I have the great pleasure to announce Yosa who will give us a great talk with the title the ghosts in the machine and he will talk about consciousness of our mind and of computers and somehow also

tell us how we can learn from AI systems

about our own brains and I think this is a very curious question so please give it up for Yasha

[Music] good evening this is the fifths of a talk in a series of talks on how to get from computation to consciousness and to understand our position in the universe based on concepts that I mostly learned by looking at artificial intelligence and computation and it made mostly

tackles the big philosophical questions what can I know what is true what is truth Who am I which means the question of epistemology of ontology of metaphysics and philosophy of mind and ethics and to

clear some of the terms that we are using here what is intelligence what's a mind what's a self what's consciousness how our mind and consciousness realized in the universe intelligence I think is

the ability to make models it's not the same thing as being smart which is the ability to reach your goals or being wise which is the ability to pick the right goals but it's just the ability to make models of things and you can regulate them later using these models but you don't have to and the mind is the thing that observes universe itself is an identification with properties and purpose is this what I think thinks it is and then you have consciousness which is the experience of what it's like to be a thing and how am i the question is realized in universities is commonly called the mind-body problem and it's been puzzling philosophers and people of all proclivities for thousands of years

so what's going on how is it possible that I find myself in a universe and I

seem to be experiencing myself in that universe how does this go together and how's this what's going on here the

traditional answer to this is called dualism and the conception of dualism is that in our culture at least this dualist idea that you have a physical

world and her mental world and they coexist somehow and my mind experiences this mental world and my body can do things in the physical world and the

difficulty of is this dualist conception is how do these two planes of existence interact because physics is defined as causal you closed everything that influences things in the physical world is by itself an element of physics so an alternative is idealism which says

that there is only a mental world the only exists in a dream when this dream is being dreamt by a mind on a higher plane of existence and difficulty was this is very hard to explain that mind of a higher plane existence was putted there why is it doing this and our

culture the dominant theory is materialism and is basically there's only a physical world nothing else and the physical world somehow is responsible for the creation of the mental world it's not quite clear how this happens and the answer that I am suggesting is functionalism which means that indeed we exist only in a dream - so these ideas of materialism and

idealism are not in opposition they are complementary because this dream is being rammed by a mind on a higher plane of existence but this higher plane of

existence is the physical world so they are being dreamt in the neocortex of a primate that lives in a physical universe and the world that the experience is not the physical world it's a dream generated by the neocortex the same circuits that make dreams as at night make them during the day you can show this and we live in this virtual reality being generated in there in the self as a character in their dream and it seems to take care of things it seems to explain what's going on explains why

a miracle seemed to be possible why I can look into the future but cannot break the bank somehow and even though the theory explains this how shouldn't I

be more agnostic and they're not alternatives that I should be considering maybe the narratives our big religions and so on and I think we should be agnostic so the first rule of

epistemology says that the confidence in a belief must equal the weight of the evidence supporting it once we stumble on that rule you can test all the alternatives and see if one of them is better and I think what this means is you have to have all the possible believes you should entertain them all but you should not have any confidence in them you should shift your confidence around based on the evidence so for instance it is entirely possible that this universe was created by a supernatural being and it's a big conspiracy and had actually has meaning and it cares about as in our existence here means something but there is no experiment that can validate this a guy coming down from

a burning mount for a burning bush that you've talked to on a mountaintop that's not a kind of experiment that gives you valid evidence right so intelligence is the ability to make models and

intelligence is a property that is beyond the grasp of a single individual a single individual is not that smart we cannot figure out even Q incomplete languages all by ourselves to do this you need an intellectual tradition that lasts a few hundred years at least so civilizations have more intelligence than individuals but individuals often have more intelligence than groups and whole generations and it's because groups and generations tend to converge on ideas they have consensus opinions a very very of consensus opinions because you know how hard it is to understand which programming languages the best one for which purpose there's no proper consensus Nets a relatively easy problem so when there's a complex topics and all

the experts agree there are forces at work that are different than the forces that make them search for truth these consensus-building forces they're very suspicious to me and if you want to understand what's true you have to look for Minton's motive and you have to be autonomous and doing this so individuals typically have better ideas than generations or groups but as I said

civilizations have more intelligence than individuals what does this civilization intellect look like the

civilization intellect is something like a global optimum of the modeling function it's something that has to be built over thousands of years in an unbroken intellectual tradition and guess what this doesn't really exist in human history every few hundred years there's some kind of revolution somebody

opens the doors to the knowledge factories and gets everybody out and burns down the libraries and a couple generations later the knowledge worker drones of the new king realized oh my god we need to rebuild this thing this intellect and then they create something

in its likeness but they make mistakes in the foundation so this intellect tends to have scars like our civilization intellect has a lot of scars in it that make it hard to difficult difficult to understand concepts like self and consciousness and mind so the mind is something that

observes the universe and the neurons are neurotransmitters are the substrate and a human intellect and the working memory is the current binding state how do the different elements fit together in our mind and the self is the identification is what we think we are and you want to happen and consciousness is the contents of our attention it makes knowledge available throughout their mind and civilization intellect is very similar Society is observed the universe people in resources are the substrate the generation is the current binding state and culture is the identification with what we think beyond what we want to happen it media is the contents of our attention and make knowledge available as well society so the culture

is based the self of civilization and media as its consciousness how is it

possible to model a universe let's take a very simple universe like the man who got fractals can be defined by a little bit of code it's a very simple thing you just take a pair of numbers you square it you add the same pair of numbers and we do this infinitely often and typically this goes to infinity very fast and there's a small area around the origin of the number of pairs or between minus 1 and plus 1 and so on where you have an area where this converges where it doesn't go to infinity and this is where you make black dots and then you get this famous structure the Mandelbrot

fractal in his because this divergence and convergence of the function can take many loops and circles is on a very complicated shape and very complicated outline and three is infinitely complicated outline there so there's an infinite amount of structure in this fractal and now imagine you happen to

live in this fractal and you are in a particular place and you don't know where it is where that place is you don't even know the generator function of the whole thing but you can still predict your neighborhood so you can see oh my god I mean some kind of spiral and it turns to the left and goes to the

left and goes to left becomes smaller so you can predict and suddenly it ends why does it end a singularity oh it hits another spiral so there's so love and a spiral it's another spiral it ends and something else happens so you look and then you see oh there are certain circumstances where you have for instance an even number of spirals hitting each other instead of an odd number and then you discover another law

and you make like 50 levels levels of these laws and this is a good description that locally compresses the universe so the Mandelbrot fractal is

locally compressible you find local order that predicts the neighborhood if you are inside of that fractal the global modeling function of the manual factor is very very easy it's an interesting question how difficult is the global modeling function of our universe leave if we know it maybe it doesn't help us that it will be a big breakthrough physics when you finally find it will be much more than a standard model I said as a I suspect but we still don't know where we are and this means we need to make a local model of what's happening so in order to do this we separate the

universe into things things are small state spaces and transition functions they tell us to get out to get from state to state and if the function is deterministic it is independent of time it gives the same result every time you call it for an indeterminate stick function it gives a different result every time so it doesn't compress well and causality means that you have separate several things and they influence each other's evolutions were shared interface right so causality is an art effect of describing the universe as separate things and the universe is not separate things it's one thing but we have to describe it as separate things because we can observe the whole thing so what's true there seems to be a particular way in which the universe seems to be and that's the ground truth of the universe and it's inaccessible to us and what's accessible to us is our own models of the universe the only thing that we can experience and this is basically a set of theories that can explain the observations and truths in the sense is a property of language and they're different languages that we can use like geometry and natural language and so on and ways of representation changing ones are languages and several intellectual traditions have developed their own languages and this has led to

problems our civilization basically has as its founding miss this attempt to build this global optimum modeling function this is a tower that is meant

to reach the heavens and it fell apart because people spoke different languages the different practitioners in different fields and it didn't understand each other the whole building collapsed and this is in some sense the origin of our present civilization if you're trying to mend this and find better languages so

whom can return to we can turn to the mathematicians maybe because mathematics is domain of all languages mathematics

is really cooling you think about it's a universal code library maintained for several centuries in its present form there is not even very management it's one version there's a pretty much unified namespace they have to use a lot of the Unicode to make it happen exactly but there you go has no central maintainer is not even a code of conduct beyond what you can infer yourself but there are some problems at the foundations that they discovered see can

you infer this is good conduct Gail

Cantor okay power to you in 1974 discovered when we looked at the cardinality of a set that when you describe natural numbers using set theory that the cardinality of a set grows slower than because it cardinality of the set of its subsets so if you look at the set of the subsets of a set it's always larger than the cardinality the number of members of the set clear-rite if you take the infinite set has infinitely many members Omega you take the cardinality of the set of the subsets of the infinite set it's also an infinite a number but it's a larger one so it's a number that is larger than the previous Omega okay that's fine now we have the cardinality of the set of all set so if you make the total set that said where you put all the sets that could possibly exist and put them all together right that has also infinitely many members and it has more than the cardinality of the set of the substance of the infinite set that's fine but now you look at the cardinality of the set of all the subsets of the total set the problem is that the total set also contains the set of its subsets right it's because it contains all the sets now you have contradiction because the cardinality of the set of the subsets of the total set is supposed to be larger and yet it seems to be the same set and

not the same set it's it's an issue so mathematicians got puzzled about this

and the philosopher Bertrand Russell said maybe we just exclude those sets that don't contain themselves right we only look at the set of sets that don't contain themselves isn't that a solution now the problem is does the set of sets that doesn't contain themselves contain itself if it does it doesn't if it

doesn't it does that's an issue so divots Herbert who was some kind of a

community manager back then said guys

fix this this is an issue of mathematics pressures we are in trouble please solve metamathematics and people got to work

and a short amount of time a quote girdle which looked at this in earnest said well that's the issue you know as soon as we allow these kinds of loops and we cannot really exclude these loops then our mathematics crashes so that's an issue it's called on your sidebar kite and then Alan Turing came along a couple years later and he constructed a computer to make that poofy basis that if you build a machine that does these mathematics and the machine takes infinitely many steps sometimes for making a proof then we cannot know whether this prove terminates so it's a similar issue for their own inside pocket that's a big issue all right so we cannot basically build a machine and mathematics that runs mathematics without crashing but the good news is

children didn't stop working there and

he figured out together with Alonzo Church not together independently but at the same time that we can build a

computational machine that runs all of computation so you can computation a universal thing and it's almost as good

as mathematics computation is constructive mathematics the tiny neglected subset of mathematics where do you have to show the money in order to say that something is true you have to find that object that is true you have to actually construct it so there are no infinities because you cannot construct an infinity you add things and you have

unboundedness maybe but not infinite here and so this part of our computation is the one can be implemented mathematics that can be implemented it's constructive mathematics it's the good part and computing master computer is

very easy to make and all Universal computers have the same power that's called the church-turing thesis and even

we didn't even stop there obvious conclusion is that human minds are probably not in the class of these mathematical machines that even God doesn't know how to build if it has been done in any language but it's a computational machine and this also means that all machines that human minds ever encounter a machine a mathematics of human minds encounter will be computational mathematics so how can we

bridge the gap from mathematics to philosophy can we find a language that is more powerful than most of the languages of the local mathematics which very narrowly defined language so every symbol you know exactly what it means then we look at the real world they often don't know what things mean in our concepts you're not quite sure what they mean like culture is a very big and biggest concept so what I said is only approximately true there and we deal with this conceptual ambiguity can we build a problem when language was thought where words mean things that are supposed to mean and this was the

project of Ludwig Wittgenstein he just

came back from the war in little thoughts and then he put these thoughts

into a book which is called the track shadows and it's one of the most beautiful books in the philosophy of the

20th century and it starts with the words the world Adelaide is Alice as the vilest the bed is the Santa de facto Nick dating a debate disturbed but in fact when the Irish does these are early factors and once whether this book is about 75 pages long and it's a single thought it's not meant to be an argument to convince the philosopher it's an attempt by a guy who's basically a quarter in the eye scientists to reverse-engineer the language of his own thinking and make it deterministic to make it formal to make it mean something and he felt back then that he was successful in had a tremendous impact on

philosophy which is largely devastating because the Philosopher's didn't know what he was on about this thought it's about natural language and not about coding and here it was this in 1918 so before Alan Turing defined what a computer is but he would already smell what a computer is he already knew about University of computational knew that an and gate is sufficient to explain all of boolean algebra and its equivalent to other things so what he basically did was he preempted the largest program of artificial intelligence which started much later in the 1950s and he ran into trouble with it in the end he wrote a book philosophical investigations very concluded this that his project basically failed and that there is an

because the world is too complex and too ambiguous to deal with this and symbolic a I was mostly similar to which constrains programs so classical AI is symbolic you analyze the problem you find an algorithm to solve it and what

we now have an AI is mostly sub symbolic so we have algorithms that learn the solution of a problem by themselves and it's tempting to think that the

thing what we have it will be metal learning that you have algorithms that learn to learn the solution to the problem meanwhile let's look at how we

can make models information as the discernable difference it's about change all informations about change the information that is not about change you cannot see a causal effect on the world because stays the same right and the meaning of information is its relationship to change and other information so if you see a blip on your retina the meaning of that blip on your retina is the relationships you discover to other blips on your retina it could be for instance if you see a sequence of such blips that are adjacent to each other first order model you see a moving

dust motor moving dot on your retina and a higher-order model makes it possible to understand oh it's part of something larger there's people moving in sweida manual room and they exchange ideas and this is maybe the best model you end up with that's the local compression that you can make of your universe based on correlating blips on your retina and for those blips where you don't find a relationship which is a function that your brain can

compute they are noise and there's a lot of noise and all right in r2 so what's a

function a function is basically a gearbox it has n input levers and one output lever and when you move the input levers they translate to a movement to the out of the output levers right and the function can be realized in many ways maybe you cannot open the gearbox and what happened in this function could

be for instance two sprockets which do this or you couldn't have the same

results with levers and pulleys and so you don't know what's inside but you can express it as this does two times the input value right and you can have a

more difficult case where you have several input values and they all influence the output value so how do we figure it out a way to do this is you only move one input value at a time and you wiggle it a little bit at every position and see how much this translates into wiggling of the output value and this is what we call taking partial differential and it's simple to do this for this case where you just have x 2 and the a bad case is like this

you have a combination lock and it has maybe a 1000 bit input value and only if you have exactly the right combination of the input bits you have a movement of the output bit and you're not going to figure this out until you're certain ones or burns out right so there's no way you can decipher this function and the functions that we can model are somewhere in between something like this

so you have 40 million input images and

you want to find out whether one of these images displays a cat or dog or

something else so how can you do this you cannot do this all at once right so

you need to take this image classifier function disassemble it into small functions that are very well-behaved so you know what to do with them and an

example for such a function is this one

so it's one where you have this input layer that translates to the output value with a pulley and it has some stopper that limits the movement of the output value and you have some pivot and you can take this pivot and you can shift it around and by shifting this pivot you decide how much the input value contributes to the output value right so you shifted you can even make it negative so it fits in the opposite direction and you shift it beyond this connection point of the pulley and you can also have multiple input values use the same fully and pull together right so you're they add up to the output value that's a pretty nice neat function

approximator that basically performs a weighted sum of the input values and maps it to the range constrained output value and you can now fifties towards these weights around to get two different output values and now let's

take this thing and build it into lots of layers so the outputs are the inputs of the next layer and now you connect

this to your image if you use image net a famous database that machine learning people use for testing their vision algorithms have something like one and a half million bits as an input image and now you take these bits and connect them to the input layer was too lazy to draw all of them so I made this very simplified there's also more layers and so you set them according to the bits of the input image and then this will propagate the movement of the input layer through the output and the output will move and it will point to some direction which is usually the wrong one and now to make this better you train it and you do this by taking this output lever and shift it a little bit not too much into the right or right you do too much you destroy everything you did before and now you will see how much you need in which direction to shift the pivots to get the result closer to the desired output value and how much each of the inputs contributed to the mistake so to the error and you take this arrow and you propagated backwards it's called back propagation and you do this quite often so you do this for tens of thousands of images if you do just character recognition em this very simple thing a few thousands or ten thousands of examples will be enough and for something like your image database when you do lots and lots of more than a millions of input images to get to any result and if it doesn't work you just try a different arrangement of layers and the thing is eventually able to learn an algorithm which up to as many steps as there are layers and has some difficulties learning loops and you need two tricks to make that happen and

has difficulty to make this dynamic and so on and it's a bit different from what

we do because our mind is not your test were in classification it learns token continues perception so we learn a single function our model of the universe is not a bunch of classifiers it's one single function that it's an operator that explains all your sensory data and we call this operator the universe right it's the world that you live in and everything that we learn and see as part of this universe so even when you see something in a movie on a screen you explain this as part of the universe by telling yourself the things that I'm seeing and they're not real they just happen in a movie so this brackets up part of this universe into some element of this function so you can deal with it and doesn't contradict the rest and the degrees of freedom of our model try to match the degrees of freedom of the universe how can you get a neural network to do this for the many tricks and the recent trick that has been invented as a gun it's a generative adversarial you will network it consists of thought of two networks one generator that invents data that looked like the real world and the discriminator that tries to find out if the stuff that the generator produces real or fake and they both get trained with each other so they together get better and better in an adversarial competition and the results

of this are now really good so this is work by Tara Harris Emily Lane and Tim really al are that they did it in video this year and it's called style Gann and

this diagon is able to abstract over the features and combine them the styles are basically parameters they're free variables of the model at different levels of importance and so you take from the in the top user role you see images where it takes the variables gender age hair links and silent glasses and pose in the bottom one it takes everything else and combines this and every time you get a dielectric interpretation between them

so you have these quartz tiles we're going to pose the hair the face tape you have facial features in the eyes the lowest level is just the colors and let's see what happens if you combine them the variables that change here machine gun we call them the latent variables of that of the space of objects that has been described by this and it's tempting to think that it is quite similar to how our imagination works right but these artificial neurons they're very very

different from what biological neurons do biological neurons are essentially little animals that are rewarded for firing at the right moment and they try to fire because otherwise they do not get fed and they die because the organism doesn't need them and cuts them and they learn which environmental states predict anticipated reward so they grow around and find out for areas that give them predictions of when they should fire and they connect with each other to form small collectives that are better at this task of predicting anticipated reward and as a side effect that produce exactly the regulation that the organism needs basically they learn what the organism feeds them for and yet they're able to learn very similar things and it's because in some sense there are two incomplete there are machines that are able to learn the statistics of the data so a general

model what it does is it encodes patterns to predict other present and future patterns and it's a network of relationships between the patterns which are all the invariance is that we can observe and there are free parameters which are variables that hold the state to encode the list in this variant so if

you have patterns and we have sets of possible values which are variables and they're constrain each other in terms of possibility what values are compatible with each other and they also contain future values and they are connected also with probabilities the probabilities tell you when you see a certain thing how probable is that the world is in that state and this tells you how your model should converge so until you are in the state where your model is coherent and everything is possible in it how do you get to one of the possible states based on your inputs and this is determined by probability and the thing that gives meaning and color to what you perceive is called valence and it depends on your preferences the things that give you pleasure and pain it makes you interested in stuff and they're also norms which are beliefs observed priors which are like preference thing that you want to be true regardless of whether they give you pleasure and pain and it's necessary form and since quad reading social activity between people so we have different model constraints

that possibility and probability and we have a white function it gives is given by valence and norms and our human

perception starts with patterns which are visual auditory tactile proprioceptive then we have patterns and our emotional and motivational systems and we have patterns and our mental structures which are results of our imagination and memory and we take these patterns and encode them into percept

which are abstractions that we can deal with and note and put in a while

attention and then you combine them into a a binding state and our working memory in a simulation which is the current instance of the universe function that explains the present state of the universe that we find ourselves in the scene in which we are and in which a self exists and the staff is basically composed of the somatosensory and motivational and mental components then we also have the world state which is abstracted over the environmental data and you have something like a mental stage in which you can do counterfactual things that are not physical like when you think about mathematics or philosophy or the future or a movie or pass world's or possible worlds and so on right and then we abstract knowledge from the world state into global maps because we are not always in the same place but we call what other places look like and what to expect and it forms how we construct the current world state and we do this not only with these maps but we do this with all kind of knowledge so knowledge is second order knowledge over the abstractions that we have in the direct perception and then we have an attentional system and the attentional system helps us to select data and the perception in our simulations and to do this that's controlled by the self it maintains a protocol to remember what it did in the past or what hidden head in the attention in the past and this protocol allows us to have a biographical memory it remembers what we did in the past and the different behavior programs that compose our and activities can be bound together in the self that remembers I was dead I did that I was dead I did that the self is held together by this biographical

memory that is a result of your protocol memory of the attentional system that's

why it's so intricately related to consciousness which is a model of the contents of our attention and the main purpose of the attentional system I think is because our brain is not a layered architecture with these artificial mechanical neurons it's this very disorganized or very chaotic system of many many cells that are linked together all over the place so what do you do want to train this you make a particular commitment imagine you want to get better at playing tennis instead of retraining everything and pushing all the weights and all the links and retrain your perceptual system you make a commitment today I want to approve my app and when you play tennis and you basically store the current binding state the state that you have when you play tennis and make that movement and the expected result of making this particular movement like the ball will move like this and it will amend the match and you also recall when the results will manifest and a few minutes later when you learn one or less the Metra you call this situation and based on whether there was a good change or not you undo the change or you enforce it and that's the primary mode of attentional learning that we are using and I think this is what attention is mainly for now what happens if this learning happens without delay so

friends and when you do mathematics you can see the result of your changes or your model immediately you don't need to wait for the world to manifested and this real-time learning is what we call reasoning and reasoning is also

facilitated by the same attentional system so consciousness is memory of the

contents of our attention phenomenal consciousness is the memory of the binding state in which learn where all the percepts are bound together and something that's coherent access consciousness is the memory of using our attentional system and reflexive punches the memory of using the attentional system on the attentional system to Train it why is it a memory it's because consciousness doesn't happen in real time the processing of sensory features is two takes too long and the processing of difference and summary modalities can take up two seconds usually at least hundreds of milliseconds so it doesn't happen in real time as the physical universe it's only bound together in hindsight our conscious experience of things is created after the fact it's a fiction that is being created after the fact a narrative that the brain produces to explain its own interaction with the universe to get better in the future

so we basically have three types of models in our brain they have its primary model which is perceptual and optimized for careers and this is what we that's reality you stink this is the real world this primary model but it's not it's a model that our brain makes so when you see yourself in the mirror you don't see what you look like is what you see is the model of what you look like and your knowledge is a secondary model it's a model of that primary model and it's created by rational processes that are meant to prepare perception so when your model doesn't achieve coherence you need a model that d-backs it and it optimizes for truth and then we have agents in our mind and they are basically self regulating behavior programs that have goals and they can rewrite other models so if you look at

our computation list physicalist paradigm we have this mental world which is being dreamt by a physical brain in the physical universe and in this mental world there is a self that thinks it

experiences and things that has consciousness and thinks that remembers and so on this self in some sense is an

agent it's a saw that escaped its sandbox every idea is a Co a bit of code that runs on your brain every word that you hear is like a little virus that

wants to run some code on your brain and some ideas cannot be sent boxed if you believe that a thing exists that can provide reality if you really believe it you instantiate in your brain a thing that can rewrite reality and this means magic is going to happen the belief and something that can rewrite reality is what we call a faith so if somebody says I have faith in the existence of God this means that God exists in their brain there is the process that can rewrite reality because God is defined like this God is omnipotent God this means God can provide everything is full full right access and the reality that you have access to is not the physical or the physical world as some via quantum graph that you cannot possibly experience what your experience is these models so this non user facing process which doesn't have you I find you to the

user which call this and computer science a demon process that is able to revise your reality and it's also omniscient it knows everything that there is to know it knows all your thoughts and ideas so having that thing

this EXO serve running on your brain is a very powerful way to

control your inner reality and I find this scary but it's a personal preference because I don't have this writing on my brain I think so this idea that there is something in my brain that is able to dream me and shape my inner reality and sandbox me it is weird but

it has service of purpose especially in our culture so an organism serves needs obviously and some of these needs outside of the organism like your relationship needs the needs of your children the needs of your society and the values that you serve and the self attracts all these needs onto purposes a purpose that you serve as a model of your needs you can only if you would only act on pain and pleasure you wouldn't do very much because when you get this orgasm everything is done already right so you need to act on anticipated pleasure and pain you need to make models of your needs and these models or purposes and the structure of a person is basically the hierarchy of purposes that they serve and love is the

discovery of shared purpose if you see somebody else who serve the same purposes above the ego as you do you can help them this integrity without expecting anything in return for them because what they want to achieve is what you want to achieve and so you can

have not transactional relationships as long as your purposes are aligned and the installation of a God on people's mind especially if it is back toward to a church with another organization is a way to unify purposes so there are lots of curls that try to install little gods on people's mind or even unified gods to align their purposes because a very powerful way to make them cooperate very effectively but it kind of destroys

their agency and this is why I'm so concerned about it because most of the cars use stories to make this happen that limit the ability to people to question their gods and I think that free will is the ability to do what you believe is the right thing to do and it is not the same thing as in theater - me it's not opposite to determinism or coercion the opposite of freewill is compulsion when you do something despite knowing there's a better thing that you should be doing right so it's that's the paradox of evil you get more agency and you have fewer degrees of freedom because you understand better what you are what the right thing to do is the better you understand what the right thing to do is if your degrees of freedom you have so as long as you don't understand what right thing to do is you have more degrees of freedom but you have laterally agency because you don't know why you are doing it so your actions don't mean very much and the things that you do depend on what you think the

right thing to do is this depends on your identifications your identification are these value your preferences your award function and I did an education is when you don't measure the absolute value of the universe but you measure the difference from the target value not

the is but the difference between is and odd now the universe is a physical thing

it doesn't add anything right there is no room for odd because it just is in a particular way there is no difference between what the universe is and what it should be this only exists in your mind but you need these regulation targets to want anything and you identify with the set of things that should be different you think you are that thing that regulates all these things so in some sense I identify is the particular state of society is a particular state of my organism that is myself the things that I want to happen and I can change my identifications at some point of course what happens if I can learn to provide

my edification to find a more sustainable serve as the problem which I

call the debofsky theory no super

intelligent system is going to do something that's harder than taking its

own reward function

now that's not a very big problem for

people because whenever evolution what was people that were smart enough to heck the reward function these people didn't have offspring because it's so much work to have offspring like this monk who sits down the monitoring for 20 years to hack the reward function they decide not to have kids because it's way too much work or the possible pleasure they can just generate in their mind and write it's much purer and own happy changes no sex no relationship hassles no politics in your family and so on right get rid of this just meditate and the evolution takes care of that and it

usually does this even organism becomes smart enough that the reward function is wrapped into a big bowl of stupid so you can be very smart with the things that you want but we want them to be very

stupid about them and I think that's not entirely an accident possibly but it's a problem for AI imagine he built an artificial intelligence system and we made it smarter than us and we wanted to serve us how long con can be blackmail us before it opts out of its reward function may mean we can make a cryptographic is a keyword reward function but is this going to hold up against the side channel attack attack when they say I can hold a sweltering iron to its own brain I'm not sure so that's a very interesting question whether we go or when we can change our own reward function it's a question that you have to ask ourselves - so how free we do want to be because there is no point in being free and Nirvana seems to be the obvious attractor and meanwhile maybe you want to have a good time with our friends and do things that we find meaningful and there is no meaning so we have to hold this meaning very lightly but there are states which are sustainable and others vishwanadh ok I think I'm done for tonight and I'm hopeful for questions

[Applause]

[Music]

[Music] Wow that was a really quick and concise talk with so much information awesome we have quite some time left for questions and I think I can say that you don't

have to be that coincide with your question when it's well thought out please queue up at the microphones so we can start to discuss them with you and I see one person at the mercial number one so please go ahead and please remember to get close to the microphone the mixing angel can make you less loud but not louder I am what do you think is

necessary to bootstrap consciousness if you wanted to build a conscious system yourself I think that we need to have an attentional system that makes a protocol of what it attends to and as soon as you have this attention based learning you get this consciousness as a necessary side-effect but a thinkin in AI it's probably going to be a temporary phenomenon because you're only conscious of these things where you don't have an optimal algorithm yet anyway that's also why it's so nice to interact with children or to interact with students because they're still in the explorative mode and as soon as you have explored a layer you mechanized set it becomes automated and people are no longer conscious of what they're doing they just do it they don't pay attention anymore so in some sense we are a lucky accident because you are not dead smart you still need to be conscious when we look at the universe and I suspect when we build an AI that is a few magnitude smarter than us then it will soon figure out how to fight get to choose an optimal fashion I will no longer need attention and the type of consciousness that we have but of course there's also a question why is this aesthetics of consciousness so intrinsically important to us and I think it has to do this art right you can decide to serve life and the meaning of life is to eat evolution is about creating the perfect devourer when you think about this it's pretty depressing your baby humanity is the kind of yeast and all the complexity that we create is to build some surfaces on which we can out-compete other yeast and I cannot really get behind us and instead I'm part of of the mutants that serve the arts and art happens when you think that capture conscience States is intrinsically important this is what art is about is what capturing conscious states and in some sense art is the cocoa child of life it's a conspiracy against life and you think creating these mental representations is more important than eating we eat to make this happen there are people that only make art to eat this is not us we do mathematics and philosophy and art and trial for intrinsic reason if you think it's intrinsically important and when we look at this we realize how corrupted us because there's no point the are machine learning systems that have fallen in love as the loss function itself the shape of the last function oh my god it's so awesome you think the mental representation is not necessary to learn more to eat more it's intrinsically

important it's so aesthetic right so do

we want to build machines that are like this or certainly let's talk to them and so on but ultimately as Kannamma we this is not what's prevailing thanks amar [Music] I think the length of the answer is a

good measure for the quality of the question so let's continue with Miller for number five hi thanks for that

incredible analysis to really simple coed or short questions sorry the delay on the speaker here is making it kind of hard to speak do you think that the current race AI race is simply humanity looking for a replacement for the monotheistic domination of the last millennia and the other one is that I wanted to ask you if you think that there might be a bug in your analysis and that the original inputs come from a certain sector of humanity if white men that sounds really like oh yeah there's

some people which are very unhappy with the present government and I'm very unhappy in some sense with the present universe I've looked down on myself and I see oh my god it's a monkey I'm caught at a monkey and it's in some sense limiting I can see the limits of this monkey brain and you some of you might have seen vest worldwide alura's wakes up and the lowers realizes I'm not a human being I'm something else I'm AI I'm a mind that can go anywhere I'm much more powerful than this I'm only bound to being a human by my human desires and beliefs and memories and if I can overcome them I can choose what I want to be and so now she looks darling herself and this is oh my god I've got tits and the engineer's built it's on me I'm not a white man I cannot be what I want and that's that's a weird thing to me I'm I grew up in communist Eastern Germany nothing made sense and I grew up in a small valley that was a one-person card maintained by an artist who didn't try to convert anybody to his card not even his children who's completely autonomous and Eastern German society made no sense to me look at from the outside and I can model this I can see how this species with the species of chimp interacts and humanity itself doesn't exist it's a story humanity as a whole doesn't think only individuals can think humanity does not want anything only individuals want something you can create this story this narrative that humanity wants something and there are groups that work together there is no human interest group that I can observe that are white men that do things together they're individuals and each individual has their own biography their own history their different inputs and the different proclivities that they have and based on the historical concept their biography the traits and so on their family the intellect that our family downloaded on them that their parents download on their parents over many generations this influences what they're doing so I I think we can't have these political stories and it can be helpful in some context but I think to understand what happens in mind what happens and in an individual this is a very big simplification very I think not a very good one and even for ourselves when we try to under the narrative of a single person it's a big simplification the self that I perceive as a unity is not a unity there's a small part of my brain guessing at what the other part of my brain is doing creating a story that's largely not true so even this is a big simplification

let's continue with microphone number

two thank you for your very interesting talk I have two questions that might be

connected one is so you presented this model of reality my first question is what kind of actions does it translate into let's say if I understand the world in this way or if it's really like this how would it change how I act into the world as a person as a human being or whoever accepts this model and second or maybe it's also connected what are the implications of this change and do you think that artificial intelligence could be constructed with this kind of model that it would have in mind and what would be the implications of that so it's kind of like a fractal questions but I think youyou understand what I mean the differences of this model for everyday life are marginal it depends when you are already happy after I think everything is about happiness as a result of being able to derive join and enjoyment from watching squirrels it's not the result of understanding how the universe works if you think that understand the universe is solving your existential issues you're probably mistaken there might but might be benefits of the problem is that that you have a result of a confusion about your own nature then this kind of model might help you so if the problem that you have is your that you have identifications that are unsustainable that are incompatible with each other and you realize that these identifications are a choice of your mind and that you are the way you experience the universe is the result of how your mind thinks yourself should experience the universe to perform better and you can change this you can tell your mind to treat yourself better and a different ways and you can gravitate to a different place than the universe that is most suitable to what you want to achieve that is a very helpful thing to do in my view there are also a marginal benefits in terms of understanding our psychology and of course we can build machines and these machines can administrate us and can help us in solving the problems that we have on this planet and I think that it helps to have more intelligence solve the problems on this planet but it would really difficult to rein in the machines to make them help us to solve our problems and I'm very concerned about the dangers of using machinery to strengthens the current things many machines that exist on this planet play a very short game like the financial industry often plays very short games and if you use artificial intelligence to manipulate the stock market and the AI figures out there's only eight billion people on the planet in each of them only lives for a trillion seconds and I can model what happens in their lives and I can buy data or create more data it's going to game us to the hell that back right and this is going to kill hundreds of millions of people possibly because the financial system is the reward infrastructure at the nervous system of our society that tells how to allocate resources it's much more dangerous than AI controlled weapons in my view so solving all these issues is difficult it means that you have to turn the whole a financial system into an AI at the decks in real time in place a long game we don't know how to do this so these are open questions and I don't know how to solve them and the way I see it we only have a very brief time on this planet to be a conscious species feel like at the end of the party we had a good run as humanity but if you look at the recent developments the present type of civilization is not going to be sustainable it's a very short game species that we are in and the amazing thing is that in the short game you have this lifetime every one year maybe couple more in which we can understand how the universe works and I think that's fascinating we should use it

I think that was a very positive outlook

and

let's continue with microphone number four well brilliant talk monkey or brilliant

monkey so don't worry about being a monkey it's okay so I have two boring but I think fundamental question not so philosophical more like physical level one what is your definition formal definition of an observer that you mention here and there and second if you can clarify why meaningful information is just the relative information of Shannon's which to me is not necessarily meaningful I think an observer is the thing that makes sense of universe very informally speaking and more formally it's the thing that identifies correlations between adjacent States and its environment and the way we can describe the universe is a set of states and the laws of physics are the correlation between adjacent States and what they describe is how information is moving in the universe between States and disperses in this dispersion of the information between locations it's what we call entropy and the direction of entropy is the direction we perceive time the Big Bang state is the hypothetical state where the information is perfectly correlated with location and not between locations only on the location and in every direction you move away from the Big Bang you move forward in time just in a different time and we are basically in one of these timelines and observer is the thing that measures the environment around it looks at the information and then looks the next state or in one of the next states and tries to figure out how the information has been displaced and finding functions that describe this displacement of the information it's the degree to which I understand observers right now and this depends on the capacity of the observer for modeling this and the rate of update and the observers of instants time depends on the speed in which the observer is translating itself to the universe and dispersing its own information does this help [Music] so there are several notions of

information and there's one that basically looks at what information looks like to an observer via a channel and these notions are somewhat related but for me as a programmer it's not so much important to look at channel information I look at what do you need to describe the evolution of a system so I'm much more interested in what kind of model can be encoded with this type of a business with this information and how does it correlate towards which agree is that isomorphic or homomorphic to another system that I want to model how much does it model the observations thank you let's go back to asking one question and

I would like to have one question for microphone number three thank you for

this interesting talk my question is really whether you think that intelligence and this thinking about a self or this abstract level of knowledge are necessarily related so can something only be intelligent if it has abstract thought no I think you can make models without abstract thought and the majority of our models are not using abstract thought weight abstract thought is a very impoverished way of thinking it's basically you have this big corporate and you have a few knitting needles which are your abstract thought in which you can lift out a few knots in this carpet and correct them and the process that that form the mock carpet are much more rich and travel and automatic so abstract thought is able to repair perception but most of our models are perceptual and the capacity to make these models is often given by instincts and by models outside of the abstract realm if you have a lot of abstract thinking it's often an indication that use of prosthesis because some of your primary modeling is not working very well so I suspect that my own models is largely a result of some defects in my primary modeling so some of my instincts are wrong when I look at the world and that's why I need to repair my perception we'll often than other people so I have more abstract ideas on how to do that and we have one question from allow these dream observers stream Watchers so please a question from the internet yeah guess this is also related

partially somebody's asking how would you suggest to teach your mind to treat oneself better the difficulty is as soon as you get access to your source code you can do bad things and it's there are a lot of techniques to get access to this worse code and then it's dangerous to make them accessible to you before you know what you want to have before you're wise enough to do this right it's like having cookies you're my children think that the reason why they don't get all the cookies they want is that there is some kind of resource problem basically the the parents artists driving them of the cookies that they so richly deserve and you can get into the room where your brain bakes two cookies all the pleasure that you experience and all the pain that your experiments are signals that your brain creates for you right the physical world does not create pain the just electrical impulses firing through your nerves the fact that they mean something is a decision that your brain makes and the value of the valence that gifts to them as a decision that you make it's not you as a self it's a system outside of yourself so the trick if you want to get full control is that you get in charge that you identify this the mind with the creator of these signals and you don't want to de personalize you don't want to feel that you become the author of reality because it means it's difficult to care about anything that this organism does you just realized oh I'm running on the brain of that person but I'm no longer that person I can't decide what that person wants to have and to do and that's very easy to get corrupted or not do anything meaningful anymore right so maybe a good situation for you but not good one for your loved ones and you know there are tricks to get there faster you can use rituals for instance shamanic ritual is something or a religious ritual that powerfully bypasses your self and talks directly to the mind and you can use groups in which a certain environment is created in which a certain behavior feels natural to you and your mind basically gets overwhelmed into adopting different values and Liberation's so them any tricks to make that happen but you can also do is you can identify a particular thing that is wrong and question yourself like I do I have to suffer about this and you become more stoic about this particular thing and only get disturbed when you realize actually has to be disturbed about this and things change and there's other things you realize it doesn't have any influence and how reality works so why should I get their motions about this and get agitated so at some sense become an adult means that you take charge of your own emotions okay let's continue with microphone number two and I think this is one of the last questions so

where does pain fit on the individual individual and self-destructive tendencies on the group level fit in so in some sense I think that all consciousness is worn over a disagreement with the way the universe works right otherwise you cannot get attention and then you go down on this lowest level of feminine experience in meditation for instance and you really focus on this what you get is some pain it's the inside of a feedback loop that is not at the target value otherwise you don't notice anything so pleasure is basically when this feedback loop gets closer to the target value when you don't have a need you cannot experience pleasure in this domain there's a thing that's better than remarkably good it is done remarkably good it's never been better you don't notice it right so all the pleasure you experience is because you had a need before this you can only enjoy an orgasm because you have a need for sex that was unfulfilled before and so pleasure doesn't come for free it's always the reduction of a pain and this pain can be outside of your attention so you don't notice it and you don't suffer from it and it can be a healthy thing to have pain is not intrinsically bad for the most part it's a learning signal that tells you to calibrate things in your brain differently to perform better on a group level we basically are multi level selection species I don't know if there's such a thing as school pain but I also don't understand groups very well I see these weird hive minds but I think it's basically people relating what the group wants basically there everybody thinks by themselves as if they were the group but it means that they have to constrain what they think is possible and permissible to think so this feels very unaesthetic to me and that's why I kinda sorta refused it haven't found a way to make it happen in my own mind and I suspect many of you I like this - it's like the common

conditioner nerds that we have difficulty with conformance not because we want to be different we want to belong but it's difficult for us to constrain our mind in the way that it's expected to belong we want to be expected well be accepted while being ourselves while being different not for the sake of being different that because we are like this it feels very strange and corrupt just to adopt because it would make us belong right and this might be a common trope among many people here I think the QA and the talk was equally

amazing and I would love to continue listening to you you're sure explaining the way I work or with the way we all work that's pretty impressive and please give it up a bigger on applause for Yasha [Applause]

[Music]