc. Like anything else in the universe, it interacts with its environment and it decoheres.

So there are different branches of the wave function of the universe, which are almost the same in many, many ways. except that the Moon Hyperion is in slightly different orientations in all of these different branches of the wave function. Okay, so it can happen. But what do you really want to know about is human beings, right? Well, there's another very famous way in which a tiny quantum fluctuation or perturbation can grow up and be amplified to macroscopic behavior.

Well, there's two famous ways. One is which you just like listen to a Geiger counter, right? I mean, and if you're reacting in any way, then that's going to be different in different branches of the wave function. But the other one is mutations, right? As evolution happens and you pass on your genome from generation and generation, and there is not just sexual selection mixing up moms and dads, genomes, but there's also mutations.

Mutations are associated with quantum events. And so any given mutation happens in some branches of the wave function and not in other branches of the wave function. So the history of humankind, to the extent that it depends on the history of the evolution of our species, is very, very different in different branches of the wave function if you go all the way back to things that might have affected evolutionary history. Now, if you want to zoom in on the life of one person, the simple answer is, I don't know. The quantitative question is, if you start with a single person in their wave function and just propagate it forward, in time and don't let them, you know, make important life decisions based on quantum random number generators or anything like that.

Will their future, let's say five years in the future, will their lives be very different on different branches of the wave function? That is a quantitative question that I don't know the answer to because it's like the Hyperion question. You had to run the numbers to figure out just classically how sensitive is the behavior to small perturbations. If you knew that, then you could figure out how small the actual. perturbations were made by quantum mechanics, and then you could figure out the average difference

between one life and another. But I don't know either one of those. I don't know either how sensitive human behavior is to these small variations, nor do I really know how big the variations are just due to different quantum measurements being made or different decoherence or branching events. So I'm open to the possibility that it is important, but I don't know that it's important. It might very well not be. Hey, everyone, it's Cal Penn. I'm the host of Earsay, the Audible and I Heart audiobook club. This week on the podcast, I am sitting down with Ray Porter, the narrator of Andy Weir's

audiobook Project Hail Mary, massive sci-fi adventure about survival and science, and what happens when you wake up alone very far from Earth? I really had to make a decision because I caught myself getting that frog in my throat and starting to get teary as I'm not. narrating some of these sections, and it's like, okay, yo, yeah, yo, is this indulgent? And I really thought about it. I was like, no, at this point, it would kind of be betraying the trust the author and the listener have in telling this story if I don't go through it. But there's places in this book that deeply emotionally affected me, and I left it on the mic. That's great. Because it served

the story. People will say like, oh my God, I cried at the end. It's like, yeah, dude, me too. Listen to Earsay, the Audible and IHeart Audio Book Club On the IHeart Radio app or wherever you get your podcasts My Best Skin Ever at 45? Give me a theme song and a Best Skin Care Award Because it feels like this, right? That's Farmhouse Fresh Skin, all right? I'm blowing, and everyone asks how.

The best skincare is Farmhouse Fresh, And the award is you, your best you. Visit farmhousefresh skincare.com and use code radio for a free starter routine with any purchase. David Maxwell says, and this is the other question that does actually have something to do with Laura Buchak's podcast. In your great conversation with Laura Buchak, you explored your own risk aversion and concluded that it might have implications for your stance on the moral significance of many worlds. You noted you do need to think about it further. It was one of those moments so great about interdisciplinary chats and I could hear the excitement in your voice. Has this conversation had any effect on your priors or your philosophical position?

So, yeah, let me give a little bit of the background to that. It could be interesting and important. I just don't know. Be very honest, I'm swamped with other things right now, one of which is doing this AMA. But I love doing the AMA. Don't take that the wrong way. But there's a lot of things going on. I haven't had real time for doing research in the past.

past few months. I did come out, I did finally submit a paper the other day, in case you're interested, on reality realism, is what I called it. It was, you know, remember the conversation I had with Justin Clark Donne on morality and mathematics. Justin is a philosopher at Columbia, who's an expert in both meta-ethics and also the philosophy of math, and he draws parallels, but also distinctions between them. And in his little book, The Morality of Mathematics, he actually starts by quoting me. And I was a little bit surprised to see that. But, you know, he quotes me in the big picture talking about moral realism and the fact that I am not a believer in it. Okay, I'm not a moral realist, but I am a realist about the physical world. And Justin in his book says,

but someone like Carol would have to be a mathematical realist in order to like do math about the standard model of particle physics and things like that. But interestingly, that's actually not what I believe. I'm not a mathematical realist. I'm also not an So I try to be very humble about this. Maybe I should be a mathematical realist. I've listened to people give their sales pitch and they're not convincing. Jodi Azuni was the other person who I talked to on the podcast who is not a mathematical realist. He's a good example of what we call a nominalist in the philosophy of mathematics, which is closer to my position.

Anyway, the point is I wrote up a paper saying why I think you can be not a mathematical realist and yet a physical realist. And that's the only real research publication I've had in the past 12 months. but I'm hoping that this upcoming year will be better. So maybe there's a future publication here. I don't know. But here's the point to get back to David's question. I have had this thought that for realistic versions of moral philosophy, many worlds and theories where you have a single world with true randomness,

with true quantum randomness. In other words, when you measure that spin on the particle and you say it's 50-50, imagine a theory where there really is only one world, but we just don't know which one it's going to be. It's going to be one where the spin is up or the spin is down, okay? And my position has been that for realistic moral theories, there is no difference in how you should behave in many worlds versus a stochastic single-world theory. Here was my reasoning for that. Think about realistic moral theories. Think about utilitarianism.

Think about deontology, virtue ethics, whatever it is. things like deontology and virtue ethics which say either obey rules or be virtuous, those are exactly the same, no matter what your theory of quantum mechanics is. So there's no danger, there's no temptation to think maybe they should be different in many worlds. Utilitarianism is a little bit trickier. So you have to think harder. I talk about this in something deeply hidden if you're interested. The very naive thing that you might say is, well, I'm going to maximize the amount of utility in the world. if I have two universes that are more or less the same, that is twice the utility of just one universe with the same situation in it, okay? So therefore, the way to maximize utilities just to make the most universes I can to branch the wave function of the universe. Now, that's just dumb. That's

silly. And so I do explain in something deeply hidden why that's silly and why what you really should do is weight your utility calculation by the wave function squared, just like you calculate probabilities. And if you do that, then in the standard expectation value calculation that you do in utilitarianism, you know, in utilitarianism you try to maximize utility, but you admit that you might not know what the consequences are going to be. So you have different probabilities for different outcomes and you calculate the expected utility. That's very, very well-known kind of thing. My point was just that that's the same calculation that you would do in many worlds as you

would do in the stochastic single world. I did in something deeply hidden say, look, you can come up with silly moral theories that would have a difference between many worlds and a single world version of quantum mechanics. And the one I came up with, I don't remember it exactly, it's been a while, but the point of it was the following. Imagine that you really had a moral aversion to inequality, okay, to actually exist. inequality, that your moral philosophy, whatever it was, was maximized, said to maximize the amount to which everyone's situation is the same. Everyone in the multiverses situation is the same, okay? In that case, imagine the following thought experiment. You're given a quantum spin to measure,

spin up or spin down, and you're given a bargain by a wealthy, slightly crazy philanthropist who says, you know, pick some group of people. If the spin is up, I'm not. I will give them all $10. If the spin is down, I will give them all $20. Okay. Now, if your goal is to maximize equality, to minimize inequality, but then within that constraint, you want to maximize the amount of wealth and happiness everyone has, if there was just a single world with probabilistic quantum events, you would accept that bargain.

There's a 50% chance everyone gets $10, 50% chance everyone gets $20, but either way, everyone gets the same amount of money. Whereas, if you thought that many worlds was right, then there is a world in which everyone gets $10 and a world in which everyone gets $20. And you might feel that's unequal, right? Because everyone knows what this experiment is, what the bargain is from the philanthropist ahead of time. the people in the $10 world are going to know there are other people who really exist in the $20 world and they're going to be sad because of that. Okay. Now, I don't think that's a good moral philosophy, but I did want to acknowledge the fact that in principle you could invent moral theories which differentiate between them. Okay. It's a very long prologonement to saying that what Laura was talking about opens the possibility of a, more realistic moral theory that does differentiate between many worlds and single-world theories.

Because, and I'm not going to get it exactly right again, because I haven't thought about it very deeply, but the idea would be that if you're not just maximizing utility, but you're taking risk aversion into consideration, then maybe you could imagine a reasonable moral theory which distinguished between a a 10% chance of something happening and a 90% chance of it not happening versus it really happens to 10% of the people and really doesn't happen to 90% of the people. In that latter case, there's 100% chance that it happens to someone in the former case there isn't. And that might be something that you want to differentiate between. So it's actually like not that different in spirit than the crazy example I came up in the book, but you know, it's a little bit much more reasonable.

as a moral theory. So I would like to think about that more, whether or not one can come up. What is the most reasonable, plausible, defensible moral theory that one can come up with for which it matters to you whether the fundamental ontology of the world is single world plus randomness versus many worlds? Let's see. I'm not quite sure. Joshua Everett Hedgepeth says, a priority question. I've always been somewhat confused about what it means to branch. When a world branches into two or more, is the realm of thought that there is one more world than there used to be in the quantum cosmos, or rather there already are two distinct worlds before the branch, but before the branch, one state of the world,

the state of each world was identical, thus they are labeled as one world. So this is a question I've addressed before, and the answer is it depends. Or the answer is, I don't know whether to say it depends on your choices or I just don't know the right answer. So, the question is, is it okay, when worlds do branch, is it okay to think of them as already having been separate worlds even before they branched, even though they were separate, they were identical? Is it okay to think of them that way? My impression is it is not okay to think of them that way, because before they differentiate and decoher, things can happen that can involve interference. That's what makes a world a world is that what happens in that world cannot

affect what happens in other worlds, okay? And I don't think that's true before the decoherence and the branching happens in the conventional way of thinking it, which is why the way I prefer to think of it is there is one world, and then it branches, and there are many worlds. I think that's a perfectly legitimate way to think about it. There are benefits to trying to think about it the other way. The most obvious benefit is, It makes it a little bit more plausible how we calculate probabilities. We calculate probabilities by weighting things by the wave function squared. And if you can always subdivide branches into worlds, then that is literally counting the maximum number of worlds you can subdivide into, because that's just the dimensionality of Hilbert space.

And so if you tell someone your probability calculation is literally just counting things, they're more persuaded than if you say it's a weighting of a basing. credence in a state of self-locating uncertainty. I know this empirically. They're more likely to be persuaded. But I'm not sure if it works. I do know there are people who take it very seriously. I believe that David Deutsch is someone who thinks and talks that way. And I haven't thought about it very deeply because I don't care that much. I'm always been of the opinion that worlds are convenient, higher-level human constructions that are very convenient, but they're very obvious when they happen, when the branching happens. And what happens in more subtle cases just doesn't bother me that much. Different people are welcome to do different things as far as I'm concerned.

Ghost Composer says, I just bought the biggest ideas in the universe space, time, and motion. I plan to work through this book very slowly, but you have a rough estimate of when you might finish books two and three of your trilogy. I don't exactly, but I think that the rule of thumb should be between a year and a year and a half between books. I am working to finish book two, but is not yet finished, and I'm beginning to think that it's not going to be this September, since I should be done it already, if that were going to be the case. So I'm thinking whatever it is later than this September. Taroon says, it seems to me that determinism emerges at a macroscopic level.

This is why we can send rockets to the moon. How do I reconcile this with your statement that we simply do not live in a deterministic world given quantum mechanics? Even if the terminism is just an approximation, it seems to be so accurate that we can ignore any uncertainty at the human scale. Well, we talked about this a little bit above, but I think it depends on what you mean. We certainly can't ignore any uncertainty at the human scale. If the uncertainties are big, then we can't ignore them.

The uncertainties are certainly very noticeable. Listening to a Geiger counter is an obvious example. And so it depends on the purposes for which you want to model whatever you're thinking about. The only statement that I would make absolutely is that the world in which we live behaves non-deterministically. That is just the lesson of quantum mechanics. You can't get around that. It may very well be that certain subsets of the world have deterministic approximations to them,

and you can ignore it for whatever purposes you, for some specific purpose that you want. But whenever you make approximations, what you can ignore and cannot will depend on those purposes. You have to be explicit. Clyde Schechter says, regarding your blog, what is it about the universe that you find preposterous? So the website that I have is called preposterousuniverse.com. In fact, I think that people don't always know this, but there is a website, web page for the podcast, preposterousuniverse.com slash podcast, where you can listen to all the podcasts and get all of the show notes and links and things like that. So I encourage you to visit that from time to time, even if when you're listening to podcasts, you're not always in front of a computer or anything like that.

The name preposterous universe.com came from way back in the day when I was thinking very hard about dark energy, and we had discovered that 70% of the universe is dark energy, and there is something called the coincidence problem as well as the cosmological constant problem. The cosmological constant problem is just, why is the vacuum energy so much smaller than you might expect it to be? the coincidence problem is why is the amount of vacuum energy or dark energy of the same

order of magnitude as the amount of matter in the universe? And that's especially weird because these two things change with respect to each other as the universe expands. Right now there's two or three times as much dark energy as matter, but there used to be a lot more matter than dark energy. And so why are we so lucky

to live at exactly the right time? Before we had discovered the dark energy, these weirdnesses were very good reasons, and I think perfectly respectable reasons, even though they turned out to be wrong, to suspect that the cosmrestrial constant would be said to be exactly zero by some as yet unknown mechanism

that we haven't yet figured out. So the preposterousness of the universe is just that we have measured these parameters of the universe, and not only that, there's also other things like the hierarchy problem and inflation that we talked about before, features of the universe that seem very, different than what we would expect, given what we know about other features of the universe.

Now, of course, it's a joke. The universe is the universe. It's not allowed to be preposterous or weird or unnatural or anything like that. It is what sets our expectations as well as lives up to them or otherwise. But in the real world, our expectations are set by some subset of everything that happens in the universe. And so whenever there's something that seems unnatural to us, we're making a mistake. It's not a criticism of the universe when I say the preposterous universe. It's a reminder that there is something that we don't yet understand. And so we're working to understand it better. Anonymous says, ontological question about many worlds. Does many worlds say anything about the realness of probabilities before decoherence? Specifically when probabilities might destructively interfere and never get to branch into a world. I'm sorry, but it's a slightly too fuzzy. question for me to answer accurately, but I'll try to sort of talk around it and maybe hit on

what is going on. In my way of thinking about many worlds, before there's decoherence and branching, there's nothing to be probabilistic about. What the probabilities are, are the probabilities of which branch we're on in the circumstances when we don't know. The self-locating uncertainty once decoherence happens, I don't know whether on the spin-up branch, the spin-down branch, or whatever. Now, before, it is certainly true that before we do the measurement, we talk about a probability, right? And this again is because we invented all these words before we knew the physics or the philosophy behind what was going on. So what we experience as real human beings in the world is, I'm going to measure the spin. It's going to be spin up or spin down. I can't

predict exactly what it will be. But what I can do is judge the probability that it will be spin up or spin down. So I talk as if there is a unique event that will happen, and there's a probability of that event happening. According to many worlds, that's not what really, not what is really going on. Every event happens just in different worlds, and the probability means something different. But it turns out that none of that philosophical difference changes the way that we talk about or use the probabilities, so we stick with the same kind of language. So the way that I think about it is, I know, even though right now I know the exact wave function of the universe, let's say, or the exact wave function of the spin that I have in front of me, and I know exactly what's going to happen to it,

and I know there are going to be two of me in the future. So in some sense, everything is deterministic. I also know that both of those copies of me will have self-locating uncertainty because they don't know which branch they're on when the decoherence happens. So I know that all of my future selves will be uncertain. There is a sensible, rational way for all of them to assign credences to the different possibilities, and therefore it makes sense for me to act as if, and speak as if there is a probability, an objective probability of something coming true or not. Even though that's not what's really going on, that is a perfectly good way to talk, and that turns out to work. Rue Phillips says, if you and Jennifer were able to live as you do now without aging or getting sick,

and you could choose how long you could live before you pass on, how many years do you think would be interesting and why? Another 50, 100,000 years until the Earth is destroyed or until humans are no more. It's a good question. I mean, it's not a great question because this is very, very counterfactual. We're not going to live any of those numbers of years. We could live 50, I guess, right?

A hundred seems unlikely, but medical science could advance. But I certainly think I could live way longer than any of those. Well, any of 50 or 100, let's put it that way. A thousand, yes, I think very strongly that I could live at least a thousand years and still keep things interesting. Until the earth is destroyed or humans are no more, I don't know how long those are going to be. My puny half a century old self now has trouble imagining what I would be doing a million

years from now that would be interesting. But maybe in the next few hundred thousand years, I will come up with things to keep things interesting. So I really just don't know. I mean, if I had to pick now how long I would live, it would certainly be, I don't know, well, here's the extra problem that I have. I don't know what's happening to the rest of the world in this scenario. Like if there's an apocalypse or a, you know, I'm past the devastation of the earth and I'm the only living being, it's a lot less fun than if there's a more or less flourishing civilization I'm part of. But assuming there is a more or less flourishing civilization, I can easily imagine thousands or tens of thousands of years

of interest personally. Justin Wolcott says, do you think the benefits of consuming more than 30 minutes of news per day outweigh the downsides? Then he was on to list some of what he thinks are the downside. You know, I think this is actually a really good question because it's true that in the modern world, we are deluged with news or the ability to catch up on. all sorts of news and all sorts of places. And there is some feeling that you have an obligation to know what is going on in various corners of the world. But no one that I've seen has ever really

set out the specifics of what that obligation is or where it comes from. I do think that I want to be informed about various things in the world, but you can't be informed about everything, right? So there's clearly a choice being made. There's too much going on in the world to know everything, to know the name of every person and their personal situation, right? We coarse grain a little bit. So we're going to know maybe what goes on in a country, even if we don't know any of the people in that country. And I don't know.

We live in a world where, well, we live in a society here in the United States where the way that we govern our country is by representative democracy. We're supposed to vote for people who then run the government. And even those people we vote for, even though it's their full-time job, to make and implement policy, they don't know everything that's going on everywhere in the world. They have staff members to help them decide what to do on difficult issues. So I do think that there's a case to be made that we are sort of over-informed about some things, just in the sense that we can fret about them and feel bad about them without having any power

to do anything over them. At the same time, it's very clear that some people, many people, are under-informed about very important issues of the day. So I would feel very guilty going on some campaign to think that we should know less about what is going on in the outside world. Certainly here in the USA, the typical person is not very well informed about what is going on outside the USA, especially in countries that don't speak English, etc. So I don't know. It depends on whether you mean personal benefits or societal benefits. I think that as far as personal benefits are concerned, you could easily make the case that individual human beings would be better off not spending too much

time following the news, right? But there is some social obligation to be a good citizen also, so I'm in favor of knowing just enough. So I guess what I'm saying is I think this is a good and important question, and I don't know of anyone who's done a systematic answer to it, so I can't give you mine. Kyle Steven says, I've seen a lot of pop physics articles and videos recently, postulating that we live inside of a black hole. The idea itself seems reasonable at first take, but what would we look for to confirm whether this is true or not? Do our observations of the world align with this hypothesis? So I like this question because it's very easy to answer. No, we don't live inside a black hole. It is not reasonable. There are no observations that align

with this hypothesis. I can't absolutely rule it out, but let me both say what the right way to think about the answer is, and then the wrong way that some people sometimes do. What is a black hole? So a black hole is a region of space time with the property that if you cross into it, then you're going to hit a singularity in the future rather than ever being able to escape. You're not going to be able to escape without going faster than the speed of light. That's what a black hole is. Does that sound anything like our universe at all? No. We have no evidence that it's going to be a singularity in our future. And we have no evidence that there is anything called the outside, right? As far as we can see, the universe looks more or less the same, even to the

limits of our ability to look at it. So it doesn't look like it's embedded in some larger, empty space that we could hypothetically imagine escaping to. So for both of those reasons, those are the two properties of a black hole. You can't escape to the outside world, and there is an outside world to escape to. Neither one of those applies to. To our universe. So why would anyone think that this was a sensible thing to say that we live inside a black hole? Well, I think at least half of it is it sounds kind of cool and provocative, right? And people are going to get clicks by saying those kinds of things. There is a better reason than that. Still not a very good reason. And here's the better reason. There are various proofs going back to

Penrose and Hawking and Goroche and others that say that if you get enough energy into one place of the universe, then there needs to be, because of the gravitational attraction, a singularity either in the future of that region of spacetime or in the past. Now, of course, they had to say either the future or in the past because the equations of general relativity do not pick out a direction of time. They're perfectly time reversal invariance. So there's no theorem that says that if you just get enough energy in a region of the universe, it will collapse in the future to a singularity.

that would be weirdly picking out the future rather than the past, okay? So either one is possible. But a black hole does pick out a direction of time. A black hole is a region of space time into which you can go, but from which you cannot escape as you personally are moving into the future. So a black hole is a particular solution to the equations of general relativity that has a time ordering, that has a direction of time. But the theorem doesn't have a direction of time.

So what's going on? Well, what's going on is our universe, if you plug in the numbers, comes pretty close. You can argue about the details at the margins, but it comes pretty close to satisfying this criterion that says there's enough energy to have a singularity. That's not surprising because guess what? We had a singularity in the past, called the Big Bang. At least that's the prediction of classical general relativity where all of this discussion is more or less taking place. So, but that's not a black hole. In the black hole, the singularity is in the future, and you're surrounded by empty space,

so there's some place to escape from. In our universe, there's no empty space that we're surrounded by that we know of, and the singularity is in the past. If anything, our universe is like a white hole. A white hole is the time reverse of a black hole, and it has a singularity in the past from which you can escape. It's not exactly the same as a white hole, because as far as we know, there's no outside world to which we can escape, right?

But it's much, much closer than that conceptually than a black hole. So there's literally no reason to actually, if you understand what's going on, say that our universe is like a black hole. All right, I cannot pronounce this person's name. Liam Imden says, from an epistemological perspective, do you see any obvious ceiling for the current wave of AI research, or is it time to acknowledge this may well be a defining moment for the history of our species? You know, I presume there's some ceiling, but I don't think that I think that what do you mean is, is the ceiling like any moment now?

Are we being tricked into thinking that there's a rapid rate of progress right now, but it's actually going to slow down very quickly? I think that, you know, like we tend to see progress as something that has a rate when we look back on it historically from a remove. But real progress is very nonlinear, right? Poking around very slowly for a while, and then there's a leap forward. As I said, way at the beginning of the podcast, I think that things like, the current AI programs that are getting a lot of publicity are both super duper impressive in many ways and very different than what came before, and also not what we're kind of ultimately looking for in terms of actual intelligence in the phrase artificial intelligence.

I think this is what people are not – this is what I don't see people really wrapping their brains around, which is that there are these whole set of things that we're calling artificially intelligent that aren't like intelligence, really, in any noticeable way. But that doesn't mean they're uninteresting or unimportant. What is actually doable might end up being very, very different than what we set out originally to do. That doesn't mean it's not interesting or important. I don't know whether the current wave of AI research is going to end up being a defining

moment for the history of the species. I do think that these AI advances are very important and will play a large role, and they're not done yet. That is my not super-duper expert opinion. Sean Corum says, if there is something like five times more dark matter than regular matter, why do the effects of dark matter only show up at galactic scales or larger? Why doesn't the more prevalent dark matter have effects in the solar system such that it needs to be taken into account when calculating the orbits of the planets or space probe trajectories? So there is a simple answer there, which is that dark matter has different physics than ordinary matter.

And what I mean by that is the physics of dark matter particles interacting with each other. Ordinary particles have this thing called electric charge, which is very important. And the reason why it's very important is because the field that carries the force associated with electric charge, the electromagnetic field, is a massless field. It leads to massless particles called photons. And the reason why that is important, why is the masslessness so important? It's because when two particles come together to interact like an electron and a proton or two electrons or whatever, they can emit a tiny, tiny amount of energy in the form of a very, very low energy photon. If you think about the role, the relationship between mass and energy,

E equals MC squared is telling you the rest energy of a particle. And that's basically the least amount of energy it can possibly have. If you want to make an electron, you need at least MC squared of energy where M is the mass of the electron. If you want to make a photon, the photon's energy is not MC squared. Photons are massless. Photons have nothing but kinetic energy. They still have energy. But the minimum energy of a photon is zero.

You can go all the way down. And that's because it's massless. And so when you have a force that is coupled to some charge like electric charge and that is mediated by a massless particle, you can change the momenta and the energies of the particles with the charge by arbitrarily finely chosen amounts, by emitting just a little energy in the form of a photon. And what that means is, when different particles come together, they can dissipate. They can hit each other and then lose energy by emitting some photons, and that makes them stick together.

two dark matter particles, which as far as we know don't couple to anything like electric charge, certainly don't couple to electric charge, do they couple to some analog of electric charge? That was a paper that I wrote with Mark Kameankowski and others. Dark electromagnetism as a possibility. That's an open possibility, but the coupling would be very small, so it probably wouldn't be noticeable, otherwise would have noticed it. So for all intents and purposes, dark matter particles are like billiard balls. Okay, maybe they bump into each other, maybe they don't, but billiard balls are small,

so the probability that they bump into each other is very, very, very tiny. So for the most part, when you get a cloud of dark matter particles, they just pass right through each other. They don't clump. They don't make larger objects like the sun or the earth. The whole solar system, the whole history of the solar system, is the history of a cloud of gas shrinking by giving off light, by giving off radiation, by losing energy to the rest of the world and therefore condensing into planets and objects.

Dark matter can't do that. So there's lots of dark matter in the galaxy. There's some dark matter in the solar system, but a very, very tiny amount compared to the density of matter that we have in ordinary matter. And for that reason, you don't need to take it into account when you're thinking about orbits of planets or anything like that. Douglas de Young says,

I've been told that the event horizon of supermass of black hole is not a special place for an observer freely falling straight in. Why then can't I bring a small black hole with me? Is there something preventing a black hole within another black hole? No. I don't know who's been giving you advice about carrying black holes into other black holes, but there is no problem whatsoever in carrying a small black hole into a bigger one. I'm not sure why you'd want to do that,

but then it would simultaneously be the case that the small black hole inside the bigger one had the property that anything that entered its event horizon could not escape to the the surrounding area that counted as the big black hole, and the stuff within the region of the big black hole could not escape to the outside world. Both of those can be true at the same time. Andrew Goldstein says, to what extent do you think an artificial intelligence algorithm could be programmed to propose unanticipated life forms, consistent with Stuart Bartlett's term loif, i.e. dissipates energy, performs self-sustaining chemical reactions to reproduce, maintains internal conditions, and uses information about its environment to do. survive. Andrew's referring to the podcast. He was Stuart Bartlett about the fact that life as we know it has different aspects and we can imagine hypothetical organisms that have some of those aspects and not others. I have no trouble whatsoever imagining that we can create in a computer or nudge a computer itself to creating unanticipated life forms. I'm not even sure if we need artificial intelligence algorithms. So maybe that would be useful, but I think this is a good, you

place to be careful about what is the point of invoking artificial intelligence in a question like this. So we certainly have examples already of what are called, I mean, we can put evolution on a computer, okay? We can imagine situations that we have things that we call organisms that have traits and those organisms interact with each other and they mutate and they, you know, evolve, et cetera. We can do all that on a computer. I don't know if you would call it artificial intelligence at all, but something like that could very easily have some of the aspects of life as we know it and not others. So I don't think we've done as much of those kind of simulations as we might, but I do think that's an interesting thing to consider.

Sandro Stooky says, in your recent episode with Andrew Stominger, he said the number of gigabytes of information that a black hole can store is proportional to its area. And that is very, very strange because the number of gigabytes you could put on your phone is proportional to the volume in your phone. But that analogy seems problematic. The density of mass in my phone is low, the space inside it is barely curved, and the volume is a good proxy for the number of particles you can fit inside it as is its mass. So what am I missing? Well, I think that, you know, it's fair enough because you are catching physicists.

Andy Strominger happens to be the one in consideration right here, but there's many people who do this. They're being a little sloppy, okay? really the point that is trying to be made here is that there is no known system in ordinary physics where it's really true that even though it has both an area and a volume, the number of bits of information that we could imagine putting inside it scales like the area of the boundary rather than the volume. It's not supposed to be implied by that, that we had a good reason to think that inside black holes,

their entropy should go like their volume. What's really being alluded to in a very indirect way is that when you have a box of gas, when you have an ordinary thermodynamic system, at maximum entropy, the entropy is proportional to the volume. So when gravity is not important, entropy is proportional to volume in equilibrium. Black holes are in equilibrium.

Their entropy is not proportional to their volume. What is going on? Okay? That's really the question being asked. It's not supposed to be that there is some really reliable calculation that would have made it proportional to the volume. We just don't know, but the fact that it's so very different than the volume is maybe provocative. Domas says, I apologize if people are hearing a buzzing in the background. I live in a city now. There are machines outside the house. Sorry about that. Domas says, in the podcast with Rafael Buso, you had an interesting discussion on black holes and their challenges. On this topic, I wanted to ask you how much of those problems could be solved if we had a black hole nearby and we could send a probe there to cross the event.

horizon. Would that be very exciting and groundbreaking or wouldn't it tell us much? We don't know, right? If we knew, then we wouldn't need to do the experiment. But I could see it happening either way. I could certainly see if you had a black hole nearby, learning a lot from studying it. But we have very good predictions for what you should see near a black hole. So I also imagine that it's very, very possible. You could have a black hole, and all we would learn is that our predictions are right. All we would learn is that classical general relativity does a good job in accounting for the space time outside a black hole. That would not tell us about the extra questions we have about quantum black holes and how information gets out and things like that.

So there's no guarantee that you would learn very much. if the space time around the black hole that we had deviated from the prediction of gener relativity, that would be enormously interesting and informative. Probably that's not what I would expect, but it's absolutely something that's on the table. Matt says, on Earth, gravity makes things fall to the ground, but in space, gravity mostly seems to make things orbit around each other. Will Andromeda in the Milky Way eventually orbit around each other? I don't think it's right to say that on Earth, gravity mostly makes things fall to the ground and space orbit around each other.

Gravity is exactly the same in both conditions. What's different in both conditions is the set of possibilities that you are familiar with. On the Earth, near the surface of the Earth, there is an escape velocity, and if you threw an object with that escape velocity or greater, it would leave the surface of the Earth. It would not fall to the ground, okay? But that escape velocity is really, really high compared to your ordinary experience of the velocities that you know and love. So what you happen to be familiar with are things falling to the ground. The other important thing to keep in mind is that the Earth itself is not only a source of gravity,

but it's a big solid object. If the Earth were a black hole and you were in a spaceship the same distance from the center of the Earth that you are from the center of the Earth now, on its surface, the gravitational pull of the Earth would be exactly the same to you because you're the same distance from the same mass, okay? But the Earth would be much, much smaller if it were a black hole. So you could throw a baseball very easily that would go into orbit. It would not hit the Earth just because the Earth was smaller.

Baseballs fall to the ground and hit the Earth because the Earth is big. So there's nothing about gravity that is special there. As far as Andromeda and the Milky Way are concerned, guess what? They are coming toward each other. They are not really orbiting. I mean, they're kind of orbiting for the moment, but eventually they will hit each other and smushed together to make one big galley. It's going to take a while before that happens, but that's our ultimate fate. Nick B. says, what contribution do you think professional sports make to the violent rhetoric, polarization,

and aggression that seems so prevalent in U.S. society? And then he makes an argument that they are related. I think they're very, very tiny in the relationship, and the relationship might even be negative. For one thing, sports are very common in many other countries, not just the United States. And it's absolutely true that there are lots of examples of sports being related to violence or aggression, right? Soccer hooligans or riots after a championship is won or something like that. But I think one could at least as reasonably make the hypothesis that rooting for a sports team gives a channel an outlet for one's natural aggressiveness or desire to whoop it up, et cetera. So I don't know of any actual data one way or the other, whether the existence of sports tends to increase or decrease the amount of real violence in a society.

I would not be surprised if it decreased it rather than increased it. Varroon Nara Simuchar says, you've often talked about Julia Gallif's concept of the scout and soldier mindsets. I think there's a third one we should be aware of the prospector mindset. Like the scout, the prospector is also incentivized to seek truth instead of defending a doctrine. But unlike the scout, the prospector wants exclusivity and precedence in their discoveries. We all know the famously bitter historical contest for intellectual precedents, and we modern scientists are no less susceptible. do you see this as a problem and how do you deal with it? Well, I think that there are problematic aspects of it, but I don't like the idea that this is a third category that goes in there with Scout and Soldier. The Scout and Soldier mindset that Julie Gallif was talking about has to do with do we assume that we know things and we move forward and act on them? That's what the soldier does. Or do we keep ourselves in a combination of different

things that we don't know are true, go out and try to figure out, which is true. That's what the scout does. When you're talking about what you call the prospector, you're talking about the next step. You're not talking about that attitude that we have towards learning new things. You're talking about what we do once we learn new things. Do you want exclusivity and precedence? Or do you just want to share all of your knowledge widely? So that's a different distinction than scout and mindset. It's not a third concept within that category. Do I see this a problem in how the deal with it, you know, I don't be too wishy-washy here, but there are clearly beneficial aspects of that and clearly detrimental aspects of that. It would be, it's like capitalism. Capitalism also

has beneficial aspects and detrimental aspects. The idea of capitalism is supposed to be everyone is being selfish and looking out for their own interests, but it ends up helping everybody because everyone's interests sort of settle down to a self-organized, well-functioning society. I believe that there are ways in which something like that actually does happen, but I also think it's more or less indisputable that there are bad cases sometimes. We'll talk about some in upcoming podcasts. Likewise, in science, the fact that people want credit, the fact that people want to get some reward for discovering things,

I think pretty obviously increases the chances that things get discovered, right? It makes people work harder to discover those things. So there are clearly beneficial aspects of that. At the same time, there are clearly detrimental aspects because people undermine other people's attempts to learn new things and discover new things. So I kind of don't think that that's the kind of question we should seek a simple answer for. The better question is, how do we let people be competitive without letting them hurt each other along the way? That's a hard question.

I don't have any simple answers to it. Emmett Francis says, I went back and read through from eternity to hear, and I was struck by the use of extensive numbered notes at the end of the main text. I really enjoy reading through those, but sometimes I don't make the effort to when going through a given chapter. Can you speak to the choice to include notes like these versus just incorporating these thoughts into the text or including footnotes when necessary? Yeah, you know, I think that I like in my book writing to try out different things. You know, that was my first trade book. I had written the textbook, Spacetime and Geometry beforehand, but that was the first book I wrote for a general audience.

And what often happens when you're writing your first general audience book is you try to do everything, right? You try to put as much, you don't want to leave things out because who knows if you'll ever write another book. So, and I had a lot to say about the era of time and cosmology and relativity and things like that. So I said them all. And part of those were historical digressions and jokes and things like that, which I put, into footnotes, or end notes, I should say, not footnotes. So I thought that footnotes would be distracting in a case like this. I thought that end notes gave me the freedom to say all sorts of things.

And I absolutely admit that sometimes the end notes were not worth going for. Sometimes there were little gems in the end notes. Other times it was like, oh, I really skipped all the way back to the book just for this. I did fight hard to make sure that the cross-referencing worked. Like when you went to the end notes, it was made clear what page the end note was on that was being mentioned, et cetera. So I tried to make it as easy as possible. And these days, a lot of people read on an electronic device, where it is very easy to click on an end note and go back right away. Nevertheless, I haven't done it that much in subsequent books.

I think that in subsequent books, it has just seen given the, topics and given the style, et cetera, to be more useful to go straight ahead in a more or less linear narrative. I mean, in the biggest ideas in the universe books, the ways in which those books are different is that there's a lot of equations that I'm aiming at a slightly more technical discussion. But I have very few footnotes and very few references or anything like that. I'm really trying to, given that the actual text is hard and you really need to concentrate on it. I was trying to strip away any distractions. So I think it depends. I think it depends on what your goal is in writing the book, what audience you're trying to reach. Are you, are you,

like, there's a lot of postmodern books that are sort of pastiches written in different styles and things like that. Sometimes I indulge in that a little bit in something deeply hidden. We had the dialogue chapter, which I thought worked for that particular case. But I think the simple answer is, I play around with different things, trying different things as they are appropriate. and who knows what will happen in the next book. Brendan Kay said, while answering a previous AMA question, you said that to simulate the universe

would require a computer the size of the universe. But why does a simulated universe have to be rendered in real time? Could a smaller and simpler computer simulate a more complex universe given enough compute time? Sure. I didn't want to be taken too literally

when I said simulating the universe requires a computer the size of the universe. I guess the better thing to say is simulating the universe requires an amount of computation equal to the amount of computation being done by the universe, okay, which is very large. If you want to do that computation in some other arrangement, that's fine. Be my guest.

It's harder than you might think because the universe interacts with itself, dividing the universe up into separate bits and calculating it one by one and then knitting them together to make the whole universe, especially in a quantum universe where there's entanglement and things like that could end up being very, very difficult. But that wasn't the point I was trying to make. The point I was trying to make was just that there's a lot of computations involved in simulating the universe. Stevie CPW says, why is it necessary to reconcile gravity with quantum mechanics?

And there's more explanation there that I edited out. So, yeah, this is a common question. I think this is one that I have addressed before in different ways, but let me try in a slightly different way. we get along in various circumstances in physics with treating part of the system we're looking at classically and part quantum mechanically. Like you can often treat a heavy nucleus classically and then the photons that is interacting with quantum mechanically, for example. There is a semi-classical approximation in quantum electrodynamics. So it is therefore tempting to imagine that maybe the universe just is like.

that with gravity. The gravity itself is classical. But it can't work that way. It is literally just not possible for it to work that way, at least gravity as we know it, because it's not just that there's an approximation that works pretty well, but that the kind of thing you're dealing with is completely different. It's like saying, can you add a real number to a vector? You're just trying to combine two different types of things. It's not like you can do it approximately and call that good enough. It's just an impossible mathematical operation. In general relativity, you have space time and you have a field on space time. And so locations in space are very, very important. In quantum mechanics, you have a wave function. That's a very different kind of thing.

What you want to try to do, presumably, is relate that wave function to the energy and matter that goes into curving space time. But the whole point of quantum mechanics, there's not a number called the energy of the system at this point in time. At some point in space and point in time, you can try to measure the energy of a system at some point in space and time,

and you can predict the likely outcomes you're going to get, but there is no once and for all pre-existing number. So what is the gravitational field supposed to respond to? Maybe you're going to guess it responds to the expectation value to the average, the typical energy that you might measure if you were to measure things. But how you measure those things matters a lot.

And sometimes you're going to measure something very different, like in the real world. So why do the expectation value matter at all? So there's a fundamental mismatch between gravity and quantum mechanics. We can get away for certain approximate purposes, treating gravity classical and matter as quantum mechanical, but that cannot possibly be the deep, fine. answer. Justin Proctor says, why can I never think of good questions to ask in these kinds of things that haven't already been asked and answered? I think that's the question. Why can't I ask, think of good questions? This is, ironically enough, a very good question. Let me rephrase it as,

what does it mean or what does it take to ask a good question? Where do good questions come from? I'm not going to give you the once and all final answer here. I hope you're not disappointed, But I do think we can think about the issue in terms of, in particular, Justin is asking about your thinking, let's imagine, I'm putting words in Justin's mouth, sorry about that. Let's imagine that we listen to the podcast and we're imagining questions we could ask ex post facto after we've listened to the podcast, okay? What does it mean to come up with a good question? And I think the important thing here is that people are not empty vessels into which information is poured, whether in the form of a podcast or anything else, people have preexisting ideas about the universe. And when they're listening to something, when you're listening to a talk or when you're reading a paper or whatever, you're trying to reconcile that with what you already know. It might just be as simple as you have a framework for kinds of things that you could be learning and you're just sort of flipping switches to see where this particular presentation fits in, or you might actually have very specific ideas about the particular topic being talked about, and you're trying to see whether or not what is being

said or what you're reading agrees with that or disagrees with it. And I think that there's a couple different ways in which questions could be engendered. One question is, I was expecting you to say this, and you didn't, either because there was a hole in my understanding, like from listening to you, I sort of filled in what I thought you were trying to say in a systematic way, and I ended up with a gap, right? I didn't understand how you got from here to here, or I was expecting you to explain this thing, but you didn't. And that's obviously fruitful grounds for asking questions, right? Help me fill in my mental map of what it is you are saying. Another is, if there's just a conflict, right? I think that this is true. You said this other thing, and you

didn't convince me that my version of it was not the right one. So why did you think your way rather than my way try to convince me of it? I think there's, and none of these are algorithmic, right? Asking good questions is not something that you could easily write a flow chart that would teach you how to do it if you followed it every time. There's an art form in there. And then the last thing is, you know, practice. Everything. The answer, how do I become good at it, is practice. I remember there was a moment in my graduate school career where I just promised myself that I was going to start asking questions in seminars. This was a big step because I often didn't understand what was going on in the seminars. And the people who were asking questions all seemed to be like the big names and

things like that. It was a little step you had to consciously take. It didn't happen automatically. And also, sometimes you ask a question, you realize, that was not a very good question to ask. I could have done better than that. So working at it, Getting better is the best advice I can give there. Kevin D. is asking about, he says, I'm curious about joining my local physics slash science society, the Philosophical Society of Washington. However, I'm worried that I'll be a fish out of water there

in terms of both my experience in physics and my academic background. My motivation in joining would be just to listen to the occasional talk and learn something new. Do you think I should join or should I look for a more amateur type club? I actually think you should join. In fact, I think I'm giving a talk. talk at the Philosophical Society of Washington. I seem to have a recollection that I agree to do that. I'm too busy now to actually know what I'm doing more than a week in advance. And it's not this week

that I'm doing it. So who knows when, but keep a lookout for me on the calendar there. You know, I think that it depends on the society. I'm not very familiar with the Philosophical Society of Washington. But it's generally people who are interested, right? And everyone wants to learn. Like, I'm not an expert in most of the things I talk about on this podcast. So I got to learn. and I've got to figure out how to ask questions that get me even closer to learning things. I would hope that anyone who is a member of a society like that is similarly motivated. They want to learn things. And so being around people who want to learn things is also a good opportunity for you to learn things,

have them share with you. So I would be in favor of it. I wouldn't be worried that it's all full of experts talking at a PhD level. For one thing, there aren't experts in all of the areas. that might be interested to a physics slash science society. Even if you're highly trained in one area, you're not going to be in another. For another, you know, the experts who are trying to do their job might go to a professional conference or something like that

more than a physics slash science society. So I suspect there's going to be a lot of people who are other members who are educated non-experts or, you know, non-credentialed, but taught nevertheless by themselves, which it sounds like maybe you'd, fit into very well. Gota Einaval says the polarization of American politics is a worry for the whole world. I wonder if the parliamentary election system used, for example, in many European countries, could help. It would mean that the political parties put up lists in each of the states. Each state

sends a particular number of representatives to the parliament, Congress, and these representatives are distributed between the parties according to the size of their vote. The experience from the Nordic countries is, I believe, that this generally reduces the power of extreme. and gives more power to centrists, since they more easily can make coalitions. I think, you know, I don't have a strong opinion one way or the other. I think that if you look at European countries versus the U.S. or whatever, there's clear examples where the U.S. has done well, the Nordic countries have done well, the southern European countries have done well, and examples where they've all done badly. And I don't know enough of the systematic history

to make a final judgment. I think one issue is that it's always easy to see the problems with the current system. It's hard to see what new problems might arise if you change the current system. It's true that the parliamentary voting system might very well make it harder for extremists have a lot of power. On the other hand, if you get unlucky, you can have two mainstream parties that split the vote and some tiny extremist party is the one that needs to make a coalition with one of the bigger ones, and therefore you've suddenly given more power to the extremists. And also there was this idea during the founding of the United States of explicitly separating the powers between presidency, judiciary, and the legislature to make it harder for one

idea to take over and quickly be implemented amongst a small group of people. The downside of a parliamentary system is that the party in power has a lot of power to get things done. That's also the upside. That's the irony of politics. But you can't have divided government between President and Congress. And the original idea of the U.S. founders was that divided government could be good. It could actually reflect the people's inability to choose what to do.

Now, or at least the people's incomplete fealty to one side or the other. I think the idea originally was that if you had divided government, If you had Congress in the power in the hands of one party and the presidency in the hands of another party, they would have to compromise and work together to do things that were benefiting the common good. In the present situation, that doesn't happen. So I'm completely open to suggestions for ways to work in the real world, in a world where the game theory, as we talked about with Ezra Klein years ago, the game theory calculation has been done by politicians,

and they are more likely to stay in office by opposing everything the other party does, whether or not that's the best thing for the country. Having said all of that, I mean, in some sense, you know, it's just us talking here. There's nothing going to be done. There's zero chance the United States is going to have such a dramatic change in its governmental system that will become a parliamentary system. The people who would need to make that happen have a vested interest in not letting it happen. So we should be thinking about if we want to make things better, more realistic ways to fix things.

Paul Cousin says on the Inquiry Minds podcast, I heard Antonio Padilla talking about the weight of information, say, when you upload a photo to your phone, you're making it ever so slightly heavier. He did not express it as a metaphor, which troubles me. Is that literally true? So I don't know if that's literally true in the case of uploading a photo to your phone. things like that can be true, but they don't have to be true. So imagine, it's not some strictly speaking law of nature that an information containing collection of particles has more energy than one that does not contain information. Think, for example, of a set of go pieces, pieces for the game go.

So little white stones or black stones, arranged in a lattice. If all the stones are white and there's no nothing, no pattern there, no information, it weighs a certain amount, has a certain amount of mass. And if you use the white and black stones to write some message so that it does contain information, if it's the same number of stones, it's the same mass. There's no interaction energy between the stones, et cetera. If it were spins in the lattice of some material, then the spins would interact with each other. and then they might have lower energy

if they're surrounded by all spins that are like themselves. In that case, the attempt to actually put information in would require flipping some spins and therefore raising the energy. That might actually physically be what happens in a camera. I don't even know what the physical way that real-world iPhones, et cetera,

capture images are. So there are actually, there absolutely are examples where putting information into a system increases its mass. Now, it might be more general than that also, but it might, but there's still going to be assumptions in the background about are you in contact with a thermal bath or something like that. So I don't want to discount the idea. There are very, very interesting ideas about the interplay of information and energy and entropy and things like that, but it's a complicated thing

that you, to get things exactly right. You have to be very, very specific about what your assumptions are. I guess at the end of the day, I have a little bit of resistance to thinking of information as physical, which is like a motto in some of these subfields. I think that physical stuff is physical, and it may or may not contain information. But if you didn't have any physical stuff, then you couldn't carry information. So I think the physical stuff comes first in my way of thinking about the world. Brendan says, does infinity actually exist in the physical world? I know time and space might be considered infinite, but is there an actual way of us distinguishing between truly infinite and just really big that is just close

to infinite. You know, the answer is we don't know. Infinity is a very useful hypothesis in many cases. In many cases, it's easier to do calculus, for example, where you're imagining that there are an infinite number of points along the real line than it is to do discrete math, where you divide things up into tiny but finite intervals. So it might be just a convenient approximation, but we don't know. We don't know whether an infinite number of points in space. We don't even know if space is fundamental or emergent. We don't know if space lasts forever. I'm not sure how we would know other than to be able to say at some future time, not right now, but be able to say thinking about the world using the concept of infinity turns out to be way more useful than thinking about it in some finite or discrete sense. So I think we should keep an open mind about that. We can't demand answers to all the big questions right away. Speaking of which, Johann Lovgren says, is there a relationship between naturalness and emergence? The short answer is, no, not that I know of. I'm not even sure what naturalness is.

We use the word naturalness a lot in different contexts, but again, you have to be clear about what the context is. So there are specific examples in quantum field theory, where you can say that a quantity is natural or not natural, and Gerard de Toft and other people have given very specific definitions of what they mean about that context. But that might not be what you mean in a more general philosophical context about naturalness. If you think of naturalness as just this is something that would not surprise us given our expectations, that is such a broad category that it's hard to know what its relationship would be with anything, much less with emergence. Let me say something that I think is true, but I'm not even 100% sure, but that gets to the, issue raised by your question, which is that if we think of emergence as, you have some

comprehensive microscopic description of a system, whether it's atoms or superstrings or whatever it is, but some low-level, fundamental or close to it description, and you also have a higher-level, coarse-grained emergent description, okay? Let's imagine that you have that. Let us ask the question, what are the features of the lower-level theory that allow you to have a higher level coarse-grained theory? I think the answer is we don't know. I think it's a good question. It's one that I think about at a research level, but I don't have any very strong opinions about what the right answer is. So even if all you do is ask, do most possible microscopic theories have an emergent higher-level coarse-grained description, or is it very, very rare? I don't even know the

answer to that. I suspect it's rare, so I suspect that there is some non-naturalness to the existence of emergent descriptions, but I honestly don't know. I would like to know much more about that. Richard Moore says, in two previous AMAs, a listener asked about lottery election systems. It seems to me that approval voting, in which voters place a checkmark next to as many candidates as they wish and each checkmark is counted as one vote for the candidate, removes what I think are the worst aspects of our plurality system. The spoiler effects and the tendency to polarize both the electorate and the candidates. And since it is not a ranked voting system, it is not subject to the limitations imposed by Arrow's impossibility theorem? What do you think of this system?

I'm not a big fan of approval voting, although I do get that it has some advantages, especially over plurality voting, which we have right now. But that's not hard because plurality voting, everyone knows is the worst, except that it's the simplest. That's the only, it's simple, you go in, you vote for one person, you walk out, right? That's simple in that sense. in approval voting, you say whether you approve or disapprove of a long list of candidates, you instantly run into the problem that a lot of these names are ones you might never have heard of. So presumably you don't approve of those if you've never heard of the names before, but that might not be perfectly an accurate reflection of what you would think if you did know about them.

But the other thing, the bigger reason that I would worry about approval voting is that in my thoughts about this, I have come to appreciate the important. of the intensity of belief. I don't care so much about Arrow's theorem. Arrows theorem is interesting as a mathematical result, but it's not a practical worry in most cases. What is more important in most cases is the idea that if I just vote for someone or don't vote for them, that's a harsh binary choice. It is not saying, well, I really, really, really want this person and, you know, this person I could take them or leave him, and it ends up being the same vote, right? Like, do I approve of some you know, someone who I would go to the mat for and someone who I could barely tolerate might both get my approval.

And that is information that is thrown away by that kind of voting system. But again, I don't have the final answer. I don't know what the right voting system is. So don't take me too seriously about that. That's just my off-the-cuff impression in that direction. Mike Meyer says, The temperature of the cosmic microwave background is roughly 2.7 Kelvin in all directions. If I start traveling at relativistic speeds in one direction,

would the temperature distribution of the CMB appear an isotropic, hotter in the direction I'm traveling and colder in the opposite direction? Yes, in fact it does, even though we're not moving at relativistic speeds with respect to the microwave background. There is a dipole temperature onisotropy in the cosmic microwave background that is big. It's, you know, 10 to the minus 3, as opposed to 10 to the minus 5 for the intrinsic temperature variations, and we attribute that dipole to our motion with respect to the cosmic microwave background rest frame. So basically there is one rest frame with respect to which the microwave

background looks completely isotropic at the dipole level, at this side versus that side level, and no other rest frame will have that property. And that was actually the first thing discovered in terms of temperature and isotropies in the cosmic microwave background. It tells us how fast we're moving through space. I forget the number, something like 300 kilometers a second, seems to roughly be the order of magnitude. Faisal Siddiqui says, on the black hole information loss paradox, I've listened to the Neda Englehart episode several times, but I'm sorry I still do not understand how the book burning in a bonfire case is different than throwing a book in a black hole. Could you please elaborate? Well, roughly, in the book burning in a bonfire case, we know enough physics

to predict given the entire book and the entire fire down to the level. of every atom and particle, precisely what radiation will be emitted, okay? We can make an absolute prediction using the Schrodinger equation and the standard model, etc. We know exactly what the information is going to be, the exact distribution of radiation and ash and heat and whatever. We know exactly what it will be in principle. In practice, of course, that's way too much information. We can never do it, but in principle we could do it. In a black hole, we don't have that. In a black hole, according to Stephen Hawking's calculation, What comes out is thermal radiation.

That tells you the spectrum, you know, the average amount of this wavelength and that wavelength and that wavelength, but we don't know exactly what is coming out. We have no way of doing that calculation. There seems to be, in Hawking's Way formulating the problem, no relationship between the information stored in the book that you throw into the black hole and the radiation that comes out other than how much mass the book had.

So it's actually a very different question. And the reason why it's an interesting question is because you might say, well, okay, do a better calculation. And that's what people are trying to do. But it turns out to be very hard to know what to do. And there's elaborate arguments that say there needs to be non-locality. I mean, the book falls in. It's inside the event horizon. And it's not bleached or anything like that.

All the information is still there. Somehow it gets outside the event horizon. How did it do that? That's the essence of the real problem. Josh Powers says, what would be the differences between real universes and simulated ones? Do you think there would necessarily be any significant differences, or might real and simulated universes be practically the same for any intelligent beings inhabiting them? I think they could be practically the same. I don't think there's necessarily a significant difference to put it in your terms.

If you're interested in this kind of thing, I can heartily recommend David Chalmers' book on the idea. We had David on the podcast years ago, and it was interesting because, you know, David is a very, very famous philosopher in consciousness, coiner of the term, the hard problem, et cetera. So I wanted to talk about that. But he was in the midst of writing his book, which is now out called Reality Plus, about simulated universes and virtual reality and does it count as reality. And he tries his best to make the case that it does count as reality. So I would check that out. It's a very, very good book, very, very readable. A. Lama says.

what's a reasonable credence that the accelerating expansion of our universe is characteristic of the whole universe? Do we assume this due to simplicity naturalness, or do we have some observational evidence? Well, neither. We don't assume it at all. It depends on what you mean by the whole universe, of course. We observe part of the universe, right? There is something called the observable universe. Within the observable universe, things seem to be the same everywhere, given that we're looking at the past when we look at far away things, as far as we can tell, by looking at things, things are on average the same everywhere, including the fact that the universe is accelerating. So that's a data-based conclusion. Beyond the observable universe, we neither have evidence that it is

accelerating in the same way, nor do we assume, nor do we have to assume, that it is accelerating in the same way. It could be that the universe continues on for some finite time, finite distance, or infinite distance, doing more or less the same thing that it does in our observable universe, or things could be radically different. As in theories of eternal inflation in the multiverse, things are radically different outside our observable universe. So we just don't know, and it's good to keep an open mind. G. Kloon says, I listen to slash watch some other podcasts or YouTube videos of people who are

doing something similar to you. I'm not an academia or science, but many of these podcasters constantly say, one, that universities and science have been taken over by the woke, woke culture and the left, which is something they always paint as negative. And two, I also hear that many physicists aren't doing real science, that physics is in crisis and there's a group, a lot of group think and that non-mainstream views are forced out, especially when it comes to string theory and dark matter. You're much closer to this than I am.

Do you have this feeling? Is there any or some truth to what these other podcasters are saying? I'm skeptical, but would love to have your take on it. you know, this is the kind of thing, no, it's roughly speaking, not true. That's the very, very short answer. But, you know, they're close enough to true things that you can see how they can get away with saying things like this. It's in both cases, in the case of both the accusation that universities have been taken over by the woke, woke culture, and the idea that science is in a crisis and there's a lot of group think. In both cases, there is something going on that I think is, legitimately worth thinking about and critiquing. But also in both cases, these legitimate issues are taken up as fuel or ammunition, would even be a better word, for some political background viewpoint that they want to push. Usually in the latter case, when they say physics is in crisis and there's a lot of group think, the thing they want to push is their own physics idea. And they're

sad that the establishment does not give them recognition for their brilliant physics idea. In the former case, when they're complaining about woke culture on the left, they're probably trying to support things on the right. That's usually how these things work. Now, like I said, there are things, there are things worth critiquing. I'm not saying that there's nothing to be critiqued here. I think the extent to which woke culture has permeated and taken over universities is incredibly exaggerated as someone who's spent a lot of time in universities.

But I think there are legitimate critiques to be made that there is a segment of academia or academic culture that is not open enough to listening to ideas that they don't agree with. I think that's a perfectly legitimate conversation to have, but it's a tricky conversation to have, and it's made much harder by the politicization of it, which is as soon as you hear people complaining about the word woke, they're using this for some political agenda. They're not trying to have some careful conversation with an open mind about difficult issues. They're trying to bludgeon you with some heavily emotionally laden verbiage. And you should listen to other podcasts in that case.

For the physics case, I might do, actually, I've been thinking about doing a solo podcast on this or something like that, but I do think that there are trends within physics that are absolutely worth critiquing. You know, I've done it. I've critiqued them. When we talk about foundations of quantum mechanics,

I've certainly critiqued it plenty of times, but there are deeper other issues. The idea that it's, it's group think and that it's a crisis and things like that. Again, this is just, you know, emotionally charged language that is trying to make the issues more obscure rather than making them more clear. And so it becomes harder to talk about these issues. I don't like talking about issues where the issues are intrinsically difficult and subtle and you have to think about them, but that there's a whole bunch of people who turn them into manichy and black and white politically

charged discussions. You know, I just tend to stay away from that because I don't find enjoyable, personally. But sometimes it's better to, you know, even if it's not enjoyable, you got to talk about it one way or the other. So that's my take on it, as you say. Paul Duffield says, one of the ideas from past guests that you bring up a lot is Paul Blooms against empathy. Is it just a coincidence or is it something that you're specifically mulling over and trying to get opinions on from a variety of perspectives? Well, I think, I hadn't noticed that, but I absolutely believe it is possible. My explanation for it would be that I strongly believe something more or less the opposite of what Paul argues for

in that book and that in that podcast. But I do, you know, respect Paul's thoughts on it and his work as a psychologist, et cetera. And I don't think, you know, he's not, he doesn't fall into the category I just said of people trying to, you know, oversimplify and politicize things. He's thinking about difficult issues very carefully. But I strongly think that having more empathy is really crucially important. And the distinction seems to be that Paul is convinced, if I understand correctly, he's convinced that empathy is just flawed

because we're going to always have empathy more for people like ourselves and lesser people unlike ourselves, and we should strive to be more rational rather than empathetic to make the world a better place. I am much more impressed by people's failure to be rational, and they're even more and more subtly, their ability to think they are being rational while actually ignoring some very important aspects of a problem.

And I think that empathy is one of the ways to help us, help us, what is the right way to do it? To help us avoid that mistake, to help us make sure that we are considering all the relevant aspects of the problem by trying hard to figure out what other people in very different circumstances would be thinking about this problem. Rationality is great, but it's almost too hard. to do it by itself. It is, or rather, it's not that rationality is hard, is that it's too easy

to use rationality badly. And I think that empathy can be a, something that helps us get over that. And Paul obviously thinks the opposite. So I'm interested in what other people think from different perspectives. Mickle Pickle says, what is it about mystery movies and books that you find engaging? You know, in some sense, it's science, right? In some sense, it's science. In some sense, a mystery novel or book or movie is posed a puzzle, posing a puzzle, having data, and you try to like put the data together to solve the puzzle in a way that is predetermined to wrap up nicely at the end of some time. So it's like science where you always know you're going to find the answer.

What could be more enjoyable than that? Patricia Paulson says, I can get how particles can exist for most forces, but cannot figure out how a particle, the graviton, could exist for gravity. which is geometry. What am I seeing incorrectly here? It's not that there's anything incorrect there. It's the mismatch between particles, gravitons, and the statement that gravity is geometry. Classically, gravity is geometry. But the particles, the graviton, comes from quantizing the theory, and then it's a different kind of thing, right? The trajectory of a particle in phase space is deterministic, classically. It's a wave

quantum mechanics. It's a different kind of thing. Okay. So, you know, as I alluded to before earlier in the podcast, there's space time and there's the metric on space time. Okay. So the metric is a field that takes on different values at different points in space and how the values relate to each other at different points in space time tells you what the curvature is. And that's the classical way we have of describing how geometry works and where gravity comes from. But then the quantum theory of that says that there is. is no once and for all gravitational metric field. That's the equivalent of a classical trajectory, right?

That's not what the world is made of. It's a wave function. And that wave function in principle, not in practice because it's too hard, but in principle, the wave function of the metric tells you, if you were to measure the metric all throughout space at one moment of time, what is the probability of getting different results? And the nice thing is, so we don't have a full theory of quantum gravity, But the nice thing is what we can do is look at the weak field limit.

Just imagine the gravity is very, very weak, in which case we can approximate the curved gravity of space time as flat space time plus a gravitational field on top of it. And then we just have a field in flat space time that we can quantize, and that we know how to do. We've done that a lot. And so the small perturbations of the metric tensor that describe gravity,

in the weak field limit are something we can very easily quantize. And out pops gravitons, out pops particles. It's almost inevitable. In any sensible quantum field theory, you're going to get particles in the weak field limit one way or the other. And the reason why you get gravitons is exactly the same reason you get photons or whatever, because there are quantization conditions on the energies of vibrations in the field once you do the rules of quantum mechanics. to it. Just wait to see book two of the biggest ideas in the universe where I talk about this a little bit

more detail, or you could just look at the video, right? There's videos on, in the video where I talk about fields in the biggest ideas in the universe series, I do talk about why you get particles when you quantize a field. P. Walder says, what do you consider are the issues in fundamental physics that make explanations of downward causation difficult to accept? The short answer is locality. Okay? Downward causation is the idea that somehow what is going on at the higher levels of a series of emergent explanations,

emergent theories, emergent descriptions can somehow be important for explaining what happens at the lower levels. So the caricature, it's not quite fair, but it's pretty darn fair, is electrons would behave differently if they were in a rock or a brain or a snowflake or a fungus or something. something like that. The larger context in which the fundamental particle is embedded could be affected by a downward causation from the broader ensemble of which it is a part. That's a perfectly legitimate idea to think about, but it is entirely 100% incompatible with everything we know about quantum field theory. In quantum field theory, the state of the electron, Let's just speak classically before we get to quantum field theory. Just classically, there's an electron field, or there's an electromagnetic field, or a gluon field,

or whatever field you care about, and there's an equation of motion for that field that tells what it does. And that equation of motion says the value of the field at one point in space is changing. That's what equations of motion tell you. And the amount by which it's changing depends only on the values and the derivatives of other. fields at exactly the same point. It is very clear, completely unambiguous, that nothing that is going on at other points in space far away can possibly affect the equation of motion for the field at this point. You can imagine equations of motion that do that, but they're not field equations. It's not a field theory. It's something else. And quantum field theory is exactly the same way, but with quantum mechanics. So you need to fundamentally overturn the principle of location. for downward causation to be important. Also, I see no evidence for it, so I'm not going to spend a lot of time.

Anonymous says, can you explain the cross-product to me without the right-hand rule? Like, where does it come from? Why is it always perpendicular to the original vectors? I dip my toes into Lee algebra in my particle physics course,

and it feels like the answer is hidden there. This is an almost impossible question to answer without knowing what would qualify as a satisfactory answer. I mean, you can always just give the definition of the cross-product. For those of you who don't know, if I have two vectors, you know, the two vectors in three-dimensional space always describe a plane. You can always imagine the plane in which both vectors are simultaneously embedded, okay?

So the cross-product of those two vectors is a third vector that is perpendicular to that plane, and the magnitude of the vector is the product of the magnitudes of the two vectors you're multiplying by each other times the sign of the vector of the angle between them. Is that right? Is it the sign? I believe it is, yes. So if the vectors are lining right on top of each other, the sign of the angle, the angle is zero.

The sign of that is zero. So the cross-product vector is also zero. If they're perpendicular to each other, the sign of the angle. that angle is one, and so the magnitude of the cross-product is just the product of the magnitude of the two vectors. So if you think about it, what did you do? When the vectors are perpendicular to each other, the magnitude of the cross-product vector, if one magnitude is A and the other one is B, and they're perpendicular, the cross-product

magnitude is A times B, which is also the area of a little rectangle that you would make by drawing those two vectors and using them as two sides of the rectangle. Whereas if you squeeze the vectors together, so they're on top of each other, now the area of the rectangle that they describe is zero, because they're both right on top of each other and the vector is zero. So the magnitude of the cross-product vector is just the area of a little parallelogram that the two vectors describe. Why is it always perpendicular?

Well, we defined it that way. So that's one perfectly legitimate answer to that question. But let me back up a little bit and just ask, you know, the game that is being played here, mathematically speaking, physically speaking, there may may not be uses for these games, but the math game is the following. Here are two vectors, based at the same point, okay? So they have the same tail, and they point towards different heads. And let's ask ourselves, what other vectors can we construct from these two vectors that are perfectly well-defined, by which I mean they don't depend on arbitrary choices we make about

coordinate systems or components or anything like that, they're just intrinsic to the vectors. It turns out there aren't that many vectors that we can define just by using the information we're given in these two vectors. The cross product is one of them, as it turns out, in three dimensions of space. In higher dimensions, there's a whole different set of things that can be done. You would need to read about differential forms and wedge products and exterior products and things like that. I write a little bit about those in my book, Space Time, and Geometry,

but I don't know of a resource that is specifically aimed there. But I think that the philosophical thing to say is there aren't that many well-defined constructions that make a third vector out of two. Here is one of them. Its direction is perpendicular to the first two,

and its magnitude is the area of the little rectangle, a little parallelogram that they define. It's a perfectly good thing to define. And there's a whole separate thing about why that's really useful in actual physics. That's, yeah, that's another question to get that. I'm not even sure I know what the answer is. Okay, I'm going to group two questions together.

Josh Belsman says, I'm forever trying to wrap my head around the vastness of many worlds theory. Does it suggest that there's a universe representing every possible permutation of every subatomic particle interaction, or whatever is even more granular than that? or is it more like a neural network or probability tree where each new universe is based on a subset of likely prior permutations? And then John Stout says, John S. Bell wrote, one is given, this is a complaint that Bell had about many worlds.

One is given no idea of how far down toward the atomic scale the splitting of the world into branch worlds penetrates. Can you address this issue? So two things to say. I mean, there's the sort of background philosophical point and then the down and dirty point. The background philosophical point is, as I've already said in this podcast, I don't care. Different people are welcome to be prosnickety in different ways about when the universes count as different universes or when the branching happens.

As long as two things are satisfied. Number one, the whole wave function of the universe is just the actual wave function obeying the Schrodinger equation. And number two, when the branching has clearly happened because there's decoherence and there are two different macroscopic worlds, you count them as different macroscopic worlds. As long as those two things are true, you're welcome to be specific about whatever rule you want to invent for what counts as different worlds. I don't really care. Doesn't bother me. Doesn't affect my life. However, okay, operationally, that's the background philosophy. Operationally, branching happens when decoherence happens. Branching happens when the quantum system that was originally in a superposition becomes entangled with its

environment irreversibly. That's what decoherence is. And then what happens in the one branch of the wave function no longer interferes with or can be affected by what is happening in the other one. Therefore, we're allowed to treat them as separate worlds. So I really, I mean, this kind of thing, this makes me feel like Boltzmann must have felt. You know, Boltzman in the 1800s tried to say, I know what the second law of thermodynamics is. It's just because there's a lot of particles and they probably move toward higher entropy because there's more ways to be high entropy than to be low entropy. And he got a huge number of people saying, what do you mean probably? The second law of thermodynamics is a law.

You're not allowed to say it probably happens. It has to absolutely happen. But the probabilities are so large that it didn't have to absolutely happen and it didn't really matter. It could be perfectly okay just to be an approximate kind of thing because it was more than good enough. Branching in many worlds is just like that. You don't need a precise, absolute, absolutely, perfectly agreed upon definition of when it happens. It happens perfectly obviously in the macroscopic cases we care about.

In the microscopic cases where it might be ambiguous, you're welcome to define it however you want and nothing changes one way or the other. Certainly the fundamental ontology doesn't care. Jan or Jan, not sure, says, I recently decided to obtain my genome sequence. Most of the people I spoke about this topic prefer not knowing their genetic background because of the fear that an unknown health risk might be detected, I find this attitude quite curious because it is ignorant,

because being ignorant of a health problem, of course, doesn't prevent its manifestation. What do you think about the pros and cons of knowing your own genome sequence and have you considered obtaining yours? I'm totally in favor of it. Yeah, I'm absolutely on your side, I think, if I pull out the implications of your question correctly, that to know that you are susceptible to getting a really bad disease more than the average amount

seems like really, really useful information. Maybe you can take some steps to prevent it or mitigate it or something like that. I don't know. But I would certainly want to know that if I could. So I don't get that particular objection to it. Now, I do get that there are worries mostly from third parties who just, who just don't trust individual human beings to take probabilistic information and use it reliably. You know, people are worried that if you find out you have a 10% chance of getting something

rather than just a 1% chance, you'll be panicked. And so I think I can judge my own probabilities pretty well, so I'm not worried about that. In the real world, in practical questions, I do have questions about many of the companies that actually do this. You know, they're doing studies. They're collecting data from you. You are the product, not the customer for these people, usually. They want to see, you know, various frequencies of various things happening. And it's a little bit shady. I'm not sure. Maybe it's fine. I don't know. I haven't looked into it. I haven't done it. But not out of any principled objection to it. Just that I'm busy doing other things and haven't really felt the need to do it yet. Michael Schillingford says, What are your views on selfhood? Particularly do you believe that there is an emergent self? Well, I think there is a self.

I think the self is not fundamental. Therefore, yes, I think it is emergent in the sense that we've been talking about earlier. That is to say, the idea of a self is something that is nowhere to be found in the fundamental laws of physics, but is clearly very useful as part of our description

of the everyday human-sized world. So, therefore, it is emergent. That is the definition. basically. And I think that, you know, there's a lot of subtleties here. There are subtleties about the self through time. Are you the same self tomorrow that you will be yesterday? Remember we had the conversation with Lori Paul about transformative experiences? You could be a very different self in the future than you are right now. And how do you rationally account for that possibility? Of course, many worlds opens up lots of metaphysical issues about the self. I think

the easiest way to deal with all of these issues is to say that the self was always an approximate notion, or I should say the idea of persistence of the self through time was always an approximate notion. You're never exactly the same person. You were a minute ago, much less a year ago. But to a good approximation, there is some continuity there, right? And I think exactly the same thing works in many worlds or whatever. But, you know, if we ever build a transporter machine, you might have to think more carefully about what exactly counts as the self. David Dubrow says, Reading from eternity to hear and now something deeply hidden,

am I right to see a parallel between many worlds and your approach for explaining the enigma of the past hypothesis? In both cases, there is a puzzle that seems to point outside our universe for an answer. In many worlds, the apparent collapse of the wave function is no collapse at all. Decoherence of a superposition creates multiple branches of the wave function and they all exist. Similarly, you can explain that. the seemingly low entropy beginning of our universe by positing a larger system that somehow spawns baby universes, and when those expands, their entropy increases. It seems that it all comes down

to this. What we think of as our universe is just part of a larger system, and in the context of this larger universe, these enigmas no longer exist. Yeah, you know, I haven't really thought of that particular commonality between those two beliefs, but yes, I think it's there. I agree with it, And in fact, you know, with respect to what we were saying earlier about naturalness and so forth, it makes perfect sense. The preposterous universe question. There are things about our universe that seem mysterious. Why? Because we have certain expectations.

And there are features of the universe that don't match those expectations. So the universe is not wrong. Clearly our expectations are wrong. How do we retrain our expectations? Like you can say, well, fine, your expectations were wrong. But just saying that doesn't get you anywhere. That's not helpful information. That doesn't move us forward.

To move us forward, you have to say, okay, here is what your expectations should be and where they should come from. And putting the universe that we observe into a larger context can be one way of doing that. I'm not going to say it's the only way or the universally best way or whatever, but it can often be a way of doing that. So it's not surprising to me that in these two contexts that kind of move. works well both times. Jeremy Ditman says, in your episode featuring Danny Bassett and Perry Zern, you briefly discussed the policing of curiosity. And I'm wondering if the 1970s PRL policy banning the publishing of papers concerned with

foundational questions in quantum mechanics serves as an example of this in the physics community. Do you believe the ban effectively delayed advances in our understanding of entanglement and quantum computing, for instance? And is this something akin to? this, still happening today in contemporary physics from your perspective, or has the massive expansion of roots for publishing and popularizing, effectively mitigated this sort of policing? I think this is one of those tough questions, I got to say, because there is absolutely

policing of curiosity that goes on, but I can absolutely see that sometimes there should be policing of curiosity, not in the sense that you literally want thought police, tracking you down and punishing you if you're curious about the wrong things. But in the real world, especially in academia, where we're trying to understand the universe better and we're doing it by thinking about things, being curious about things, doing research on them, writing them up and sharing those ideas,

we're up against the finitude of our resources, right? Of course, it would be best if every possible idea was chased down by somebody. But most of those ideas are not going to turn out to be very good, and we don't have an infinite number of people. So, in the real world, we have to choose, it's not a matter of policing so much as we have to choose to support investigation of some kinds of curiosity and not support others. If you're an advisor of PhD students and your students want to write a paper or a thesis on some topic, you have to be judgy. You have to say, yes, that's a good topic. No, that is not a good topic.

And the reason why it might not be a good topic might be because I don't think you can do it. it. I don't think the results would be interesting. I don't think anyone else cares about those results. I think there are other questions that would be better served by your talents, et cetera, et cetera. So there is some necessarily some shaping of where we give support and encouragement in different kinds of curiosity. And I'm sure this can be extended well beyond the narrow confines of academia and research and things like that. So, but of course, it can also be bad, right? It can also be I don't think this question is interesting, therefore nobody should think it is interesting. So again, this is a fuzzy answer because not an extremist in either way, but I think that it's interesting and important to reflect on whether we are in good faith, judging that a certain idea is just not worth the resources to pursue or whether we're just being a curmudgeon and saying, yeah, I don't know.

I didn't think about things like that. It sounds very different than what I expected, so go away, right? There are good and bad reasons to take a stand against doing certain kinds of research, is what I would say. Again, if there were infinite resources, then there'd be no good reasons to prevent people from doing whatever they wanted, but there aren't. So something has to give. Nalita S. says, what in your upbringing would you say helped you be humble with a growth, mindset. I'm a teacher and want my students to have those kinds of traits. I don't know. Yeah, that's a very good question. You know, I'm being a teacher, even though I am a teacher,

you know, I teach college students. And I presume college professors call themselves professors usually not teachers, even though they certainly are teachers and they do teach. I presume that you're teaching younger students than that. And even though it's a very important activity, we get very little training in it, right? We're not very reflective about how best to do it and not even just to the explicit teaching part, but the guidance, the supervision, the advising of things that are tangential to or completely outside the classroom. So things like how to inculcate and encourage humility or growth mindset or something like that, I really don't have any explicit advice. I think the one thing I can say, not very helpful, but the one thing I can say is exemplify

those virtues if you want students to get them themselves. Like they're hard to train. Like, you sort of have to hope that the student already wants to be humble. If they don't want to be humble, it's very hard to get them to be humble. But if they want to be, you can help them move in that direction. Like, you can want to be humble but not succeed, right? Or you can want to have a growth mindset and not have it. But then at least maybe you'll put some effort into trying. And in those cases, just seeing it done is as valuable as anything else I can think of. When you're standing up in front of the class, show some humility, right? Like be clear when you don't understand something, when you've made a mistake, all of these things. That's a tricky thing

to do because you also need some respect, some level of authority. You don't want the students to completely distrust everything you say, but you want them to realize that you can make mistakes. And I like to think that they trust you more when you're honest about your mistakes and you let your curiosity shine through. You know, you make it clear that you're not studying or talking or teaching about this particular thing because you're supposed to or you have to. But you're truly passionate and excited about it. And that's hard to fake. If you actually are, they will get it. You know, they're watching you for hours on end and they pick up all these little things.

that you don't even think that they're noticing. That's what students do. But beyond that, yeah, I'm sorry, I don't have any specific suggestions. I do think it's an interesting thing to think about, but someone who's a professional at being a good educator would be a better person to ask than me. Paul Proudlock says, I've now attended both Brian Greens and Brian Cox's

Science Physics public presentations to great delight. While listening to Professor Green last night in Toronto, I could carolize his presentation some, by adding the ways you have taught special and general relativity, and of course inserted the many world's interpretation were appropriate. Have you considered putting on such a presentation and touring it? You know, roughly speaking, no. I'm very glad that they do it. You know, Brian, both Bryans, Brian Green and Brian Cox are friends of mine who are enormously successful popularizers of science and physics. And so I don't know if everyone out there knows, but I don't even know about Brian Green's stuff particularly, but Brian Cox in the UK really has perfected a show that is not just a lecture.

It's not just, you know, he gets up there and talks about, you know, like I do. Like I get up there with my PowerPoints that I made the previous night and talk to people. I do that all the time. But this is a whole different level of thing with high production values, everything really thought out, vivid graphics, computer generated stuff, music, you know, a whole thing that keeps people entertained and is really at the same time actually educational. Doing that, it's a lot of work, right? It's a tremendous amount of work. And I absolutely think it's valuable. I'm really, really glad that they do it. It's just something that I've chosen not to do and also probably

would fail. Because the thing about both of those is you have to kind of be famous before you do them. And I know that you all know me because you're listening to the AMA. You're like at hour three, in the AMA for the Mindscape podcast, but I do not have the public recognition that either one of those Bryans do. So if I did put enormous amount of work into something like that and booked a 300-seat auditorium

and had 15 people in it, that would be discouraging for me. So it is, again, I guess the theme of this AMA is satisfying our desires under conditions of finite resources, right? I, you know, something like that would be

fun, but given the resources I have and the other things I want to do, writing books, doing the podcast, doing research in physics and philosophy, teaching my courses, all of these things, I don't have time to do that. You know, when people say they don't have time to do something, they don't really mean they don't have time. They mean, I am not prioritizing at as high as I am the other things that I want to do with my time. So that's the right thing to say.

I do not prioritize trying to do something like that as much as I do other things with my time. Am I making the right choices with my priorities? Who knows? But I'm having fun for the moment, even though I have a little bit too many things that I've agreed to do. Okay. The very last question of today's AMA comes from Johann Falk, who says, I think it was when listening to episode 206 with Simon Conway Morris on evolution, that you concluded that we only have a sample size of one when it comes to determining how often life evolves into civilization level life. Then it occurred to me, couldn't we for all effective purposes, say that life in the ocean and life on land evolved separately, where it comes to chances of reaching civilization-level life? There are, of course, interactions between the two biospheres, but in many aspects, they are separate when it comes to evolving intelligent life.

So if I'm right, then we have at least a sample size of two. Do you agree? Well, I guess, so there's, I realized only after reading this question a couple times that it depends even by your sample size. Is your sample size the successful achievements of civilization level life or every appearance of life, right? I mean, we have a sample size of no civilization level life appeared on the moon. So is that part of the sample? I think that what I meant was, you know, the sample size of just successful appearances of civilizations. And in that case, I would not count the ocean.

I don't think there's any civilizations in the sea that are different than the ones on land. But also those two ecosystems are super duper intertwined with each other. I don't think it's actually fair in any ways to think of them as separate for these kinds of questions. For one thing, there is a last universal common ancestor. If you go back in biological time, both the living beings that we know of in the sea and on the land came from a common ancestor. But even much more recently than that, there is a given take, human beings and other. land animals often eat seafood, right? We have an enormous impact on the ecology of what goes on in the oceans, et cetera. Even back before we started dumping trash and fossil fuels into the biosphere,

that was still something, human beings still had a big impact. So, and by the way, you know, to make things a little bit more concrete, one successful development of civilization could easily crowd out all other possibilities. Like people often ask, is it evidence that life is difficult to evolve that we do have a universal common ancestor? That there are not 15 different examples of life independently starting here on Earth. I don't think that's much evidence for anything because there are ecological niches and whoever starts first is likely to win. I think that the actual life that started is more or less likely to spread to all the niches it can find, and life that started later, even if it's separate, would have a tough time competing with that.

And civilizations might be exactly the same way. So once you're on the same planet, I think that by my standards, you can only count one development of a civilization per planet as part of our sample size. So I still don't know how likely it is that life evolves into technologically advanced civilizations or not. These are fun things to think about. Maybe someday, even before too long, we will have a much larger sample size than that. And with that thought, thanks for listening to the AMA. Have a good month, and thanks very, very much for supporting Minescape.

I really appreciate it.