Hello and welcome to. Me sophie shevardnadze. With technology involving at a cost make speech and Artificial Intelligence no longer just a hollywood dream as a path ahead of us a dangerous one will our lives still be real while im here in Oxford University to ask all these questions to one of the most prominent thinkers in this field nick bostrom. Its really great to have you with us so youre a philosopher or author who writes about whats going to happen to us basically possibly so one of the ideas that you put forward is this idea of. You know. So correct me if i were wrong but if i get this correctly its its basically that humanity may come up with a technology that may do this to extension and therefore we would need computer surveillance while that might be an oversimplification but the vulnerable world hypothesis. Is the hypothesis that at some level of Technological Development it gets to be said to destroy 6 basically so that by default one civilization reaches the level of development. Will get that stated. There are a couple of different ways in which this could be true one maybe the easiest way to see is. If it just because very easy at some level of Development Even for a small group or individual to cause must destruction so imagine if Nuclear Weapons for example instead of requiring these rare difficult to obtain Raw Materials like plutonium or highly enriched uranium imagine if it had been an easy way to do it like baking sand in the microwave and you could have. The energy of the atom and if that had turned out to be the way things are then maybe at that point civilization would have come to an end then. With surveillance from what i understand you cant really predict the future nothing can when you can survey people and watch what theyre doing but then they will be inventing things under surveillance but you want to know that it is detrimental until something has gone wrong that the fact of surveillance wouldnt really prevent well so if if one thinks that the world at some level of technology is vulnerable in this sense one can then obviously wants to ask well what could we possibly do in that situation to prevent the world from actually getting destroyed and it does look like insurgents in our house. Ubiquitous surveillance would be the only thing that could possibly prevent that. Now would even that work well i mean the pads on the specifics of this narrow so youd have to think just how easy would it be to cause destruction would you just snap your finger or say like a magic world the world blows up well then maybe surveillance wouldnt suffice but suppose its something that takes several weeks and you have to you know do build something in your apartment and maybe require some skill you know at that point you could imagine a very fine grained. Surveillance infrastructure having that kept giving the capable it didnt intercept. But also how much destruction is. Created if somebody does this is it once it blows up or the whole of the earth maybe you could afford a few slipping through the net so youd have to don look at the specifics now of course surveillance in itself also is a source of risk to human civilization you could imagine various kinds of total terror and regimes becoming more effective more permanent. Peter surveillance in itself is a tell it hereon regime. What do you mean then i mean if youre surveilled 21st 7 of us that in essence is a giant Computer Police state well it depends on i think what this information would be used for. If it so that some. Say Central Authority micromanages what everybody is allowed to do with our lives then certainly that would be a total of terror and turn on president a degree. But suppose it was a kind of posture surveillance and people just went on with our lives and ollie if somebody actually tried to create this mass destruction thing would there be a response. In that scenario maybe it would not look so totalitarian really realistic though because as soon as someone is in charge of this total surveillance and then if its passive like youre saying. Very specific things like total destruction of a city or the world they would for sure take advantage of it its possible that im on the way i mean im going on just the way humans are mate yeah well i think to varying degrees there are institutional checks and balances in different colors right now we have a lot of very powerful tools and in some places of the world theyre used by despots and you know other parts of the world theyre used by the more democratically accountable and liberal governments and the thing in between certainly it would be the case study if you created this kind of extremely fine grained surveillance infrastructure thats a group create. A very substantial danger that either immediately or after some period of time it would be captured and by some nefarious group or individual and then used for oppressive purposes that certainly i think that that is one major reason for why. People are rightly in my view very suspicious of the surveillance technologies and whether. It could still be the case because its not something we get to choose that the world is so configured that at some level of technology the destruction is much easier than creation or defense and it could just be that in that situation the only thing that would prevent actual destruction would be a very fine grained surveillance im just you know for you me for doubting this a little just because ive seen with my own eyes what a police state is a little bit so it never really work so unless its sort of attacking them and the world is so diverse and were also different and ive seen it with my own eyes that human imperfections and disorganization you know they just somehow always grow through any restrictions or norms just like graphs repayment you know yeah well so what is it precisely that. Youre not convinced about that that could be some level of technology at which destruction becomes easy or that so impossible surveillance could prevent that the world from going to the idea so even if that was simple surveillance will still have to interact somehow with you know once thats what is not convincing to me right so i think there it becomes a matter of degree which set of sonora would you be able to provide the world from getting the story with surveillance up so take todays world were massive destruction is possible but its also very hard like Nuclear Weapons let us say like so that we can have. A reasonable ability even with present day Surveillance Technology to detect if a nation is building a secret program. So if you then roll it back you require less of the rare all materials less big installations fewer people working on this it gets harder and harder to detect. Right with Current Technology but this is a very rapidly advancing field with. A show Recognition Software that you could have cameras that could monitor in principle you could monitor every body and all you could imagine even if you want an extreme case but just a kind of the most straight theoretical possibility of modern if everybody wore a collar all the time with with cameras and microphones so that literally all the time when you were doing something some ai system could kind of classify what actions you were taking and and if somebody were detected to be doing this kind of forbidden action alarm could be sounded and some human alerted or some say well my problem with ira is that. It is created by in essence. Beings that are thought by human beings so how can it be Something Better or perfect earth than human beings enable able to not me so i think because im thinking if lot beings are creating Artificial Intelligence and Artificial Intelligence is simulating human beings then its only waiting flawed beings and its going to miss something well i mean a im not sure it would have to simulate human beings but be depending on which pretty particular scenario we were looking at it may or may not be necessary to not miss a single thing i mean if youre looking at the kind of much worse Global Warming scenario its fine a few people drive cars even in that world right as long as the majority kind of stop doing it you wouldnt even need new Surveillance Technology there you would just need a carbon tax or something if you moved to the other extreme where a single individual alone can destroy the whole world more than obviously there it would be essential but not a single one slipped through but then it depends on how hard would it be for a single individual with a need to do something very distinctive activity accumulate some special role materials then maybe it would become possible to have the kind of survival. Could avoid that today obviously our Law Enforcement capabilities are very limited but. I do think there are quite drop advances in using to recognize him a tree like recognize faces and to classify actions and then you could imagine thats being built up over a period of 10 or 20 years into something quite formidable so you wouldnt be voluntarily submitting the human race to where well. Thats what im about i mean is im not im not good im just noting that there are certain scenarios if the world unfortunate that turns out to be vulnerable and out way where it looks like it will lead to actually get destroyed or people will put in place to surveil and smash now. That might be depending on what kind of Surveillance Technology you have. Different ways of configuring that. Maybe it would be almost completely automated or in the near term certainly it would require a lot of human involvement one way to sort of check things that have been flagged by algorithmic means for example and then maybe respond take a short break right now while were back well continue talking. About whether were living in a simulated world by computers or not stay with us. Most people think just stand out in this business you need to be the 1st one on top of the story or the person with the loudest voice of the biggest race in truth to stand out of the News Business you just leave as the right questions and demand the right answer. Question. And were back with the neck bostrom nick so you know a lot about a much more Artificial Intelligence much more than me to think we can program Artificial Intelligence to be this benevolent platonic aimed at this i dont know in lightened monarch or anything that has to do. With control or total control is inevitably repressive and bad. Well i mean i dont think we would know how to do that today i mean of course we cant even build ais that can do all the things that humans cant today but if say next year somebody figured out a way to make ais do all the jobs that humans can do like some big breakthrough i dont think we would know yet how also to align it with human values that is still a technical problem that people are working on since the last few years but with some significant way still to go. So getting methods for scalable ai control so that no matter how smart the becomes even maybe it becomes far smarter than we want to because there is a possibility. That you have is to become smarter than most i think eventually. And then by that time you would want to also have the ability to make sure that they still act in the way you intended even one theyve become intellectually far superior ultimately so that thats a technical problem. That needs to be solved with technical means but then if you solve that you still dont have what we could call the political problem of the governance problem like so it would enable the humans to get the ass to do what they want we still dont need to figure out how to ensure that this new powerful technology d is used primarily for beneficial purposes as opposed to wage war oppress one another. And that that part is not the technical problem that its kind of a political matter like judging from the history of humanity if youre saying theres a slight possibility that i can become more intelligent than us in a way more intelligent. Its not being mean humans trying to control and make i do all these things that they want to do it cia controlling the humans and doing. Well were not humans what they would want to be mean but in the ideal case. Being aligned with human values in as much as we would you know specify what it is that we want to achieve i would help us achieve it. Do you thing you could ever simulate real feelings and memories. Do you think it can ever really predict a human brain something as chaotic as a human brain because we dont really know what it is how blowing i mean i dont think that would be necessary for alignments to have a very detailed i mean we humans cant do that with one another and we can still be friends with one another or help other people and so forth so that doesnt require the ability to create 100 percent accurate and relational prediction. So you have this other theory. Before the vulnerable world that we my all be living inside some sort of a matrix. And there are layers maybe a simulation. Is a right. Actually is something i published back in 2003. And its an argument that tries to show that one of 3 propositions is true so it doesnt tell us which one. Proposition won the 1st alternative. Is that all civilizations current stage of technology development. To go extinct before they reach a technological maturity so its going to be that maybe theyre out there far away other civilizations but they all failed to reach a technological maturity because human nature doesnt change i mean Technology Goes further but humans use it to destroy the world. Yeah that that could be the case and a very robust saw that even if you have thousands of human like civilizations out there they would all succumb before they reach technological maturity so thats one way things could be another the 2nd alternative is amongst all civilizations that do reach technological maturity they all his interest in creating these kinds of what i call ancestor simulations these would be detailed computer simulations. At the find an author level of granularity that the people in the simulations would be conscious and have experiences like ours maybe some civilizations do get there but theyre just a completely uninterested in using their resources to create these kinds of simulations. And the 3rd alternative the only one remaining i argue is that we are almost certainly living in a computer simulation right now built by someone who wants to build us a ship and anything thats the most probable one. They did the simulation argument doesnt say anything about which of these is true or most likely it just demonstrates this constraint that if you reject all 3 of them you have a kind of probabilistic incoherence and wind of the full argument involves some Probability Theory and stuff but i think the basic idea can be conveyed relatively intuitively its supposed to 1st turn it is false so that some nontrivial fraction get through to material to suppose the 2nd alternative is also falls so that some of those who have gone through to maturity do use some of their resources to create simulations ok right then you can show that. They because each one of those could run a lot of simulation study some of them go through there will be many many more simulated People Like Us there would be People Like Us living in our regional history you think a whole 6000000000 of us. But not just that but you could show that at technological maturity even by using just a tiny fraction of say one planets worth of compute resources even just for one minute you could draw on you know tens of thousands of simulations of all of Human History so that if the 1st 2 and we could talk more about the evidence gallantly how that simulation is possible even if we dont understand our brain well might they obviously we cant do that you say i mean i really honestly our evolution argument makes no assumption about the timescale behaved 20000 years or 20000000 years it still holds. And so because each simulating civilization would be able to run using a tiny fraction of its resources. Hundreds of thousands millions of runs through all of Human History almost all. Beings with our kinds of experiences were dumbass simulated ones rather than non simulated ones and conditional in that they are good we should think we are probably one of the simulated ones so in other words what that means is if you reject the 1st 2 alternatives it seems you are forced to accept the 3rd one which done shows you can reject all 3 in other words that at least one of them is true so thats the structure of the simulation argument ok so you answered my 1st question about how can we how can anything simulate human brain because youre saying there is no time span so again that. 2 questions if were living in a simulation why would the future eyes. Even make one just for fun i mean so. Many possible reasons you could imagine i mean you could imagine scientific exploration like wanting to know counterfactual history what would have happened if things had gone differently that could kind of be. Theoretically interesting and maybe useful for trying to understand other extraterrestrial civilizations you might encounter you could imagine. Entertainment reasons that we humans do our best with novels that bring you into this world that we put on theater plays and make movies Computer Games in many cases making the most realistic as we can of course we cant make them perfectly realistic now but if you had that ability maybe we would make them perfectly realistic. So that that would be another example maybe maybe even some kind of historical tourism you could imagine if you can actually time travel maybe you could build an exact simulation of the past and interact with that and it would be as if you had to travel to the past and you could experience what it can be like and other reasons as well that we we dont necessarily know very much about what would motivate or drive some kind of technologically mature post human civilization and why they would want to do. Different things with the resources and then i guess the core question eightys even if were living in a simulation rate does it really matter to us and me and you