Kind: captions
Language: en
the following is a conversation of Yoshi
Bach VP of research at the AI foundation
with a history of research positions at
MIT and Harvard Yosha is one of the most
unique and brilliant people in the
artificial intelligence community
exploring the workings of human mind
intelligence consciousness life on Earth
and the possibly simulated fabric of our
universe I could see myself talking to
Yoshi many times in the future quick
summary of the ads to sponsors Express
BPM and cash app please consider
supporting the podcast by signing up at
expressvpn comm slash FlexPod and
downloading cash app and using code lex
podcast this is the artificial
intelligence podcast if you enjoy it
subscribe on youtube review it with five
stars in a podcast supported on patreon
or simply connect with me on Twitter at
Lex Friedman since this comes up more
often than I ever would have imagined I
challenge you to try to figure out how
to spell my last name without using the
letter E and it'll probably be the
correct way as usual I'll do a few
minutes of ads now and never any ads in
the middle that can break the flow of
the conversation this show sponsored by
expressvpn
get it at expressvpn comm slash flexpod
to support this podcast and to get an
extra three months free on a one-year
package I've been using expressvpn from
many years I love it I think expressvpn
is the best VPN out there they told me
to say it but
think it actually happens to be true it
doesn't log your data
it's crazy fast and it's easy to use
literally just one big power on button
again for obvious reasons it's really
important that they don't log your data
it works on Linux and everywhere else
too shout out to my favorite flavor of
Linux Ubuntu mottai 2004 once again get
it at expressvpn comm slash FlexPod to
support this podcast and to get an extra
three months free on a one-year package
this show is presented by cash app the
number one finance app in the App Store
when you get it
use code Lex podcast cash app lets you
send money to friends buy Bitcoin and
invest in the stock market with as
little as one dollar since cash app does
fractional share trading let me mention
that the order execution algorithm that
works behind the scenes to create the
abstraction of the fractional orders is
an algorithmic marvel so big props the
cash app engineers for taking a step up
to the next layer of abstraction over
the stock market making trading more
accessible for new investors and
diversification much easier so again if
you get cash out from the App Store
Google Play and use the collects podcast
you get ten dollars in cash wrap will
also donate ten dollars to first an
organization that is helping advanced
robotics and STEM education for young
people around the world and now here's
my conversation with the OSHA buck as
you've said
up in a forest in East Germany just as
what we're talking about off mic to
parents who were artists and now I think
at least to me you become one of the
most unique thinkers in the AI world so
can you try to reverse engineer your
mind a little bit
what were the key philosophers
scientists ideas maybe even movies or
just realizations that a impact on you
when you're growing up that kind of led
to the trajectory or what the key sort
of crossroads in the trajectory of your
intellectual development my father came
from a long tradition of architects
distant branch of the family and so
basically he was technically a nerd and
nerds need to interface in society with
non-standard ways sometimes I define a
nerd as somebody who thinks that the
purpose of communication is to submit
your ideas to peer review and normal
people understand that the primary
purpose of communication is to negotiate
alignment and these purposes tend to
conflict which means that nerds have to
learn how to interact with society at
large who is the reviewer in the nerd
view of communication everybody who will
consider to be a peer so whatever
happiest individual is to around well
you would try to make him or her the
gift of information okay so you're now
by the way my research will have Mellon
for me so you're architect or artist I
study architecture but basically my
grandfather made the wrong decision he
married an aristocrat and I was drawn
into a window into the war and he came
back after 15 years so basically my
father was not parented by a nerd by but
by somebody who tried him tell him what
to do and expected him to do what he was
told and he was unable to he's unable to
do things if he's not intrinsically
motivated so in some sense my
grandmother
broke her son and her son responded by
when he became an architect
to become an artist
so he bought wounded bizarre
architecture he built houses without
right angles he'd be lots of things that
didn't work in more brutalist traditions
of eastern Germany and so he bought an
old water mill moved out of the
countryside and did only what he wanted
to do which was art eastern Germany was
perfect for p'jem because you had
complete material safety put was heavily
subsidized Oskar was free you didn't
have to worry about rent or pensions or
anything so as a socialized communist
side yes and the other thing is it was
almost impossible not to be in political
disagreement with your government which
is very productive for artists so
everything that you do is intrinsically
meaningful because it will always touch
on the deeper currents of society of
culture and be in conflict visit and
tangent visit and you will always have
to define yourself and with respect to
this so what impact did your father this
outside the bar outside the box thinker
against the government against the world
artists have it was not a thinker he was
somebody who only got self-aware to the
degree that he needed to make himself
functional so in some sense he's it was
also late 1960s and he was in some sense
a hippie so he became a one-person cult
he lived out there in his kingdom he
built big sculpture gardens and he
started many avenues of art and so on
and convinced a woman to live with him
she was also an architect and she adored
him and decided to share her life with
him and I basically grew up in a big
cave full of books
I'm almost feral and I was bored out
there it was very very beautiful very
quiet and quite lonely so I started to
read and by the time I came to school
I've read everything until fourth grade
and then some and there was not a real
way for me to relate to the outside
world and I couldn't quite put my finger
on why and today I know it was because I
was a nerd obviously and it was the only
nerd around so there was no other kids
like me and there was nobody interested
in physics or computing or mathematics
and so on and this village school that I
went to was busy in high school kids
were nice to me I was not beaten up but
I also didn't make many friends or but
relationships that only happened and
starting from ninth grade when I went to
a school for mathematics and physics do
you remember any key books from my
cigarette everything so I went to the
library and I've worked my way through
the children's and young adult sections
and then I read a lot of science fiction
for instance Danny's laflamme basically
the great author of cybernetics has
influenced me back then I didn't see him
as a big influence because everything
that he wrote seem to be so natural to
me and it's only later that I contrasted
it with what other people wrote another
thing that was very influential on me
were the classical philosophers and also
the Tudor of Romanticism so German
poetry and art cross two heads off and
Heine and up to Heather and so on that's
a love Heather so at which point is a
classical philosophers end at this point
or in the 21st century what's what's the
latest classical philosopher does this
stretch through even as far as Nietzsche
or just I were talking about Plato and
there's that one I think that Nietzsche
is the classical equivalent of a
poster yeah but he's not so much tolling
others he's trolling himself because he
was at odds with the world largely his
romantic relationships didn't work out
he got angry and he basically became a
nihilist and his nether is not a
beautiful way to be isn't until I show
it to cast him be trolling yourself to
be in that conflict in that no Venice at
some point you have to understand the
comedy of your own situation if you take
yourself seriously and you are not
functional
it ends in tragedy as I did for
Nietzsche by thinking you think he took
himself too seriously in the in that
tension and as we apply the same thing
and in HESA and so on this step involves
two enormous classic a dollar sense
where you basically feel misunderstood
by the world and you don't understand
that all the misunderstandings are the
result of your own lack of
self-awareness because you think that
you are a prototypical human and the
others around you should behave the same
way as you expect them based on your
innate instincts and it doesn't work out
and you become a transcendentalist to
deal with that and so it's very very
understandable
great sympathies for this to the degree
that I can have sympathy for my own
intellectual history but out of it was
an intellectual a life well-lived a
journey well traveled is one where you
don't take yourself seriously from now I
think that you are neither serious or
not serious yourself because you need to
become unimportant as a subject that is
if you are if a lot of a belief is not a
verb you don't do this for the audience
you don't do it for yourself you have to
submit to the things that are possibly
true and you have to follow wherever
your inquiry leads but it's not about
you and has nothing to do with you
so do you think then people like Iran
believed sort of an idea of there's a
objective truth so GE what's your sense
in the philosophical well if you remove
yourself a subjective from the picture
you think it's possible to actually
discover ideas that are true or we just
in a measure relative concepts they're
an either true nor false it's just a
giant mess you cannot define objective
truth without understanding the nature
of truths in the first place so what
does the brain mean by saying that it
covers something as truth so for
instance a model can be predictive or
not predictive then there can be a sense
in which a mathematical statement can be
tool because it's defined as true under
certain conditions so it's basically a
particular state that a variable can
have an assembled game and then you can
have a correspondence between systems
and talk about truth which is again a
type of model correspondence and that
also seems to be a particular kind of
ground rules so for instance you're
confronted with the enormity of
something existing at all right that's
standing when you realize something
exists rather than nothing and this
seems to be true right there is two EPs
absolute truth in the fact that
something seems to be happening
yeah that that to me is a showstopper I
could just think about that idea and be
amazed by that idea for the rest of my
life and not go any farther because I
don't even know the answer to that why
does anything exist at all well the
easiest answer is existence is the
default right so this is the lowest
number of bits that you would need to
encode this whose answer who brought the
simplest answer sympathisers that
existence is that if
what about non-existence I mean that
seems non-existence might not be a
meaningful notion in the sense so in
some sense if everything that can exist
exists for something to exist it
probably needs to be implementable the
only thing that can be implemented as
finite automata so maybe the whole of
existence is the superposition of all
finite automata and we are in some
region of the fractal that has the
properties that it can contain us what
does it mean to be a superposition of
fine and vanish superposition of all
power like all possible rules imagine
that every automaton is basic an
operator that acts on some substrate and
as a result you get emergent patterns
most a substrate is no idea to know so
it's based on substrate it's something
that can store information something
that can store information there is a
counter something that can hold state
still doesn't make sense to me the why
that exists at all I could just sit
there with a with a beer or or a vodka
and just enjoy effect monitoring the why
may not have a why this might be the
wrong direction so a skin to this so
there could be no relation in in the Y
direction without asking for a purpose
or for a course it doesn't mean that
everything has to have a purpose or
cause right so we mentioned some
philosophers in that early just taking a
brief step back into in today okay so we
asked ourselves when did classical
philosophy end I think what Germany
largely ended was the first revolution
that's basically even which was that
this was when we ended the monarchy and
started a democracy and at this point we
basically came up with a new form of
government that didn't have a good sense
of the this new organism that society
wanted to be and in a way it decapitated
the universities so the university spent
on so modernism like a headless chicken
at the same time democracy failed in
Germany and we got fascism as a result
and it burnt down things in the similar
way as Stalinism burnt down intellectual
traditions in Russia and Germany boast
Germany's have not recovered from this
Eastern Germany at this bog or a
dialectic materialism and western
Germany didn't get much more edgy that
Hamas so in some sense both countries
lost their intellectual traditions and
killing off and driving out
Jules didn't help yeah so that was the
end that was the end of really rigorous
well you would say it's classical
classical philosophy is also this thing
that in some sense the low-hanging foods
in philosophy were mostly wrapped and
the last big things that we discovered
was the constructivist turn in
mathematics so to understand that the
parts of mathematics that work are
computation it was a very significant
discovery in the first half of the 20th
century and it hasn't fully permeated
philosophy and even physics yet
physicists checked out the core
libraries from mathematics before
constructivism became universal what's
constructivist and what are you French
girls incompleteness theorems that kind
of discuss so it basically girdle
himself I think didn't get it yet
Hilbert could get it Hilbert saw that
for instance a country's set theoretic
experiments and mathematics led into
contradictions and he noticed that mr.
current semantics we cannot build a
computer in mathematics that runs
mathematics without crashing and a good
proof could prove this and so what
Google could show is using classical
mathematical semantics you run into
contradictions and because gödel
strongly believed in these semantics and
one then in what he could observe and so
on he was shocked
it basically shook his well to the core
because in some sense he felt that the
world has to be implemented in classical
mathematics and for Turing it wasn't
quite so bad I think that you were in
could see that the solution is to
understand the quest mathematics was
computation all along which means you're
for instance PI and classical
mathematics is a value it's also a
function but it's the same thing in a
computation a function is only a value
of n you can compute it and if you
cannot compute the last digit of pi you
only have a function you can plug this
function into your local Sun let it run
until the Sun burns out this is it this
is the last digit of pi you will know
but it also means that it can be no
process in the physical universe or in
any physically realized computer that
depends on having known the last digit
of pi yes which means there are parts of
physics that are defined in such a way
that cannot strictly be true because
assuming that this could be true leads
under contrary
actions so I think putting computation
at the center of the the worldview is
actually the right way to think about it
yes and Wittgenstein could see it and
Wittgenstein basically preempted the
largest program of AI that Minsky
started later like thirty years later
Turing was actually a pupil of Vidkun
Stein and really I didn't know there's
any connection if it can stand even
cancel some classes venturing was not
present because he thought it was not
worth spending the time if you read the
attract address it's a very beautiful
book but capacity one salt on 75 pages
it's very non typical for philosophy
because it doesn't have arguments in it
and it doesn't have references in it
it's just one thought that is not
intending to convince anybody hisses
says it's mostly for people that had the
same insight as me just spell it out and
this insight is there is a way in which
mathematics and philosophy ought to meet
mathematics tries to understand the
domain of all languages by starting with
those that are so form Aliza bulette you
can prove all the properties of the
statements that you make but the price
that you pay is that your language is
very very simple so it's very hard to
say something meaningful in mathematics
yes and it looks complicated to people
but it's far less complicated than what
our brain is casually doing all the time
it makes sense of reality and philosophy
is coming from the top so it's mostly
starting from natural languages which
vaguely defined concepts and the hope is
that mathematics and philosophy can meet
at some point and Wittgenstein was
trying to make them meet and he already
understood that for instance you could
express everything Western and calculus
that you could produce the entire logic
to NAND gates as we do in all modern
computers so in some sense he already
understood - and universality before
touring spelled it out I think he when
he wrote the Tractatus he didn't
understand yet that the idea was so
important and significant and I suspect
then when curing wrote it out nobody
cared that much your chewing was not
that famous when he lived it was mostly
his work in decrypting the German codes
that made him famous and or gave him
some notoriety but this same status that
he has to computer science right now in
the eye is something that I think he
could acquire later it's kind of
interesting and do you think of
computation and computer science and you
represent that to me is maybe that's the
modern-day you in a sense are the new
philosopher by sort of the computer
scientist who dares to ask the bigger
questions that philosophy originally
started is the new philosophy is the new
philosopher certainly not me I think I
mostly the oldest child that grows up in
a very beautiful Valley and looks at the
world from the outside and tries to
understand what's going on and my
teachers tell me things and they largely
don't make sense right so I have to make
my own models I have to discover the
foundations of what the others are
saying I have to try to fix them to be
charitable I try to understand what they
must have thought originally or what
their teachers or their teachers
teachers must have thought until
everything are lost in translation and
how to make sense of the reality that we
are in and whenever I have an original
idea
I'm usually late to the party by say 400
years and the only thing that's good is
that the parties get smaller and smaller
the older I get and the more I explore
the part the party gets smaller and more
exclusive and more exclusive so it seems
like one of the key qualities of your
upbringing was that you are not tethered
whether it's because your parents or in
general maybe you're something within
your within your mind some genetic
material you were not tethered to the
ideas of the general populace which is
actually a unique property we're kind of
throughout you know the education system
and whatever from that education system
just existing in this world forces
certain sets of ideas onto you can you
uh disentangle that why were you why are
you not so tethered even in your work
today
you seem to not care about perhaps a
best paper in Europe's right being
tethered to particular things that
current today in this year people seem
to value as a thing you put on your CV
and resume you're a little bit more
outside of that world outside of the
world of ideas that people are
especially focusing the benchmarks of
today the things what
can you disentangle that because I think
that's inspiring and if there were more
people like that we might be able to
solve some of the bigger problems that
sort of AI dreams to solve and that's a
big danger in this because in a way you
are expected to marry into an
intellectual tradition and visit this
tradition into a particular school if
everybody comes up with their own
paradigms the whole thing is not
cumulative as an enterprise right so in
some sense you need a healthy balance
you need paradigmatic thinkers and you
need people that work within given
paradigms basically sciences today to
find themselves largely by methods and
it's almost a disease that we think as a
scientist somebody who was convinced by
the guidance counselor that they should
join a particular discipline and then
they find a good mentor to learn the
right methods and then they are lucky
enough and privileged enough to join the
right team and then they will their name
will show up on influential papers but
we also see that there are diminishing
returns with this approach and when our
field computer science day I started
most of the people that joined this
field had interesting opinions and
today's thinkers and AI either don't
have interesting opinions at all or
these opinions are inconsequential for
what they actually doing because what
they're doing is they apply the
state-of-the-art methods with a small
epsilon and this is often a good idea if
if you think that this is the best way
to make progress and for me it's first
of all very boring if somebody else can
do it why should I do it right if if the
current methods of measuring learning
lead to strong AI why should I be doing
it right well just wait and hold that
done and wait until they do this on the
beach or read interesting books or write
some and have fun but if you don't think
that we are currently doing the right
thing if we are missing some
perspectives then it's required to think
outside of the box it's also required to
understand the boxes but it's it's
necessary to understand what worked and
what didn't work and for what reasons so
you have to be willing to ask new
questions and design new methods
whenever you want to answer them and you
have to be willing to dismiss the
existing methods
if you think that they're not going to
give the right answers it's very bad
career advice to do that so maybe to
briefly stay for one more time in the
early days one would you say for you was
the dream before we dive into the
discussions that we just almost started
one was the dream to understand or maybe
to create human level intelligence born
for you I think that you can see AI
largely today as advanced information
processing if you would change the
acronym of AI and to that most people in
the field would be happy it would not
change anything what they're doing for
your automating statistics and when you
of the statistical models are more
advanced than what statisticians had in
the past and it's pretty good work it's
very productive and the the other aspect
of AI is is philosophical project and
this philosophical project is very risky
and very few people work on it and it's
not clear if it succeeds so first of all
let's this is you you keep throwing a
sort of a lot of really interesting
ideas and I have to pick which ones we
cook with but sort of first of all you
use the term information processing just
information processing as if it's it's
the mirror
it's the muck of existence as if it's
the epitome of a logistic that that the
entirety the universe may be information
processing it consciousness the
intelligence might be information
problem so that maybe you can comment on
if that's if the advanced information
processing is is a limiting kind of
realm of ideas and then the other one is
would II mean by the philosophical
project so I suspect that general
intelligence is the result of trying to
solve general problems so intelligence I
think is the ability to model it's not
necessarily goal directed rationality or
something many intelligent people are
bad at this but it's the ability to be
presented with a number of patterns and
see a structure in those patterns and be
able to predict the next set of patterns
right to make sense of things and some
problems are very trainable usually
Intel
serfs control so you make these models
for a particular purpose of interacting
as an agent with the world and getting
certain results but it's the
intelligence itself is in the sense
instrumental to something but by itself
it's just the ability to make models and
some of the problems are so general that
the system that makes them needs to
understand what itself is and how it
relates to the environment so as a child
for instance you notice you do certain
things despite you perceiving yourself
as wanting different things so you
become aware of your own psychology you
become aware of the fact that you have
complex structure in yourself and you
need to model yourself to
reverse-engineer yourself to be able to
predict how you will react to certain
situations and how you deal with
yourself in relationship to your
environment and this process if this
project if you reverse engineer yourself
new relationships or reality in the
nature of a universe that can continue
if you go all the way this is basically
the project of AI or you could say the
project of AI is a very important
component in it the tutoring test in a
way is you ask a system what is
intelligence if that system is able to
explain what it is how it works then you
would should assign it the property of
being intelligent in this general sense
so the test the Turing was administering
in a way I don't think that he couldn't
see it but he didn't express it yet and
the original 1950 paper is that he was
trying to find out other that he was
generally intelligent because in order
to take this test the wrappers of course
you need to be able to understand what
that system is saying and we don't yet
know if we can build an AI have you
don't yet know if you are generally
intelligent basically you win the Turing
test by building an AI yes so it so in a
sense hidden within the Turing test is a
kind of recursive test yes it's a test
on us yeah the Turing test is basically
a test of the conjecture whether people
are intelligent enough to understand
themselves okay but you also mentioned a
little bit of a self-awareness and then
the project of AI do you think this kind
of emergent self-awareness is one of the
fundamental aspects of intelligence so
as opposed to goal oriented ease you
said kind of puzzle solving is
coming to grips with the idea that
you're an agent in the world and I find
that many highly intelligent people are
not very self-aware right so
self-awareness and intelligence are not
the same thing and you can also be surf
aware if you have put priors especially
it without being especially intelligent
so you don't need to be very good at
solving puzzles if the system that you
are already implements the solution but
I do find intelligence so you kind of
mentioned children right it is that the
fundamental project of AI is to create
the learning system that's able to exist
in the world so you kind of drew a
difference between self-awareness and
intelligence and yet you said that the
self-awareness seems to be important for
children so I call this ability to make
sense of the world and your own place
and so to understable make you able to
understand what you're doing in this
world sentience and I would distinguish
sentience from intelligence because
sentience is the possessing certain
classes of models and intelligence is
the way to get to these models if you
don't already have them I see so can you
maybe pause a bit and try to answer the
question that we just said we may not be
able to answer and might be a recursive
meta question of what is intelligence
and I think that intelligence is the
ability to make models the models is I
think it's useful as examples very
popular now neural networks form
representations of large-scale data set
they they form models of those data sets
when you say models and look at today's
new all networks what are the difference
of how you're thinking about what is
intelligent in saying that intelligence
is the process of making models two
aspects tool to this question one is the
representation is the representation
adequate for the domain that we want to
represent and the other one is is the
type of the model that you arrive at
adequate so basically are your modeling
the correct domain
and I think in both of these cases
modern AI is lacking stuff and I think
that I'm not saying anything new you're
not criticizing the field most of the
people that design our paradigms are
aware of that and so one aspect that
you're missing is unified learning when
we learned we'd at some point discover
that everything that we sends this part
of the same object which means we learn
it all into one model and we call this
model the universe so an experience of
the world that we are embedded on it's
not a secret direct via to physical
reality physical reality is a view at
quantum graph that we can never
experience or get access to but it has
this properties that it can create
certain patterns at our systemic
interface to the world and we make sense
of these patterns and the relationship
between the patterns that we discover is
what we call the physical universe so at
some point in our development is a
nervous system we discover that
everything that we relate to and in the
world it can be mapped to a region in
the same three-dimensional space by and
large we now know in physics that this
is not quite true well it's not actually
three-dimensional but the world that we
are entangled is at the level of which
we are entangled this is largely a flat
three-dimensional space and so this is
the model that our brain is intuitively
making and this is I think what gave
rise to this intuition of res extends
a-- of this material world this material
domain it's one of the mental domains
but it's just the class of all models
that relate to this environment this v
dimension of physics engine in which we
are embedded physics engine or embedded
i love that phrase it just slowly pause
so the the quantum graph i think you
called which is the real world which you
can never get access to there's a bunch
of questions i want to sort of
disentangle that maybe one useful one
one of your recent talks i looked at can
you just describe the basics can you
talk about what is dualism
what does idealism what is materialism
what is functionalism and what connects
with you most in terms of because you
just mentioned there's a reality we
don't have access to okay what does that
even mean
and why don't we get access to it only
part of that
one week why can we access it so the
particular trajectory that mostly exists
in the West is the result of our
indoctrination by a card for 2000 years
occult which yes the Catholic cause
mostly yes and for better or worse right
it has created or defined many of the
modes of interaction that we have that
have best created this society but it
has also in some sense scarred our
rationality and the intuition that
exists if you would translate the
mythology of the Catholic Church into
the modern world is that the world in
which you and me interact is something
like a multiplayer role-playing
adventure yes and the money and the
objects that we have in this world this
is all not real or is Eastern
philosophers would say it's my eye it's
just stuff that is it appears to be
meaningful and this embedding in this
meaning and people leave in it is
samsara this it's basically the
identification with the needs of the
mundane secular everyday existence and
the Catholics also introduced the notion
of higher meaning the sacred and this
existed before but eventually the
natural shape of God is the Platonic
form of the civilization that you're
part of it's basically the super
organism that is formed by the
individuals as an intentional agent and
basically the Catholics used relatively
crude mythology to implement software on
the minds of people and get the software
synchronized to make them walk in
lockstep this basically get they get
this got online and you make it
efficient and effective and I think our
God technically is just itself that
spends multiple brains as opposed to
your and myself which mostly exists just
on one brain
right and so in some sense you can
construct yourself functionally as a
function is implemented by brains that
exists across brains and this is a God
with a small G that's one of the if you
look evil Harare kind of talking about
this is one of the nice features of our
brains it seems to that we can all
download the same piece of software I
got in this case and kind of share it
yes you give everybody a spec and the
mathematical constraints that are in
front
to information-processing make sure that
given the same spec you come up with a
compatible structure okay
so that's there's the space of ideas
that we all share and we think that's
kind of the mind and but that's separate
from the idea is from from Christianity
for from religion is that there's a
separate thing between the mind as a
real vault and this real world is the
world in which God exists God is the
quarter of the multiplayer adventure so
to speak and we are all players in this
game and that's dualism usually but it
is because the mental realm is exists in
a different implementation than a
physical realm and the mental realm is
real and a lot of people have this
intuition that there is this real room
in which you and me talk and speak right
now
then comes a layer of physics and
abstract rules and so on and then comes
another real room where our souls are
and our tool form isn't the thing that
gives us phenomenal experience and this
of course a very confused notion that
you would get and it's basically it's
the result of connecting materialism and
idealism in the wrong way so okay I
apologize but I think it's really
helpful if we just tried to define try
to define terms like what is joules and
what is idealism what is materialism for
people done' so the idea of dualism and
our cultural tradition is that there are
two substances a mental substance and a
physical substance and they interact by
different rules and the physical world
is basically causally closed and is
built on a low level causal structures
or the bezier bottom level that is
causally closed it's entirely mechanical
and mechanical in the widest sense
so it's computational there's basically
a physical world in which information
flows around and physics describes the
laws of how information flows around an
adult would you compare it to like a
computer where you have a hardware and
software the computer is a
generalization of information flowing
around basically but join discovered
that there is genuine universal
principle you can define this Universal
machine that is able to perform all the
computations so all these machines have
the same power this this means that you
can always define a translation between
them
as long as they have unlimited memory to
be able to perform each other's
computations so would you then say that
materialism is this whole world is just
the hardware and idealism is this whole
world is just a software why I think
that most idealists don't have a notion
of software yet because software also
comes down to information processing
right so what you notice is the only
thing that is real to you and me is this
experimental world in which things
matter in which things have taste in
which things of color phenomenal content
and so on and you are bringing up
consciousness okay and this is distinct
from the physical world in which things
have values in only in an abstract sense
and you only look at cold patterns
moving around so how does anything feel
like something in this connection
between the two things is very puzzling
to a lot of people of course to many
philosophers so idealism starts out with
the notion that mind is primary
materialism thinks that matter is
primary and so for the idealist the
material patterns that we see a play in
playing out a part of the dream that the
mind is dreaming and we exist in the
mind on a higher plane of existence if
you want and for the materialist there
is only this material thing and that
generates some models and via the result
of these models and in some sense I
don't think that we should understand if
you understand it properly materialism
and idealism is a dichotomy but there's
two different aspects of the same thing
so the via thing is we don't exist in
the physical world we do exist inside of
a store way that the brain tells itself
ok that's it let me uh let my my my
information processing I take they take
that in we don't exist in the physical
world we exist in the narrative basic
your brain cannot feel anything
New York cannot feel anything they're
physical things physical systems are
unable to experience anything but it
would be very useful for the brain or
for the organism to know what it would
be like to be a person and to feel
something yeah so the brain creates a
simulacrum of such a person that it uses
to model the interactions of the
person's the best model of what that
brain this organism thinks it is in
relationship to its
and so it creates that model it's a
story a multimedia novel that the brain
is continuously writing and updating but
you also kind of said that you said that
we kind of exist in the head and that's
alright yes that story yeah what is real
in any of this so like there's a again
these terms are you kind of said there's
a quantum graph I mean what is what is
this whole thing running on then is this
story and is it completely fundamentally
impossible to get access to it because
isn't the story supposed to is in the
brain in a in something in existing in
some kind of context so what we can
identify as computer scientists we can
engineer systems and test our theories
this way that may have the necessary and
sufficient properties to produce the
phenomena that you're observing which is
there is itself in a virtual world that
is generated in somebody's neocortex who
that is contained in the skull of this
primate here and when I point at this
this indexicality is of course wrong but
I do create something that is likely to
give rise to patterns on your retina
that allow you to interpret what I'm
saying right but I both know that the
world that you and me are seeing is not
the real physical world what we are
seeing is a virtual reality generated in
your brain to explain the patterns on
your retina how close is it to the real
world that's kind of the the question is
it when you have when you have like
people like Donald Hoffman let's say
that like that you're really far away
the thing we're seeing you and I now
that interface would have it's very far
away from anything like we don't even
have anything close like to the sense of
what the real world is or is it a very
surface piece of architecture imagine
you look at the Mandelbrot fractal right
this famous thing that when a man would
discover deadlines if you're you see an
overall shape and they're right but you
know if you truly understand it you know
it's two lines of quote it's basically
in a series that is being tested for
complex numbers and in the complex
number plane for every point and for
those for this year is is diverging
you paint this black and where it's
converging you don't and you get the
intermediate colors by taking how far it
diverges yes right this gives you this
shape of this fractal but imagine you
live inside of this fractal and you
don't have access to where you are in
the fractal or you have not discovered
the generator function even right so
what you see is all of all I can see
right now is the spiral and the spiral
moves a little bit to the right is this
an accurate model of reality yes it is
right it is an adequate description is
you know that there is actually no
spiral and the mailboat fractal it only
appears to like this to an observer that
is interpreting things as a
two-dimensional space and then define
certain regularities in there at a
certain scale that currently observes
because if you zoom in the spiral might
disappear and turn out to be something
different at the different resolution
right yes so at this level you have the
spiral and then you discover the spiral
moves to the right and some point it
disappears so you have a singularity at
this point your model is no longer valid
you cannot predict what happens beyond
the singularity but you can observe
again and you will see it is another
spiral and at this point it disappeared
so maybe we now have a second-order law
and if you make 30 layers of these laws
then you have a description of the world
that is similar to the one that we come
up with when we describe the reality
around us it's reasonably predictive it
does not cut to the core of it so you
explain how it's being generated how it
actually works but it's relatively good
to explain the University of your
entangled fence but you don't think the
tools are computer sizes the tools of
physics could get could step outside see
the whole drawing and get at the basic
mechanism of how the pattern the spiral
is generated imagine you would find
yourself embedded into a mother but
Franklin you try to figure out what
works and you you know somehow have a
throwing machine there's enough memory
to think and as a result you've come to
this idea it must be some kind of
automaton and maybe you just enumerate
all the possible automata until you get
to the one that produces your reality so
you can identify necessary and
sufficient condition for instance we
discover that mathematics itself is the
domain of all languages and then we see
that most of the domains of mathematics
that we have discovered are in some
sense describing the same
this is what category theory is obsessed
about that you can map these different
domains to each other so they're not
that many fractals and some of these
have interesting structure and symmetry
breaks and so you can just cover what
region of this global fractal you might
be embedded in from first principles yes
but the only way you can get there is
from first principles so basically your
understanding of the universe has to
start with automata and the number
theory and then spaces and so on yeah I
think like Stephen Wolfram still dreams
that he's it that he'll be able to
arrive at the fundamental rules of the
cellular automata or the generalization
of which is behind our universe yeah
it's you've said on this topic you said
in a recent conversation that quote some
people think that a simulation can't be
conscious and only a physical system can
but they got a completely backward a
physical system cannot be conscious only
a simulation can be cautious yeah
consciousness is a simulated property
that's simulate itself yeah just like
you said the mind is kind of the call it
story narrative there's a simulation or
our mind is essentially a simulation and
usually I try to use the terminology so
that the mind is basically a principles
that produce the simulation it's the
software that is implemented by your
brain and the mind is creating both the
universe that we are in and the self the
idea of a person that is on the other
side of attention and is embedded in
this world why is that important that
idea of a self
why is that an important feature in
simulation it's basically a result of
the purpose that the mind has it's a
tool for modeling right we are not
actually monkeys via side effects of the
regulation needs of monkeys and what the
monkey has to regulate is the
relationship of an organism to an
outside world that is a large part also
consisting of other organisms and as a
result it basically has regulation
targets that it tries to get to this
regulation target start with priors
they're basic like unconditional
reflexes that we are more less born with
and then we can reverse-engineer them to
make them more consistent and then we
get more detailed models about how the
world works
and how to interact with it and so these
priors that you commit to are largely
target values that our needs should
approach set points and this deviation
to the set point creates some urge some
tension and we find ourselves living
inside of feedback loops right
consciousness emerges over dimensions of
disagreements with the universe things
that you care things are not the way
there should be but you need to regulate
and so in some sense the sense self is
the result of all the identifications
that you're having an identification is
a regulation tracker that you're
committing to it's a dimension that you
care about do you think is important and
this is also what locks you in if you
let go of these commitments of these
identifications you get free there's
nothing that you have to do anymore and
if you let go of all of them you're
completely free and you can enter
Nirvana because you're done and actually
this is a good time to pause and say
thank you to sort of a friend of mine
Gustav's or Ostrom who introduced me to
your work I wanted to give him a shout
out he's a brilliant guy and I think the
AI community is actually quite amazing
and Gustav is a good representative that
you are as well some I'm glad first of
all I'm glad the internet exists you -
who's this where I can watch your talks
and then get to your book and study your
writing and think about you know that's
that's amazing okay
but the you've kind of described instead
of this emergent phenomena of
consciousness from the simulation so
what about the hard problem of
consciousness the can you just linger on
it like but why this is still feel like
I understand you're kind of the self is
an important part of the simulation but
why does the simulation feel like
something so if you look at the book by
say george RR martin with the characters
have plausible psychology yeah and they
stand on a hill because they want to
conquer the city below the hill and
they've done in it and then look at the
color of the sky and they are Princip
and feel empowered and all these things
why do they have these emotions it's
because it's written into the story
right and threatened with the story
because it's an adequate model of the
person that predicts what they're going
to do next
and the same thing is helpful it's
basically a story that our brain is
writing it's not written in words it's
written in perceptual content basically
multimedia content and it's a model of
what the person would feel if it existed
so it's a virtual person and you and me
happen to be this virtual person so if
this virtual person gets access to the
language center and talks about the sky
being blue and this is us but hold on a
second do I exist in your simulation you
do exist even almost similar way as me
so there are internal states that I that
are less accessible for me in that you
have and so on and you're my model might
not be completely adequate there are
also things that I might perceive about
you that you don't perceive but in some
sense both you and me are some puppets -
puppets that enact this play in my mind
and I identify with one of them because
I can't control one of the puppet
directly and with the other one I can
create things in between so for instance
we can go or in an interaction that even
leads to a coupling to a feedback loop
so we can sync things together in a
certain way or feel things together but
this coupling is itself not a physical
phenomena entirely a software phenomenon
it's a result of two different
implementations interacting with each
other so this is thing so are you
suggesting I did like the way you think
about it is the entirety of existence
simulation and we're kind of each mind
is a little sub simulation that like why
don't you why doesn't your mind have
access to my mind's full state like for
the same reason that my mind hasn't have
access to its own full state so what I
mean
there is no trick involved so basically
when I say know something about myself
it's because I made a model yes of your
brain is tasked with modeling what other
parts of your brain are doing yes but
there seems to be an incredible
consistency about this world in the
physical sense that is repeatable
experiments and so on yeah how does that
fit into our silly the center of apes
sim you
of the world so why is it some repeat
why is everything so repeatable and not
everything there's a lot of fundamental
physics experiments that are repeatable
for a long time all over the place and
so on
laws of physics how does that fit in it
seems that the parts of the world that
are not deterministic are not long-lived
so if you build a system any kind of
automaton so if you build simulations of
something you'll notice that the
phenomena that endure are those that
give rise to stable dynamics so
basically if you see anything that is
complex in the world it's the result of
usually of some control of some feedback
that keeps it stable around certain
attractors and the things that are not
stable that don't give rise to certain
harmonic patterns and so on they tend to
get weeded out over time so if we are in
a region of the universe that sustains
complexity which is required to
implement Minds like ours this is going
to be a region of the universe that is
very tightly controlled and controllable
so it's going to have lots of
interesting symmetries and also symmetry
breaks that allow the creation of
structure but they exist where so
there's such an interesting idea that
our - simulation is constructing the
narrative but my question is just to t