Stability and Identity in AI

In the course of your life online and off, you leave a lot of data about yourself scattered around the internet. Some of it you probably don't want to be out there, like your address, phone number, or social seecurity number Incogni is a service that tracks down and removes your personal data from multiple sites across the web not just malicious leaks on the dark web. But online directories, search sites, and commercial databases, all of those can be used by malicious actors Incogni has both an automated component where they search for your data and get it removed, but also a custom removal feature. If you find your info somewhere you don't want it to be, you can let Incogni know and a dedicated privacy expert will handle it for you I've been using the service for several months now and you wouldn't believe how many times my name appears in easily available records online or how much peace of mind it confers once they're removed So take your personal data back with incogni. Go to incogni dot com slash mindscape to get sixty percent off an annual plan using code MindsScape That's sixty percent off at Nc ogNi d. com slash mindscape. Incogni, they can't harm you if they can't find you. Have you ever considered surrounding your house with a moat to keep it safe Would you hire a professional wrestler as a bodyguard for your car Okay, maybe you wouldn't go that far But if you'd go to great lengths to avoid dealing with your insurance company You might have insoranoia And if you have insanoia, you should have NJM insurance They go to great lengths to do what's best for their policyholders Start relieving your insure anoia today injM. com Hello everyone, welcome to the Mindscape podcast. I'm your host Seaan Carro Hey, has everyone heard about the idea of free will idea that you know individual people have the ability to make choices and decisions based on reasons that can have a causal influence on how the world behaves Yes, you have. I know you have. Don't worry I'm just kidding, you've heard about free will. It's a hot topic For reasons that I will admit, I do not completely understand why freew is such a hot topic. But on the internet in particular, people like making claims. and I really think that they're not always listening to each other There are claims about determinism, indeterminism, compatibleism, incompatibism, responsibility, blame, whole bunches of things that are bounced around. It surprises me and I guess I should be happy that so many people care about what is in some sense a relatively obstruse philosophical point. I've certainly not noticed any difference between people who say they believe in free will and people who say they don't believe in free will in how they act, in how they behave, in how they treat what it means to make a choice or to place responsibility or blame on anyone else for making a choice. So I guess I should be happy that there's some sort of bilophical discussion going on here As many of you know, I have two things that I like to say about free will One is about the determinism versus indeterminism thing. Which is Id like to say, it doesn't matter whether the laws of physics are deterministic or indeterministic. That's an interesting question to ask, but has nothing to do with free will. Even if the laws of physics were indeterministic, I would still think that you could either believe in free will or not. in particular, quantum mechanics has nothing to do with free will Quantum mechanics does say that to observers in the world, the world is indeterministic. And there's this weird words logic, according to which people start from a conviction that there is no free will and convince themselves that must mean that there is determinism in the world and therefore quantum mechanics can't possibly say that there's not which is very backwards and very wrong to me. So that's one thing I think. The other thing I think is that compatibilism is roughly right. That's my personal take. Compatibilism is just the idea that even if There's determinism at the lower level. You can still talk very fruitfully and should talk very fruitfully about free will at higher levels. level of people and their actions. So I've said that many times in many different places It's time to get it right. In other words, time to talk to somebody who is really truly an expert in these questions and who has thought through them very, very carefully and see how the experts think. And unsurprisingly, there's many points of agreement and many points at which I learn new things by talking to these experts. So Christian List is a philosopher. He is at the Institute for Mathematical Philosophy, not mathematical physics, Mathematical phhilosophy in Munich. And he's done a lot of work in many different areas, a lot on social choice theory. He's written papers about quantum mechanics I think that he's probably most well known for his Defense of compatibilist free will That is to say he is explaining why Given how the world is structured and given the metaphysical commitments we have and our understanding of emergence and how the world appears to us in layers and different levels and so forth The right stance to take is treating as agents who have free will and therefore moral responsibility And notot only does he say that, but he defends it and he investigates what it means to say that, what it means to be an agent, what are the necessary criteria, how it fits together, how you can extend these ideas from individual human beings to groups to nations Potentially even to large language models or other kinds of AIs at what point Do you say that the AI has free will? As Christian will emphasize here, That's a different question than whether the AI is conscious In fact, it's a much easier question and maybe a more important question, so we really should start thinking about these questions more than we do. It'd be nice to have a rigorous philosophical framework with which to do that He's the guy who has it. So let's figure out what that framework is. Let's go. Christian Lis, welcome to the Mindescape podcast Hi Sean. Nice to be on your podcast Yeah, it's very good to have you on. You've been a philosopher working on a lot of things, including quantum mechanics, weirdly We're not going to talk about quantum mechanics for the most part today. Maybe at the end, we'll bring it up. But we have other fish to fry, as we say in this part of the world. For the listeners who are not philosophy experts. you know there's lots of different kinds of philosophy you can do. There's moral philosophy and political philosophy, whatever What kind of philosopher are you? What is the world, the specialty in which you live? Okay, so u'm Well officially u My area is described as philosophy and decision theory, so this is at least my job description here in Munich I work at the so called Mich Center for Mathematical Philosophy, which is a fairly interdisciplinary place. peoplee working here O philosophers who interact with several neighboring disciplines, so we have people in areas overlapping with maths, with physics, with economics, with cognitive science, with AI, with neuroscience, and with a whole bunch of different things. So it's an inherently very interdisciplinary place. And yeah, so I think my interest have been all over the place around individual and collective decision making and a whole bunch of metaphysical questions that are raised by this. I love the idea of a center of mathematical philosophy. Is that a thing? Do other places have centers for mathematical philosophy I think the MCMP, Munich Center for Mathematical Philosophy is probably the only place with that kind of name and label. but of course there are other places with related interests. So there is a very good place in Amsterdam called the ILLC Institute for Logic Language and Computation, they do a bunch of things that overlap with what we do. My former department of phhilosophological and scientific method at the London School of Economics also specializes in similar things So yeah, we are quite a big place in this area, but by no means the only one. I guess it does make sense. I love the idea that you know, I'm well aware with philosophers of physics, of course. But philosophers of economics, philosophers of biology, philosophers of computer science also have this mathematical bent, logicians, I suppose. And so it must be fun to have them talking to each other Absolutely. So the interdisciplinary nature of the place was one of the B attractions for me when I chose to come here. And yeah I absolutely love it. And I want to sort of give away the punchline of a lot of our discussion right away. And then we can back up and lay the groundwork. But we're going to be talking about free will And there's a free willill is weirdly popular topic on the internet. I don't know if you know this, but people love debating free will. and maybe you could just lay out options for us. I know that there's this idea that you're a determinist or not. but ye that that's not really how philosophers think about it Yeah, okay. so um So the big distinction in the philosophical landscape is that between compatibilism and incompatibilism. I mean, as I'm sure a lot of your viewers know, there's a long standing debate about whether we could have free will if the world is deterministic. So determinism would obviously be the idea that if we fix the state of the universe at a given point in time, then There's only one possible trajectory of future states under the laws of nature. seems to prevent the idea that there are folks in the road deceision notes where I can do one thing or I can do something else. And the idea of free will is so much bound up with having choices between alternative possibilities and so that leads Many people, the so called incompatibilists, to say, well, if the universe is deterministic, then that can't be free will And then on the other side of the divide are the compatibilists They say that well, even if the universe is deterministic We could still have free will, and then they try to give us an account of free will, which is often going to be a little bit more subtle or nuanced, that then tries to make sense of free will in this scenario I don't know. I mean, I could also go into the sort of two conventional options. I mean so two conventional options on the map roughly the following two One would be to say it's just a mistake to define free will in terms of the possibility of doing otherwise. So here the idea is matters for free will is not alternative possibilities, but what matters is simply Um An agent can endorse their actions. So if I do something which is in line with my goals, my motives I believe in it. I want to do it It expresses my character. I mean you can spell this out in a variety of different ways then those compatibible say that's sort of good enough for counting the whole thing as free. Right. And then the other type of compatibilist in It takes a different strategy. so they'd say Well, not some form of choice between alternative options is actually important for free will. so we must give an account of Um, you know, how u do otherwise But then they tryed to render this compatible with determinism by redefining what it means to say I could have done otherwise. So So for instance, I mean a trivial example, So this morning I had coffee rather than tea I want to be able to say, oh, I could have done otherwise. I could have had tea instead So what those compatibilists then would say is that It wasn't required that at the time of the choice, it was genuinely possible for me to have tea because maybe if the universe was deterministic, only one thing was possible. mayaybe only the coffee trajectory was a real possibility. How What those compatibists would say is and What math is is that If the world had been a little bit different. So if I had had a slightly different back history, maybe I had had a desire for tea inst stead, but then things would have been ever so slightly different. And if things had been a little bit different then the trajectory would have unfolded in a different way in the T direction. And then that's good enough for free will. So those that second kind of compatibible basically redefines can't do otherwise in terms of a counterfactual conditional. And those are sort of the conventional options out there. Can you tell us which one you are So I actually like to reframe the debate. So I mean what I've just given you is the sort of standard framing. of course, that's also what I present to my students when I give an introductory lecture on free will. but But I mean maybe in night we will go into much more detail, but sort of in a nutshell, and My point is that This standard debate frames things in the wrong way because it fails to distinguish between differentifferent levels of description at which we can think about the world namely a physical level On the one hand and a level of agency, on the other hand, and then my claim and I'm sure we'll get to discuss this properly, my claim is that once we carefully draw the distinction between levels, this opens up new space for defending free will in a more interesting way. Good. That makes perfect sense. Thank you for the preview and we will get there. Do you have a standard respondse to the claim from some people that you're not defending free will, you're just redefining what it is Well, my so my response is that actually the strategy that I'm then, you know, about to explain more properly it gives us a wonderful rebuttal of this objection. So what I would say is that Some of those standard compatibilist routes that I very quickly summarized earlier on really can be accused of redefining free will or watering down free will. I mean, if for instance, if we say Free will does not require possibility of doing otherwise at all. Free will does not require alternative possibilities at all then we have definitely waltered down free will compared to our common sense understanding of free will. I mean if you ask outside academic philosophy, I think most people will think that some notion of choice is really essential for free will. Yeah. So take this away, we have redefined or watered down free will. But even if we redefine can do otherwise, just in this counteractual way arguably we still ever so slightly redefined free will or wat it down because you know, I want to say, you know, this morning I really could have chen instead. It's not just if the world had been a little bit different, I would have chosen to sure. I mean, if the world had been different, a lot of things could have been different. but what I want to say is moment of choice, you know, it was open to me. I mean, I could have gone the coffee way and I could have gone the tea way and I opted for one, but the whole thing was my under my control And so so so yes, I mean, I totally get the point But some versions of compatibilism look like they are redefining or watering down free will. and my whole point is You know, if we reframe the debate in the right way, we can avoid that. We shop for everything at home now. Why can't we shop for blinds at home too That's why I love Th Day Blinds. Instead of wandering around a store, Th Day Blinds sends a professional design consultant straight to you They bring all the samples, help you see what actually works in your space, take expert measurements, and even handle the installation We've all bought something that looked great in a store and looked terrible once we got home. With three day blinds, you see everything in your actual light with your actual furniture. beforefore you commit Plus, whether you're home or away, you can control your window treatments with the three Day Blinds app So for a free, no charge, no obligation consultation three dayblinds d. com slash pod fifty for our buy one get one fifty percent off deal That's the number three dAY blinds d. com slash pod fifty Having the right people in your corner for life's biggest milestones makes all the difference. Like a friend who's there when you're house hunting or checking out a new ride, State Farm is there too, helping you choose the coverage you need. With a state Farm agent, you know someone is there to help you along the way. and with so many coverage options, it's nice knowing you have help choosing a plan that fits your needs so you can continue celebrating all of life's milestones. Head to statefarm. com to get a quote. Like a good neighbor, State Farm is there Okay, that's very actually super duper helpful. I mean, I'll confess, and I think a lot of my longtime listeners know, I'm already totally on board with your way of thinking about it. but it's not my professional expertise either. So hearing the true experts explain the ground rules is very helpful. The other thing I wanted to very quickly get on the table is Most of what you just said. doesn't involve words like determinism or indeterminism. I mean, you didn't use those words that much. And so it seems like compatibism versus incompatibism which is, like you say, the way that philosophers generally think about it, is just kind of orthogonal to determinism versus indeterminism. And a lot of the online debate, I got in trouble for putting a social media post that says If you start talking about free will and immediately talk about whether the laws of physics are deterministic or not, you clearly don't understand the debate. So could you explain is that was I a little bit too much or is that basically compatible, I guess, with what you're thinking Well, I think it definitely goes in the right direction, but I mean, maybe to anticipate one of the key points I think u to just ask them Is the universe deterministic or not we just frame it like this, and that's actually the way it gets framed in a lot of metaphysics textbooks. That's the way the question is framed in the influential work of Peter Vaninwagen, who developed one of the most famous arguments for incompatibilism. If you just ask, is the universe deterministic or not And my view is that That's a somewhat undpecified or Iill defined questions I think The distinction between determinism and indeterminism can be drawn but it becomes Fully meaningful, fully well defined only once we carefully specify the level of description at which we're trying to draw that distinction So once we have a a system carefully described crystal clear about the level of description then we can actually ask relative to that level of description, are we dealing with a deterministic system or not? R And sure I know those people who think u you know, some Fundamental theory of physics gives us deterministic laws of nature. So I suppose that was the mainstream view at least until Einstein U they would be able to say, yes, there is a level of description at which the physical universe behaves deterministically. And so then that would mean if you um trajectory of the physical universe at that level of description up to a particular point in time then this trajectory admits only one normologically possible continuations. so only one possible continuation among the other trajectories that are admitted by the laws of nature. So far so good But now it is also entirely possible that if we redescribe the very same system at a different level at a more microscopic level, for instance The determinism ind determinism distinction can come out in a different way and that if we now look at a sequence not so much of these super finely described micro states, but we look at a sequence of macrostates each of which is more coursese grained to a particular point in time, and we then ask Well, what are the possible micro level continuations of this sequence of micro level states under the laws governing the system. Well then it could actually be Tw or more distinct sequences of micro states are fully compatible with the laws governing the system And whenever you've got this kind of pattern you'd have some form of indeterminism relative to the macro level of description while having determinism relative to the micro level of description. And the general point is Of course Systems that we study in the sciences admit many different levels of description. I mean, we know there is the level of particle physics, there is a level of chemistry, which is already more coursear grained U There are various biological levels, so the level of let's say individual cells, but then there is also the level of larger biological systems, organisms. We can keep going like this. many different levels of description that differ in the of differ in the level of grain or detail with which we describe the world And so there's nothing weird about recognizing that At some levels you might have deterministic dynamics, deterministic behavior of the system. And at other levels, you have indeterministic behavior of the system. I mean, in a thought experiment You could even have with my friend and cor, Marcus Pivato, we just just for conceptual intuition pumping, we consider the Th experiment, you could even conjure up a hypothetical system which amidst infinitely many different levels of description, maybe ever more fine grained And you could have determinism at odd numbered levels. And you could have indeterminism at even numbered levels And the whole thing would be a coherent scenario. I mean, of course, we arere not saying that the world is like this, but it's a perfectly coherent scenario. And what it does show is that In the case of such a system, you can't really say this system is deterministic simicitor, or this system is indeterministic, simplicit. this kind of thought experiment highlights is that the distinction between determinism and indeterminism is really very much a level relative or level specific Distinction And so back to your point yes, I wholeheartedly agree that someomeone says, oh, you know, fundamental physics is deterministic, you know, which is I suppose an open question, but let let's call it short.ast a principle life possibility If someone says, okay, fundamental physics is deterministic then The reason why This doesn't automatically refute free will even on the sort of alternative possibilities characterization of free will is simply that kindind of indeterminism if any, that is required for free will is not the form of indeterminism at that microphysical level of description, but it would be indeterminism at what I call the level of agency, the agential level, which is a completely different level of description. Given this whole logic of You know, level specificity of the distinction and in determinism at the level of agency is actually fully compatible with determinism at the level of fundamental physics. And yeah. so that's the sort of the the direction in which I would you know spin or take the comment that you made. So no, I love that. It makes perfect sense to me. paraphrasing it correctly to say or exemplifying it to say even if The fundamental laws of physics were one hundred percent deterministic, and it was little billiard ball atoms bumping into each other and interacting When I flip a coin, I don't know whether it's going to come up heads or tails. And so at the level of people flipping coins, the world is indeterministic and we should treat it that way Yeah, so yeah, I mean basically I agree just maybe with just a slight twist on nuance I mean, you say, I don't know how the coin is going to land. I mean, it's true. We don't know how the coin is going to land That framing makes it sound as if it is just an epistemic phenomenon. So just something to do with predictability or our informational limitations when it comes to figuring out the details of the microstate. and And that would then invite the objection that you know when when let's say when I talk about free will involving indndeterminism at the level of agency, then this could look like, oh, what we really have is just unpredictability at the level of agency. but that's not the same as kind of genuine openness of choices. And so once more the objection would be this is not good enough for free will. I mean, here's my, u my response to that. my response is I mean, it's not the case that Only treat properties, patterns, phenomena at the absolutely most fine grained microscopic level as real I mean, that would be absurd. if we said, you know, anything that you can't Identify or pinpoint at the level of particle physics or at the level of you, whatever it is, superstings or something And any such thing, you can't pinpoint that that most fundamental level is somehow unreal. I mean, then a whole bunch of things become unreal. Solidity of surfaces becomes unreal organisms become become unreal, societies become unreal, universities become unreal. unemployment. becomes unreal, war becomes unreal. And I mean, you know tell people that these are not real phenomena. I mean, these are just absolutely real phenomena. to start with a philosophical view that takes the human perspective Seriously And that also takes the sort of common sense ontology of the world seriously. So we need to have a philosophical picture that can recognize the reality of, for instance orrdinary microscopic objects and properties This reason What I'm saying is if Howa B desescriptions, even from a scientific perspective of certain macroscopic phenomena lead us to treat these phenomena as behaving indeterministically. for instance, because in the case of dice or coin toorses because stochastic modeling is the right way to go from a scientific perspective. thenen we should just say Well, that's as scientifically well supported as anything we say in particle physics, and we should just take it at face value And that's, you know, just as real as the kind of thing that we say about a more fundamental physical level. And so therefore, I want to say this form of an High level indeterminism know Marcus Pivato and I also called this phenomenon sort of emergent indeterminism. we shouldn't think of this as just epistemic. So we shouldn't think of it as just to do with U informational incompleteness or something like that. But we should really think of it as ontic as a real phenomenon That's the little mist that I would put on your way of framing it. I like that much better. It's a classic example of, of course, what you said is absolutely what I wanted to say, but you said you said it better having thought of it more. So this is a wonderful segue into maybe we should, you know give this picture of the world as apparion levels It's due. So put aside free will just for a moment, But and I think you've already said a lot of it, but I want to give you a chance to sort of fill in whatever we need to understand here. You're claiming that there are different emergent levels of description related by course graining. and There's always a question in that picture of how much sort of independence or autonomy we should grant to the different levels. So what would you feel about that? Yeah, so okay. Yeah, as I as I already explained, we can thinkink about the world at many different levels of description, I gave these different examples from physics to chemistry to biology, to psychology to, you know sociology, economics, micro macroeconomics and so on Now what This is not just that When we move from moreore fine grade microscopic descriptions to more c grain macicroscopic ones, we sort of c grain and we throw out information. I mean we do throw out some information, we abstract away. We do this not just because of ational epistemic limitations, but we do it in order to identify patterns while sort of getting rid of noise of extraneous details because there's some low level details that are relevant for The lower level, but that may not be relevant at all for the macroscopic description. And so then in a sense it's illuminating if you extract a signal and get rid of the noise and focus on the macro pattern. So for a starter course grining is done for a principled reason. Secondly, of course, it's not just that we cse grain when we move from low level descriptions to high level descriptions But we also use different concepts and categories to think about the world So I mean, even u know philosophers of chemistry point out that a concept such as acidity, which is a chemical concept, it doesn't really have a neat physical counterpart. So if you sort of think about it already acidity be sort of easily translated just into purely physical concepts and that becomes all the more significant as we move up this kind of explanatory hierarchy. And I mean, it's pretty clear that a whole bunch of psychological concepts can't really be reduced to purely physical, chemical or biological concepts. or even you psychology think it is fairly widely accepted is not is not reducible to neuroscience and The most important, I mean, if we look at the sort of big picture, I think the most important dividing line is one between Um subintentional and intentional But levels of explanation So let's say physical explanations, chemical explanations, they're clearly subintentional U we u use some form of dynamic or stochastic modeling to describe the relevant processes, but We don't use any intentional vocabulary there. There are no goals, there are no purposes, There are no beliefs, there there' no semantic content of anything. There are no representations And On the other hand,, you know, once we once we move into the domain of psychology cognitive science, the kinds of domains where we then also think about agency or think about rationality, think about mind's mentality and also think about social phenomena We make very significant use of intentional language or intentional intentional concepts And I think there are very good reasons why intentional language, intentional concepts can't really be reduced intentional concepts or subintentional language And you know, if we are sold, I mean, again, there is a whole bunch of separate arguments as to why this reduction is not quite possible. But if we are sort of sold, on the idea Some of the concepts and categories required for intentional explanations are not reusable to concepts and categories from one of those subintentional levels of description then that gives us a good case for saying there's a kind of explanatory autonomy that the higher level it joys relative to the lower level So this is great because I want to really press on this claim about reducibility. Of course, it's crucial to these kinds of arguments. and I'm never quite sure What is being meant? I know that in Phil Anderson's famous paper on M is differentnt. He says over and over again, off course reductionism is true. What he doesn't like is constructivism where you actually go from the lower level to derive what you mean at the higher level. I mean, I would think that acidity has some definite precursor at the lower level and maybe it's just we can't identify it or we don't use that concept in its own right at the lower level But it's still A coarse grained notion in some sense. or do you mean more than that or less than that or exactly that Okay, good. U So One of the reasons why A lot of people tempted by various reductionistic positions is that they accept the idea of supervenience. So supervenience is a very natural idea. It's basically the idea Um All the high level facts that obtain as some kind of necessary byproduct of low level fat. So for instance if we put all the um lower level building blocks of this world, all the elementary particles and so on in place exactly as they are in our physical universe. then you have also thereby put you and me in place, you know, with our with our brains and minds and everything. So the supervenience idea is, you know, everything that is And that is true about Sean and Christian as people as agents is necessitated by bunch of extraordinarily complex things that are true about the underlying physical system. So fast so good.. And everyone who accepts claim that this is true is a supervenience physicalist. Okay And now the tempting but nonetheless kind of invalid argument, I would say Well, because supervenience physicalism holds, because all these high level facts, high level properties superven on low level ones We should therefore also be able to explain everything in low level terms, or we should be able to translate high level descriptions into low level ones. And that's actually the step where the so called non reductive physicalists, which I find the much more compelling position, would, you know, no longer agree and sought Hupervenience does not imply explanatory reducibility. and I can I mean there's different ways I can make this point. I mean, I can If you want to give you the sort of absute nerdiest argument, which I think you have to give us the absolute nerdiest argument just by saying that, yeah, we need that Okay, so the Well, I mean well I'm not even claiming that it's the absolute nerdiest argument because I'm sure people people can come up with even nerdy anw.. I mean, here's let's say at least one candidate for a very nerdy argument. Okay So u So the kinds of languages that we use to describe systems are all u countable languages. so that means Um, they, um permit us to form as many expressions as there are natural numbers. you know that's infinitely many, but it's countably infinitely many. you can easily convince yourself that any of the standard logics that you find in logic textbooks are accountable But also English is a acc countountable language, German is a countountable language. I mean, anything that you can write down with the help of a finite alphabet and so on is going to be a countountable language. So languages that we use are countable, languages that we Using the scienceces accountable. Okay, so far, so good Now, it follows immediately that if you have a countable language available for describing things, means You can come up with infinitely many but still countably infinitely many descriptions. o? So that means with a countable language you can describe countably many properties, for example. Okay. Now, Suppose that the following is the case. We're dealing with a I me We are dealing with a physical universe suppose The set of possible microstates that this physical universe can be in or any other physical system, let's suppose, the set of possible microstates is infinite. So there are infinitely many possible microstates. That seems completely reasonable because becausecause initial conditions could be chosen in different ways So's we we're always dealing with systems. I mean with your sufficiently realistic systems, would in principle admit infinitely many possible micro states that they can be in Now microscopic properties that we might be studying in you know one of these high level sciences, you know, be it biology, be it psychology and so on They always correspond to sets of states, right? Because any property is realized by hold by a set of states But once you've got acc accountably Once you've got accountable sorry, once you've got an infinite set of possible microstates You automatically have uncountably many possible subsets Make it a summer of Live at PNC Bank Art Center. Get four lawn tickets for just ninety nine dollars and see Goose on july second The guess whoo on july fifth Lindsay Sterling on july eleventh Weird Al Yankobvic on july twelfth, Toto, Christopher Cross, and the Romantics on july eighteenth, and many more. Get your friends and grab tickets now at pncbankartartcenter d. com burst pipe, A dead water heater, the AC calling it quits. Who do you call Home Serve is an easy way to handle unexpected home repairs. W plans covering stuff basic homeowners' insurance usually won't. Instead of scrambling for a contractor, you make one call to get the repair process started. Join the millions of customers who trust Homeerve right now. Go to homeServe dot com slash podcast for fifty percent less your first year. That's homeomeserve dot com slash podcast.avings compared to a renewal price boy in Florida Okay, even if it's a countountable number of whatos even if it's a countable number. I mean, yeah. so of course it might even with with systems that you describe with the help of the real numbers, you might even have uncountably many u, you know, micro states well, you know, then you don't even have a chance. But even even if you Even if you concede for the sake of argument, there are only countably many possible microstates of your system, as many as their are natural numbers then still there are uncountably many sets of these states And so that means at least in principle, I mean this is really just a purely combinatorial thought experiment. There are uncountably many properties that B considering Now of course most of those properties are of absolutely no interest, no explanatory relevance and so on and so on Po is There at least extentionally speaking, there are far more properties out there than acc countountable language would allow us to describe. So if you have accountable language for talking about microstates, just for pure combinatorial reasons, almost Every property correspondso collection of those microstates will not be describable bu an expression this in this countable language. And now When we think about micro properties You know, if you accept supervenience, okay, good. then what we do know, from supervenience, from supervenience would follow that any micro property does have a kind of extension corresponds at least to an extension that would be a collection of microstates. It would have to be at least if you just go with this cominatorial line of reasoning, it would be some kind of mega flu It turned out to be one at your low level accountable language allows you to describe. I mean, you might be lucky. It might be that somehow On explanatorily relevant or explanatorily salient properties are those that can be picked out with the help of the low level language. But I think now we've kind of reversed the sort of burden of proof because I think the proponent ofd of explanatory reduciability would have to show that. Cbinatorics are kind of against the reductionist. So this is the kind of This is this kind of nerdy argument as to why even if you grant supervenience you there's still no guarantee. that high level descriptions of properties are reducible to low level dispbances. I like it. and I think now the audience knows what mathematical philosophy looks like when it's done properly. Yeah of course I can also say not all mathematical philosophies is quite like this. And this argument admittedly is in a quiet pace So I think some people will like it more than others. But I think it's at least a friendly acquaintance of a question that too my mind is still unclear in the world of levels and immersions and things like that, even though I'm a big fan in general. it seems that if you do by the supervenience thesis, which it sounds like you're willing to do. So if you had exactly the same microphysical system You would also have exactly the same higher level properties Um And also, the higher level theories are more or less autonomous. You don't need to know the micro theory. I can do thermodynamics or flip coins without knowing about the standard model of particle physics. then there's two things going on simultaneously. One is that the higher level concepts and objects fit into an autonomous dynamical framework, like we can describe what happens with them But also they're observable Right? Like you know if you talk about a fluid and it has a temperature and density, those are the quantities you need out of the vastly reduced set of information you had about the atoms and molecules. And also we can measure them. I mean is that Do those two things go hand in hand automatically, or is that some nice miracle that the world provides us Well, it's of course it's true that a lot of the High level, u properties are of interest to us precisely because, you know, they play a role in our lives and, you know, we as biological organisms have also been kind of evolutionarily selected in such a way as to be sensitive to certain properties of the environment and not others. So I don't find it particularly surprising that microscopic properties are particularly well measurable. from our perspective as compared to certain microscopic properties. And I mean, I would also add that U I mean, in principle, there's many different levels of description that one could use to think about a system. And Now Which levels of description are planetarily relevant or interesting is of course, somewhat dependent on, you know what your goals as an observer are what you what your interest as an observer are, what your perspective on the world is. and so So I mean, I don't find it very surprising that you know, we as humans operating at a particular scale, you know, biological organisms of a particular size find certain levels of description, particularly interesting and salient, know, who knows, if we were intelligent beings at a completely different scale you know maybe we would be sensitive to different features of the world at a very different level of description. So there's definitely a certain amount of kind of interest relativity to our choice of levels. Good. I think that's that's a good amount of background where we can now circle back to the free will question know you made a good case earlier that free will at the macroscopic level is not just an epistemic matter of what we know and what we can predict. There's a sense of genuinely, it could have gone the other way. So but at a more detailed level, What is the difference between saying that Aents at this level description have free will versus just there's some indeterminism at this level. Are there conditions under which we can finally say, yes, that object in front of me is an agent with free will Yes, ye. so I mean, my proposal is that We should Use a checklist of free conditions for assessing whether a particular system or a particular organism has a free will And they are the following, first of all, intentional agency only systems that qualify as intentional agents are even candidates for having free will. And then I mean there's a lot more to be said exactly about what an intental agent is. perhaps come back to that later. So for instance, my water bottle that I have here is not an intentional agent it's not even a candidate for having free will. So intentional agency is the first condition The second condition is indeed alternative possibilities theseese I think have to be alternative agential possibilities U you know, corresponding to the choice options between which an agent can make choices And then the third condition is what I call causal control over the resulting actions. Philosophers sometimes also speak of mental causation. And so this is condition that says And the purportedly chosen action must count as having been caused by the agent's mental state. and must not count as having caused just by, for instance, an underlying physical process of the of the body as in a reflex, for instance. So you know, if the doctor hits my knee with a little hammer, my leg shoots up. And of course, some bodily process causes that movement we are not really dealing with a case of mental causation here. So wherese if I intentionally lift the bottle, then you might say Well I had a desire to lift the bottle, I formed the intention to lift the bottle. And then my relevant arm movement, the performance of the action, systematically co varied with the presence or absence of those intentional mental states. And so then we say, I qua agent, not just qua physical system had causal control over the resulting actions. And and so I think free will requires all three things, intentional agency, alternative possibilities, and causal control of the resulting actions. And so if you just had a system place some form of high level indeterminism that would not by itself qualify as having free will because that system wouldn't necessarily satisfy the agency condition. It wouldn't necessarily satisfy the causal control condition And so it's really just the interplay of these three things that really amount to free will. So I like where this is going, but you're using a lot of words like intentionality and reasons. And I worry that if I were a skeptic, which I'm not, but if I were, I would ask like How do you know that a system has those properties? I mean, large language model might respond in a certain way if I said, why did you reason in that way? But I'm not at all convinced that it's actually giving me an accurate response So yeah, so I mean the large language model is, of course super interesting. So let's set it aside just for a second. So let me first say something about the general methodology and then if we look at the complicated case later. So the general methodology is this I am sort of quite drawn to and was also originally quite influenced by Daniel Dennet's work on the intntentional Stance, which which you know well and which I'm sure you know your listeners are also very familiar with. Theyry sorry they might not be. giveive us a little tiny. Yes I'll give a little bit of a A summary So then it basically said, okay, there are some systems which we can understand perfectly well by just viewing them as physical systems. Let's say the solar system, how do the planets revolve around the sun You take a physical stance towards that system, you write down a physical model, you can explain the thing But then there are other systems like you and me, human organisms whom or which we can't understand adequately by just viewing them as physical systems. I mean, if you really wanted to you make sense of you and me just as Uh, um aggregates are conglomerates of vast numbers of molecules. I mean good luck. So you'd have no chance of explaining why you and I managed to know coordinate on this the time for this conversation. I mean, you know, we agreed to meet today, but we agreed weeks ago And we could actually reliably predict that we were going to show up for this thing at a purely physical level, just focusing on the molecules making up the body. we'd have absolutely no chance. So then it says Where with some systems Um, to make sense of them, to understand them, to explain them, to predict them. You've got to take an intentional stance towards them. So you've got to view them as agents, with beliefs, with desires, with goals, with intentions And once you look at them through that lens Then all of a sudden Um their behavior becomes intelligible to us, whereas from the purely physical perspective, it would be a kind of complete mystery. So obviously the key to understanding human behavior is to realize beings are intentional agents. okay So then says well, that's really all there is to the notion of agency Whenever you've got a system that you can, I think he says usefully and voluminously explain and predict from the intentional stance by viewing it as an agent, well, then that's good enough, that's an agent and I mean, I think the problem with Dennet's perspective is that It is kind of instrumentalist because then agency is just in the eye of the beholder. To be an agent on this Denfian view is just to be interpretable as an agent. So if the thermostat is well interpretable and well predictable as an agent, okay, wellher that's fine. That's it is an agent. And there is nothing more to the story And I want to go a little bit further. I want to say, well Um to be an agent is not yet the same as to be interpretable as an agent because one is a sort of epistemic criterion and the other one is sort of ontic Rather a system If interpretable satisfactorily adequately only by viewing it as an agent. So if it is if viewing the system as an agent is explanatorily indispensable We can't explain it adequately in a different way then the explanatory indispensability of viewing the system as an agent is a very good, strong indicator, a good piece of evidence. that we are truly really dealing with an agent Turns out that I have absolutely no chance of making sense of you Sean without viewing you as an intentional agent. Ver, very strong evidence that you really are an agent And so you see the point. So the indispensibility of taking the intentional stance towards a particular system is strong evidence that we are really dealing with an intentional agent this indispensability test that I also use in order to assess whether a system should qualify as an intentional agent From the perspective of the free will debate And that're just related to the issue about AI. I mean, I totally admit that it's a complicated issue Um becausecause I mean, there are there there are all these big debates, you know, are these LLMs? are they just stochastic pets? or you know are they are they really just glorified versions of the sort of autte text extension, auto complete software that we have on our smartphones O are they are they something else? or do they mimic agency or do they do they genuinely have agency? and I mean, you find people on both sides of the Divide Yeah. And and also of course the technology is in flux. so you know, maybe at an early stage of the technology, We were sort of very much at the stochastic pot end of the spectrum, but of course the technology also advances and the systems increasingly get engineered in such a way as to be explicitly designed for reasoning abilities and so on And what I would say is simply this U Now once we reach the point where those systems also satisfy this indispensability test. where it where you just cannot make good explanatory sense of them without viewing them as genuine intentional systems then we've got good evidence that they really are intentional systems My feeling is that whether we like it or not, we are kind of heading in the direction where More and more systems maybe are like this. and that's actually also why why I think that this set of criteria for free will, intentional agency, alternative possibilities causal control might I don't know whether now or in the future, but might potentially force us to conclude, prompt us to conclude that some sophisticated AI systems also qualify as having free will. There's a reason Chevy trucks are known for their dependability. that's because they show up no matter the weather, push forward, no matter the terrain, and deliver. That's why Chevrolet has earned more dependability awards for trucks than any other brand in twenty twenty five according to JD Power. Because in every Chevy truck, like every Chevy driver, dependability comes standard. Visit Chevy dot com to learn more. Chevrolet received highest total number of awards among all trucks in the JD Power twenty five US vehicle dependability St study Award based on twenty two model, new models may shown visit JDPpower dot com slash awwards for more dets Chevlet. Together, let's drive A burst pipe, a dead water heater, the AC calling equits. Who do you call? HomeServe is an easy way to handle unexpected home repairs, with plans covering stuff basic homeowners' insurance usually won't. Instead of scrambling for a contractor, you make one call to get the repair process started. Join the millions of customers who trust HomeServe right now Go to Homeserve. com slash podcast for fifty percent less your first year. That's homeomeserve d. com slash podcast. saavings compared to renewal price void in Florida. At the risk of entirely derailing the conversation. story that you told, which I'm very sympathetic to about findinding it indispensable to use some of these concepts to talk about these systems, reminds me of debates over philosophical zombies and consciousness And as a physicalist, I want to say can't conceive of a zombie philosophically because the zombie is supposed to be something that doesn't have conscious experience but behaves exactly down to the atom as if it does. And what I mean by consciousness is just that that's the way the best possible description of this system at this level involves language and concepts of consciousness, and this sounds at least a little bit parallel. Yeah, so I mean so yeah, that's so that yeah, the whole consciousness issue that that raises a separate set of separate set of issues. I mean to just for full disclosure. so while u My, um The theory of free will is fully wholly framed against the background of physicalism and indeed non reductive physicalism, as we've now discussed at some length When it comes to consciousness, I sort of go in a slightly different direction It's not something that I had kind of antecedently expected. You know when I started to think about these issues, sort of expected that I was that I would be a physicalist with respect to consciousness as well. And no, I'm maybe ended up surprising myself by u Coming out on the other coming out on the other side In a nutshell The extra complication with consciousness that simply isn't there with free will and agency is that Consciousness is first personal. And when we talk about phenomenal consciousness, we're really talking about first personal experiences. We're talking about first personal facts. we're talking about the first person perspective, And by contrast, when we ask, know, is a system an agent? does a system have representations Uh Does the system have alternative possibilities between which it can choose? Does it have causal control or mental causation in relation to its actions. These are all third personal questions can in principle formulate from the perspective of an ordinary scientific third personal observer. And so that's why I actually think The study of free will and agency can be done completely andproblematically from the ordinary third personal scientific if And so methodologically, that's sort of much closer to what David Charmers would call the easy problems of consciousness. sorry, yeah, exactly. Whereas the hard problem is You know, how how do we make sense of in a sense, the first person against the background of this personersal, impersonal scientific picture of the world. And that's I think the sort of big structural difference between the consciousness debate and the free will debate. And you know, while in the case of free will, I've and I' completely convinced myself that you can be a physicalist, you could even be a physical determinist and yet you can embrace free will and you can even embrace free will with the idea that there are alternative possibilities at the level of agency and everything fits together nicely once you recognize the sort of leveled architecture of the worldview. I find that it is much, much harder to Pperly accommodate consciousness as first personal experience, not just as third personal descriptions of the whole thing, but as first personal experience within this purely third personal or impersonal worldview of the sciences. So I've found myself ending up in a place is actually even more radically non physicalist consciousness than even Chalmas' view. So David Chalmas rejects physicalism U but u U in a sense doesn't reject the the sort of in a sense ordinary impersonal, third personal picture of the world. So I mean that he accepts the framing that to think of a world that we can talk about from a scientific perspective. And then the debate is all about what sorts of properties must populate this world in order to make sense of consciousness. And in the physicalists would say, you know, just having a world with physical properties is enough And then Charmers in his classic wonderful book, The Conscious Mind nineteen ninety six. says No physical properties alone are not good enough. You need to also have phenomenal properties and the phenomenal properties do not supervene on the physical properties and that's then how he sense of the Zombie thought experiment and his and his view that that zombies are conceivable and metaphysically possible, albeit not normologically possible. U'm This still concecedes the framing that you can look at the whole thing in a sense personally, impersonally from the perspective of The sort of Olympian scientific observers studying those systems from the outside the kind of view that you know, Nagel would call the view from nowhere in a sense And then we just debate, what properties do we need to throw in in order to make sense of of of consciousness and And I'm sort of much more sort of a nagal side and think that actually the problem lies with a view from nowhere with the impersonal perspective. We can't really properly accommodate consciousness in our worldview Um without recognizing the sort of fundamentality of the first personal perspective. and that leads me to think that We must really postulate genuine, irreducible first personal facts over and above the third personal or impersonal facts that we have in the physicalist worldview, but once you introduce these first personal facts then you are really quite radically outside the standard physicalist picture and then that raises a whole bunch of of new challenges. But that was sort of a quick summary of why I think the consonsciousness debate is structurally different. from the free will debate. Perfectly fair. I get it's refreshingly honest that you know you follow the conclusions where they go when you think about these things. But I do want to give you time. you've laid out an interesting case for why thinking about free will has to do with levels of description and the assistance of The possibility for things having been otherwise and the existence of agency and intentionality Okay, if there are these levels, then there are also higher levels than individual people. There are groups, there are corporations, there are nations At what point do we start attributing free will to them Yes, ye, great, great question. So so in fact, I sort of got into the whole subject of agency in a slightly non standard way because began my career working primarily in social choice studies, so the study of collective decision making and also the mathematical modeling of collective decision making and In the course of this work, I collaborated a lot with Patt, a philosopher in Princeton and at the Australian National University. and Philip and I On the one hand did some work together on the aggregation of judgment. So this is sort of a collective choice problem more or less in the kind of condorse arow social choice theory tradition. But we also in particular then wrote a book together on the subject of group agency. And so in this book, we discussed the question of whether It sometimes makes sense to view certain collective entities, especially organized collectives, institutional collectives like firms, corporations, collegial courts, universities, even states in their entirety, whereether it makes sense to view those collllectives as kind of unified agents in their own right And an important observation is that In ordinary life, we do this all the time. I mean, we treat collective entities as agents, you know, we talk about how the airline treats us. we ascribe goals and intentions to firms But it's not just a kind of common sense thing, but we also do this in the relevant sciences. So in economics, the theory of the firm use firms of corporations as rational actors and applies the very same rational choice theoretic models to explain their behavior In international relations theory or some areas of strategic studies, entire countries or states get treated as unitary rational actors, in fact If we look at the history of game theory, The whole field was did developed quite significantly in the aftermath of the Second World War context of strategic studies where you know, studying, for instance, at the time, the strategic interaction between the United States and the Soviet Union was a major driver for developing game theoretic models. So this idea that C corporate entities can be rational agents in their own right. It's not just a common sense idea that we find, but also very much an idea that is entrenched in the social sciences. And so that led us then to think, you know how can we develop philosophical foundations for this idea and And of course, mean you see immediately how this raises many interesting metaphysical philosophy of mind questions what do you say about the sort of mental states or the analogues of mental states of those corporate entities? And it also raises many normative questions about the sort of responsibility that those entities can have. So Philip and I def in our book, we defend a realist theory of agency, so we think that parate entities can truly be intentional agents with functional states that qualify as beliefs, functional states that qualify as desires or goals or preferences and then with an ability to systematically interact with the environment on the basis of those states. So basically, pursuing their desires in line with their beliefs. And we don't think that those corporate entities are phenomenally conscious, so they are You could think of them as kind of zombie agents if you like, but you know, zombie corporate agents If you are a realist about group agency as I am, then there is the obvious question whether we should ascribe free will also to those entities And again, I think my theory of free will, especially with its catalog of the three criteria, the three conditions that I mentioned earlier can actually allow us to think about that question systematically Because these three criteria, intentional agency, alternative possibilities for choice and causal control over the resulting actions there are portable criteria. They are not criteria that are just sort of custom made solely for the human case. but those are criteria which at least in principle could be applied to other entities as well. So you can use these criteria and ask Do chimpanzees fulfill those criteria? And it's so The answer would be they have some form of free will and I I mean I'm not a primatologist, but you know, given everything that I've read, I think we should conclude, yes, absolutely. And I mean, it would be very weird if if somehow, you know humans come out as having free will and absolutely none of the other animals do, not even our closest relatives do But then similarly, I mean earlier, we talked about LLMs, so we talked about AI systems In if if we think uh, our B explanations force us to say U such and such AI systems are intentional agents because viewing them that way is kind of indispensable. if our best explanations force us to say that they are They arere choice makers, they're genuine decision makers, they're choosing between options. and if they also force us to say They have some kind of analog of mental causation. So let's say they' high level representational states. other sort of controlling difference making variables in relation to what they do, then we'd have to say that those systems qualify as having free will in this sort of functionalist sense. And I think exactly the same be said also about gp agents. So if we have a corporate entity that satisfies those three conditions, intentional agency, alternative possibilities for choice causal control, the sort of corporate level analog of mental causation then we should conclude, yes, there is a sort of functionalist sense in which Entity does have free will And I mean, although this conclusion, I mean might sound a little bit revisionary and weird at first sight It becomes less weird once we recognize that free will is not the same as consciousness. So we are not thereby force to conclude that they are conscious. they're not, corporate entities are not ly, I think On reflection, the conclusion should even be welcome because I mean, those entities As we all know, are very powerful. They really play an imp ed an enormous role in our contemporary world, in our social environments. they can cause a lot of harms and do big damages. In fact their power is much greater than that of typical individuals, And so we should better have certain frameworks in place for thinking about responsibility and even and corporate liability and Even something like corporate criminal liability. I mean, all of those are very important notions and you know lawyers take those notions seriously and debate them And if we If we Accept a general story that some form of free will is a sort of necessary condition for fitness to be held responsible. thenen It's a kind of congial finding that that necessary condition is also satisfied by some of those corporate entities And I guess we didn't go into it in detail, but Would you say that there's this close connection between the satisf satisfying your criteria for free will and our legitimacy in assigning responsibility or blame to various agents And so I would say that free will in this functionalist sense that I've Defined here is a necessary, but not sufficient condition for fitness to be held responsible. I mean, I suggested earlier that you know, maybe chimpanzees could be said to have free will or some version of free will under those conditions. Now we don't want to say that chimpanzees bare moral responsibility or let alone legal responsibility. So therefore think that Free will understood in this way is a kind of necessary precondition And then there are some additional conditions that also have to be in place for responsibility. For instance Um certain normative cognitive capacities need to be present in the system And in addition, certain epistemic conditions must also be met informational conditions. Okay And and of course, moreor phhilosophers have debated in detail what the nature of those conditions is, but Um, but um But nonetheless, I mean free will is sort of an important part of the package. this kind of analysis suggests that yes, indeed U separate entities you know, st And this brings up an issue that I've been wrestling with myself quite a bit. A slight difference between the kind of course gining and collective behavior we get in physics and the kind we get in the social sciences, which is that In physics, when you have a bunch of atoms and they come together and you find that it's useful to assign temperature and density and pressure and things like that, The system itself suggests the right way to course grain, right? Like it's not making any choices about it Whereas in groups of human beings, We vote or we invent a system of representation or something like that, and voting systems and representation systems could be giving us wildly different results. So it's sort of not naturally emerging, but it's imposed from us. Is that a real important difference or am I just making a big deal out of nothing Well, I mean, the observation is right, but u What I would say is this so You know, suppose you're dealing with a group agent and you're interested in what sorts of beliefs or preferences or overall collective attitudes to ascribe to this group agent this this qua corporate entity. and then you're right that it might be relative to a particular voting method or institutional structure or aggregation rule re deffine the group agents' beliefs or the group agents' preferences And and of course those corporate attitudes will be contingent on the aggregation rule in question. I What you What you can then say is, well, the group believe so judgments supervenen on the individual judgements relelative to the organizational structure defines that entity. So the organizational structure might be written for instance, in the articles of association of this entity. So the constitution, you can think of this it as it's sort of software or something like this or it's operating system that specifies specifies how the thing works. And then you've just got the sort of perfect analogy with with a kind of computer. So the high level states of my computer also supervene on low level states, but they They do so relative to the operating system running, running the thing. And the operating system is the sort of much more contingent social level analog of the kind of Um you know, normological constraint that is naturally given to us in the case of a physical system, but it sort of plays a similar role. So in the case of the physical system, maybe the normological constraint in question is just given by some laws of nature. and then sort of fixes the the nature of particular supervenience relation that we're interested in in the in the corporate case the nature of the supervenience relation is relative to the organizational conucture organizational structure, which is the sort of system relative normological constraint. So to say Does thinking in this way help us decide the very hard question of are good systems of aggregating beliefs in corporations or countries for that matter Well, I mean So the way of thinking that I've summarized here is heavily influenced by social choice theory, the sort of field in which as I mentioned earlier, I started I started out and Social choice theory is sort of the formal study of aggregation rules, aggregation mechanisms, and For a long time, social choice do focus primarily on things like preference aggregation or vote aggregation or utility aggregation. but in the last twenty five years or so Many of us have a lot on the aggregation of judgments, also the aggregation of beliefs social choice theory gives us a sort of wonderful set of axiomatic tools for thinking about the nature of different aggregation methods and for comparing them. so very often the way we proceed as we We formulate a bunch of deciderata, minimal conditions, a sort of wish list of criteria are requirements that a good method of aggregation should satisfy And then u Once you've got a wish list of such axoms or criteria or deciderata, then we use mathematical analysis to ask do there exist some aggregation methods satisfying those criteria simultaneously? And sometometimes we end up with a negative result and possibility result. So that's the sort of landmark result of the field, arrows and possibility theorem is best known example of this. But sometimes we also get a possibility result. So it turns out that a bunch of conditions kind of uniquely pick out a particular aggregation rule Um, And then to the extent that we find those criteria very obvious, intuitive, appealing,, normatively compelling, that would give us very strong reasons to adopt the relevant aggregation rule. And yeah. And so one of the things that Patt and I also do in our book as we import some ideas, some social choice story to then suggest the systematic way of thinking about different organizational structures of group agents. We did have Philip as a guest here on the podcast, by the way. Wonderful That's great. That terrific. You got both of the co authors there. All right. so just sort of as the final thing to get to get on with to wind up. Well, let's go back to the LLMs because this is the sexy topic right now that everyone is interested in Um I hear your previous argument that It's very plausible in your mind that you have these three criteria for free will and maybe LLMs It's an empirical question, whether they will get there, do have it, etcetera Um There's various worries I have about this. Let me just mention one When I have an LLM in front of me, I can prompt it in such a way as to effectively totally change its personality very quickly, right? I can you know, I can tell it to like, okay Henceforth, be more impetuous or be more conservative or you know act like this person or whatever. There doesn't seem to be a kind of stable identity at the core of the LLM. Is that something that maybe Schider does play a role in having free will or being an agent Yeah, that's a that that is a good point and um Of course this is also one of those areas where the technology is in flx. because these different these systems differ quite a lot with respect to how stable or volatile their personality is. and I mean I hear that companies like Alropic