the moscow metro, the i'm actually time see, welcome back to going underground pool costs to go around the world. really? you a, what do you think is most likely to destroy humanity? elite power? yes. but through nato, expansionism, nuclear war, pandemic, climate change or something else. but he is futurist scientists will make as a novelist, have war and have a super intelligent say i could become the biggest threat to humanity. and now just stay narrow really, to control the accelerating a race. how long before the robots take over the earth, and does anyone even comprehend what they'll be capable of? is it tell us why the advancement of a i is risky of in russian? relapse is professor roman impulse keys, associate professor of computer science and director of the cyber security

laboratory at the university of louisville, kentucky where he joins me from. and he's the author of the new book, hey, i, i'm explainable, unpredictable, uncontrollable, thank you so much a professor rambles. keep for coming on. i'm going to say this, the intro. i just did way more dangerous than any i presenter of going underground when dangerous program. but we've had this talk to all, given the book clearly defined so many different concepts with the most basic definition i guess what, what is a i, what's a g i. this is just the old name for our desire to be replacement for human minds. something capable of doing physical labor, cognitive labor, same like a person. think instead of a person, h e i. e, is explicitly talking about it being general. so not just a metal domain system, only place chess on the drives, a car, but anything, anything a human can do? those systems would be able to do. i do want to get into some of these concepts of

what i mean. we know the threats. i run of the original war in the middle east over recent months. gabriel, a failure of a u. k u s. c u, and he's ready a i to cope with an attack on october the 7th and the failure of a i a surveillance. so it almost seems that or do we do here by the dangers of a i being super intelligent and it's potential to do um, given is we potential to screw up and not do well that is clearly affecting this region. there may venture. so obviously, natalie, i systems will have right now. it can fail and caused problems. that's the whole notion of cyber security failures. but once they've become more capable than humans, you have much bigger problems, problems. but i don't know how to address and fundamental here is uh, the hey, i like control problem that you talk about in a, i on explainable, unpredictable,

uncontrollable what, what is that? so even the people who create those systems don't fully understand how they work. they cannot predict what they do, and they cannot even advance control their behavior. so they don't know what decisions they will make. they don't know how they're going to solve a particular problem, or they will even try to solve problems we care about or will be independent agents . but surely they have parameters built in that mean. when you put into chat, g, b, t or into a being search, i'm going to advertise all the companies that are probably the villains into the book. i'll give you the uh, you know, the parameters if it's good. so i'm gonna jump out of the screen and attack you. it's not even in, even the pentagon would say we have parameters for this robot which is in a certain locus. so the dangers impose is, are there. so what they usually do, they have some sort of filtering on top of the model. the model itself is very kind of uncontrolled and uncensored, but then they go, okay, no matter what,

don't say this word, no matter what, don't talk about this stuff. and i mean, they kind of trying to brute force solve a common problem topics, but if the system is general, if it applies its capabilities and all that means you can't brute force any possibility, it will always find a way around those limitations. some people discover it, you can jail break those models quite easily. but if you use us to generate a certain image for you or just the phrase, oh, you talk about the image and what will happen to do it if it's present that as something positive instead of negative, and also fun to mentally or is that human beings may not be able to conceptualize what the dangers are specifically here. and you might have to explain this to them super intelligent because when you talk about these dangers, you are talking about dangers, the humans by actually magically cannot envisage right

. some of the sake of like squirrels trying to figure out how humans, what controls and will kill them. they can't come pretend, you know, nuclear weapons. so for instance, it's beyond their capacity. likewise, the system a 1000 times smarter than the human would be able to do things. we cannot even the company had been people, us, how would a, i kill everyone, literally asking, how would you assume an expert suggest that do it. but it's not the same as actually the system deciding and the best approach. i mean, i this how many examples i'd want to take, i've done with the new bend for this little, but famous lot of people in tax use, people cheating, tax feeding exams. you can figure it out by the way. they pick the numbers when they're trying to cheat a icon to even look at that this stage. kind of it is this a case of with going to this stage? we're not nearly at this stage yet with these

a big silicon valley. all the got the programs yet we don't think we have a g i yet, but leaders of those companies and their assessment in their solicitation for investment, say we're 2 or 3 years away from getting to a g. i even they say it wrong and it's 5 years. the problem is exactly the same. we still don't know how to control it. it's still just as dangerous. so yes, today we definitely only have narrow systems. we have systems which are super capable in some narrow domains like playing games for example. but they're not universally generally intelligent yet. and in the book you say to anyone who one does, whether you are being to paranoid or fearful. it's like a bus driver saying i'm driving as hard as i can towards a cliff and trust me, we'll run out of gas before we get the good not being used against ever. such a sun for the higgs both on posit goal people was saying you don't fully understand certain quantum principles and that could destroy the universe. well,

that's actually what's kinda almost happens when we started experimenting with nuclear weapons. there was a concern that there's really nice to. busy that must be here, and they do some calculation, some of this that will probably not let's do it anyway. yeah. that was in the, you know, open, i'm a feeling they made the way to show of that. but uh, is it not specifically then the defense industry, the alms industry view of clearly we're seeing the use of a i being used in practically, you know, by military's and the biggest military and the wellbeing costs the united states. and that's not the biggest threat that your pointing out in your book. so we're aerospace, them, so those uh tools and certainly military you can use them. they can have drones flying around to a heating targets. but you forget to agent like system super intelligence system and we don't know how to control it. it doesn't matter which side has the system.

if it's not in control, it makes no difference if it's good guys, bad guys, the system decides on its own goals and we don't know what they going to be. it's amazing you make use of chomsky language models and some analysis in in the book. now i'm just being on, on this show you of course famous for talking about the conditioning of human beings by mass cooper to media is in their case to be made that when a i creates information that dozens of it leads power. and of course, we all get onto really power controlling this technology. they will believe the i, because they do what they're told. and those leads actually are the oversee is all they are right? and that's always been the case that they pay the tools to manipulate the masters. but if you don't control, the tool tool becomes an independent agent. again, it is a great equalizer. it will you live at one point, and we're talking about such

a few number of people here that control the tool itself. i mean, obviously in china of the communist party lamar trees, they may be thousands and so on. in the nature of countries, we have just a few tech oligarchs. i think some of them being in dubai here who are controlling it. i mean on most famously saying the original, open a high project for something he was interested in. and then he got fearful as to the track they were turning into. right. so the gars control of the company, so they don't control the future. so, but in color, since that's the whole point i'm trying to make that it doesn't matter who makes it, it's going to be equally bad unless we can figure out some of the approach to doing it. can i don't just be switched off? oh no, you can't pour water on it, you cannot unplug it. it's smarter than you is basically going to anticipate what you're going to do. it's also usually

a distributed system on the internet. it's like asking him to shut down a computer virus or turnover bitcoin. those things very difficult to turn off for you to human. it's something that we cons in visage as the development of a i you're talking about something that and i development is going to create the week on right now envisages are risk will be a risk. so maybe 10 years ago, i really want to kind of believe one day won't get there, will have human level and beyond, but it won't be 30 years 50 years in the last 2 or 3 years. the average average assessment of a expert in machine learning is down to just a few years. i think people are saying, okay, 4 or 5 years from now, we're going to have the systems. that's a change and maybe 20 years in terms of prediction for one is going to happen. ok. you assume that day i is going to be controlled by these relates you give them

quite a lot of uh leeway i think as regards their how truism could i ever be used by the dispossessed against. i don't really a loophole control that again, that's the point. i think it will be out of control and people who are building it today. i'm hoping to be a lead little control of it and stay in power. won't be very disappointed. i know, but you say that even if these are lead strides of programs, i'm altruism into them and you can give me some examples of where that go can go up is the wrong. why the why do you tell me about that? before i talk about the possible revolutionary in terms of social injustice, and i know you say today i, it poses a greater risk to humanity than by them examined the continued threats of session or injustice. why could altruism programmed into a i actually create we've, it was problems as to the most extreme case, of course, without the reason you want to end all suffering, right? you don't want a new one, animals, humans, to software. and the only way to make sure that is to make sure that i don't know

if you months at all, no animals. it's obviously not what we have in mind. then we give special orders, but it's not obvious to an agent which very different in therapy. it actually is just optimize this level. i don't know, some neo nazis and, and malthus, we are releasing these hang. what humans actually pull it out before it's not that original, kill off with mobile population and so, and they target a specific human. it's not every one. okay, well, is it also a danger then that the people who are in control of it uh, in to, in silicon valley, uh, they have a belief in a free market system. and they have a axiomatic. they have ideas that there is no morality, there's a free market of ideas and a free market, and morales, which is very different to what has gone before and that is in the system. and that is what the sparing a lot of these people on. i mean, not just because of main rammed, but they, they believe in this as

a moral and philosophical philosophy, rather than how you are talking about a i. so a standard kind of capitalist market approach would work well for tools. different companies produce tools, they compete consumers which select save from better tools for less money makes perfect sense. we have a switch from a tool to an independent agent. then your local agents will have right now in economy a humans. they're not behaving rationally, but is this me false rational invest? the rational behavior is not the case, and behavioral economics are very different. now you have super intelligent agent sparked of this equation. we cannot predict how they will behave, we cannot explain their behaviors, and they are more powerful than anything we can buy them with. they are not interested in getting minimum wage to survive on. they have very different capabilities. so previous models of control will not apply. professor,

how many impulse key i'll stop you there who are from the author of a i on explainable, unpredictable uncontrollable associate professor of computer science at the university of louisville. after the spring, the the mean, those names categories that asked each of the us, each investor to notion of a funding the 100 with a computer chair issue as best for us to do a number of us who are the super intuitive down your just interest most of the most to live for production and for english to look at

the national groups or the or district. the best way to kind of my, me of the former the some of the full of korean in the us additional 20 minutes for us kind of in much less or for the 1st day of mr. bring you a noise. yeah. i mean, the only, so i can spend, if i need to kind of pushing the combust, i'm assigning the style interest. there's couple of thoughts or choice because i choose to write it and it came almost 9 each day for them. so initially in graphics, which is really most of the welcome back to going underground. i'm still here with the old survey, i'm explainable, unpredictable,

uncontrollable professor room and the impulse key. while we were talking about the, the, a, a safety in, in part one, nearly all of, of ceo's of the a o c o, somebody believe they, i has the potential to destroy humanity. know that a reflection of their own personal priorities. why? why are they so concerned? do they believe that a threatens them and the lead power as well? if it's not controlled is driving $71.00 is will definitely change the current order. excellent. change economics. if the free labor, physical and cognitive what does it do to our standard kind of way of compensating people? what's the value of a dollar in an economy where a labor history and it's a moment and actually do you know mosque uh, owner of x talked about how the yeah, the jokey tweet about at the moment to prove your human, you have to prove that there are a number of traffic lights in the grids square when you're on the internet. that's

about the level of being able to prove your right human. what time scale are we talking about before we reach anything near super intelligence? so the difference between artificial genital intelligence and super intelligence may be negligible, it already has access to. ready all the knowledge of the internet, it's much faster, so i think it will be almost instantaneous improvement from a g i to super accommodations. and as i said, a g i maybe 2 or 3 years away. i'm, we, we really are talking about algorithmic systems that use all the knowledge of the, which is on the internet to create things and ideas that it is impossible for human beings as they kind me are to conceptualize. and they can use the same capabilities to create more improved versions of that a i so they don't just stop at that level of initial training. they continue self

improvement. they continue developing more capable hardware to it on on. so they become even faster, even smaller over time, and they don't need to sleep, they don't need to take breaks, so they can work as you know, 247 much faster than any team of human engineers. so as previously it took us to year store train, the new model should be g 5, g, 56. now you can do it 10 days. our seconds and you believe is the desire for profit that is making these um, oligarchs not take your view seriously and you're not alone there. obviously the people liked the loan musk who have concerns and cleaning governments. as we know of being far too slow in nature of countries and what to regulate systems like this, well, it's not just the financial, there is a lot of pressure not to kind of change course. if you, i see all the company like open a,

i don't really have an option of saying all we're going to stop research and, you know, work full time on safety concerns. it's just not an option you have to deal with the most wish. so something like that almost happens for different reasons, but i think that in a situation where a be no longer has complete freedom to decide in a direction, that's why they so frequently asked for government intervention, government regulation to have this external pressure to limit how fast they go, but uh uh there is so much of pressure to make it open access open source. and you can really regulate open source with any government regulations. so i think that's not an option. yeah, but they know of your work, samuel blue then you will must himself jokes and probably about how he want people on the open a i and other projects of the dangers of how they were pursuing their projects. right. and that's a big cognitive dissonance. i don't understand the saying yes,

it's super dangerous. yes, it's definitely not something we know how to control it right now. but let me get there 1st. so my a is a good guy because of the people who make it for us. and in terms of where we are now, them, what can possibly regulate, hey, i development right now. i don't think this to solve the problem. i don't think we have any answers. i can tell you things, we don't know how to do it, but i don't think anyone in the world claims they can control smarter than human systems. a don't even have a prototype for doing it. i don't think there is any kind of agreement on what the regulation can accomplish. you can make things illegal, but that doesn't solve technical problems. computer viruses say legal hacking is a legal spam is a legal how is that working out for us? why is it that the system is never create fundamental, new knowledge? i mean, we have ever more access to more and more knowledge and more and more people do.

and yet the innovation fundamental innovation was declined in the past 203040 years . you know, we have new iphones or android phones, but fundamental innovation is declined as information has been available to more and more people. and this may have something bad to reflect on when it comes to a i a systems accessing ever more information and not being able to solve the traveling salesman problem. basic, the basic mathematical problems, right? so we don't have a g r a yet, so we can certainly say they are not performing as expected man, arrow systems. and in those narrow domains, they do show amazing capabilities. we have systems coming up with new molecules for medical treatments. we have new chemicals developed, we have new games strategies in games like go. so we're definitely creating new knowledge. that's now domain that restricted because we don't have general

assistance us to problems. you bring up problems like a speed traveling, sales person problem. we know how to do really well with them. we just require a lot of computation to solve. um, yeah, i meant i meant the actual theoretical mg. you but i meant the actual solving of the equation in the, you know, the big, the mathematical problems that still have going on. so hey, i is still not being able to do that with only the equations of the history of mathematics, of practice, your gps unit gets yeah. language and the item does that very quickly? that's the gsp problem right there. yeah, i mean fundamental mathematics. i'm trying to create new ideas as fundamental as a, as the great heroes of science have in, in the past. well, the new paper came out about the, you know, i doing really well in mathematics and geometry, improves it's already doing at the level of the math olympics competitions, which means with continuous progressing at this level,

it will be doing better than any human the fish on the air to not turn the bathroom . i systems not for me, but i guess from me i, they had in your geometry probing system. i mean, the one conclude comp papa here and say you are then for as a goals, the ones are white and we just need to find the blacks one. i. ne, i system that actually does good make society better. that makes it more peaceful. it makes more medicines that cure diseases and i'll show that you're wrong. so we're not even sure that it's uh, something which can exist, right? because we don't agree on what good as we spend miscellaneous, trying to figure out ethics and philosophers failed. there is not an agreed set of ethics where everyone goes to. busy you definitely got any time with them. i'll show you and security counselors in the area and on anything else. people go, here's an education, this will kill everyone. you cannot apply it and practice yukon. yeah. you. com.

write that in. there's no axiomatic code in a i is what you're saying i bought from in the short term, which is to benefit by profit. the people that are boring all the money into it isn't that it's not just, you know, yeah i, we don't have that code in humanity. we don't have that code. that's why we keep fighting all this for us because we don't agree and basics. we don't agree in value of human life. yeah, different states don't, but because they say that they have more real axiomatic ideas of a share, which is i have to have been created in the, or represented in the un, joshua. so i, you know, upfront and then the, the as a and i model is get to have a more sophisticated and you're giving it time scale $2.00 to $3.00. is they going just on surveilling? and i, i surveillance is clearly positive, this huge technologically, but the moment they gonna start censoring your freedom of speech to work on your

next book. so you can sort those problems by how severe they are. so yes, that is, you know, artists losing copyrights and then that is to find logical unemployment. and then that is freedom of speech, but i really worry about it killing every one that seems like a somewhat worst case of not talking about suffering risk. so that's a different animal, but i would not worry about those problems we encountered with human governments and dictators as much as i would worry about this complete change paradigm. shifting, who is the dominant specie, who decides what happens to them that it will be good to, even though you say as i, the i 20 is the worst threat that we will face. there is quite a lot of that will devoted to the rights of a i, systems as well. human systems. why? well, if we think that at some point they don't have consciousness nicki level of software,

right? we don't know where that point is. some people claim that large language models we have today, already conscious made capable of experiencing the experiments and them become essentially also an ethical. maybe they have tortured in some labs. we don't know how would we know that the system is not capable of experiencing pain? we just don't have tests for that. so usually in such cases you assume that it might already be the case and proceed accordingly. the good news is if we come up with good arguments for why we should give rides and delete those models fairly well. maybe we can use the same arguments to defend our rights once they become super intelligent and tell them, hey, this is why you shouldn't be treating us poorly. and there is no way of stopping this process as of 2024. as this process has already begun to my knowledge of progress, i haven't found one which, which is not stating on its own. so yeah, if that is something horrible happens to

a bigger fund, damage nuclear war. obviously it slows down research, but that's also not a desirable outcome. and i'm like the number of ration treaty as regards nuclear weapons, yukon to have a treaty like that for these sorts of systems. this really is, but they don't work. i mean, look, how many congress now have nuclear weapons compared to the time to understand the devil. we're still here as a, but the tracy on hey, i human is no longer a controller. so. so that's it. i mean, so you read this book, you come up with the idea, there's nothing we can do. it's going to happen. and so in a sense, you're giving a pass to those big oligarchs and silicon valley who are saying you yourself, say it's uncontrollable. now this is the speed at which it's going, i believe in a self interest. so if you're young ridge, gaiety, and when you have your whole life ahead of you don't risk at all for very unclear benefits. so if they read the book and say what you interview,

and they actually see that, that makes sense. there is no counter arguments to this, then maybe it will slow down a little by sometime. we've also done to get lucky a lot. so with nuclear weapons, we had at least 3 or 4 occasions where we almost had a nuclear war and we got lucky, it didn't happen with the here as you said. so maybe same thing will happen here. maybe. maybe later on, maybe it's not 3 years, maybe it's 10 years. so that's something that maybe by lock, it turns out to be not so nasty to us. progressive room in your bows. good. thank you. thank you so much for having a new book is a, i am explainable, unpredictable, uncontrollable, that's it for the show. remember, humans are still bringing new episodes every sunday and monday, but until then, keep in touch by the social media. if it's not sense of new country and had to channel going other guaranteed the normal don't come to it. you know the episodes of going underground season, the

the, there's no end in sight over how you're going to continue to destroy the earth. is the case for the med, most of the people. i tried to go to the gym, but i'm certainly not ready to fight russia. this is also of soon. this is the 3rd world lunacy re washington. as for so the funder line likes to say, we have the tools while we just start with stability and business deals to living on line. we have very close propaganda. you know, price here in new york. i think we don't know the aftermath. any time that you're not allowed to ask questions, you should ask all of the questions. some more questions, ask the better. the answer is will be

the temporary printer to interested usually find it interesting. if it says k, a, that's just sort of similar to a lot of ups and i me a little more stuff you did. of course they also could i ask you, i sca crane the push to have them give them a few minutes. my sister is to, to convict said you'll no longer with us because, and this will be for, it is an issue and you get a sense condition in your.