Kind: captions
Language: en
the following is a conversation with
Elon Musk his fourth time on this The
Lex fredman
podcast I thought you were going to
finish
it it's one of the greatest themes in
all film history
yeah that's great so I was just thinking
about the Roman Empire as one
does there's that whole meme uh
where all guys are thinking about the
Roman Empire at least once a day and
half the population is confused whether
it's true or not but more seriously
thinking about the wars going on in the
world today and as you know uh war and
military conquest has been a big part of
uh Roman society and culture and it I
think has been a big part of most
Empires and dynasties throughout human
history so yeah they usually uh came as
a result of Conquest I mean there's some
like the orer Hungarian Empire where
there was just a lot of sort of clever
marriages um but fundamentally there's
an engine of conquest and they celebrate
excellence in Warfare many of the
leaders were excellent generals yeah
that kind of thing so big picture
question grock approved I asked this is
a good question to ask tested grock
approved uh at least on fun mode
uh uh to what degree do you think war is
part of human nature versus a
consequence of uh how human societies
are structured I asked this
as you have somehow controversially been
a proponent of peace I I'm generally
proponent of peace I mean ignorance is
perhaps in my view the Real Enemy to be
countered that's the real hard part not
you know fighting other
humans um but all All Creatures fight I
mean the the jungle is a you look at the
people think of of this nature as
perhaps some sort of peaceful thing but
in fact it is not there's some quite
funny w w hog thing where he's like in
the jungle like saying that it's like
basically just murder and death in every
direction mhm I mean the the the plants
animals in the jungle are constantly
trying to killing each other every
single day every minute so it's not like
uh you know we're unusual in that
respect well this there's a relevant
question here whether with greater
intelligence uh comes greater control
over these base instincts for
violence yes we have much more an
ability to control our um limpic
Instinct for violence than say a
chimpanzee and in fact if if if one
looks at say chimpanzee Society it is
not friendly I mean the bonovas are an
exception um but chimpanze Society
is uh filled with violence and it's
quite quite horrific frankly that that's
that's Olympic system in action like you
don't want to be on the wrong side of a
chimpanze he'll eat your face off and
tear your nuts off yeah basically
there's no limits or ethics or uh the
Romans said just War there's no just war
in the chimpanzee societies is is worn
and and Domin is by any means necessary
yeah chenzi Society is a Like A
Primitive version of human society um
it's they're not like peac loving
basically um at all um there there's
extreme violence um and then once in a
while some some somebody who's watched
too many Disney movies decides to raise
a chimpanzee as a pet um and then that
eats their face or if they're nuts off
or Che their fingers off that kind of
thing yeah it's happened several times
uh ripping your nuts off is an
interesting strategy
for interaction some it's happened to
people it's un unfortunate like that's I
guess a one way to ensure that the other
chump doesn't like you know contribute
to the gene pool well from a martial
arts perspective it's a fascinating
strategy the
nrer I wonder which of the martial arts
teaches that I think it's safe to say if
somebody's got your nuts in their head
and as the option rubing the wolf you
will be amenable to uh whatever they
want yeah to say so like I said somehow
controversially you've been an uh
proponent of Peace on on Twitter on X
yeah so let me ask you about the war is
going on today and to see what the path
to peace could be how do you hope the
current war in Israel and Gaza comes to
an end uh what path do you see that can
minimize human suffering in the long
term in that part of the world well I
think that that part of the world is is
definitely like if you look up the there
is no easy answer in the dictionary
it'll be that like the picture of uh the
Middle East um in Israel especially so
there is no easy
answer
um what my this strictly my opinion of
you know is that
uh the the goal of Hamas was to provoke
an overreaction from Israel um they
obviously did not expect to uh you know
have a military Victory um but they they
expect they really wanted
to commit the worst atrocities that they
could in order to provoke the the most
aggressive response possible from Israel
um and then leverage that aggressive
response to um rally Muslims worldwide
uh for the course of uh Gaza and
Palestine which they have succeeded in
doing um so the this the the
counterintuitive thing here I think that
the the thing that I think should be
done even though it is very difficult uh
is that um I I would recommend that
Israel engage in the most cons
conspicuous acts of kindness possible
every everything that is the actual
thing that would th the goal ofas so in
some sense the degree that makes sense
in geopolitics turn the other cheek
implemented it's not exactly turn the
other cheek um because I do think that
there's
um you know I think it is appropriate
for Israel
to find the Hamas members and you know
um either either kill them or
incarcerate them um like something
something has to be done because they're
just going to keep keep keep coming
otherwise um
but uh in addition to that they need to
do whatever they can um there's some
talk of uh establishing for example a
Mobile hospital I'd recommend doing that
um just making sure that uh you know
there's food water uh medical
Necessities
um and and just be over the top about it
and be very transparent so it's so that
can't people can't claim it's a trick
like just put wave cam on the thing you
know old
24/7 deploy acts of
kindness yeah conspicuous acts of
kindness that that with that are
unequivocal meaning they can't be
somehow because hos will then their
response will be oh it's a trick
therefore you have to counter how how is
it not a trick this ultimately fights
the broader force of hatred in the in
the region yes and I'm not sure who said
it it's an apocryphal saying but an eye
for the for an eye makes everyone blind
now now that neck of the woods they
really believe in the whole eye for ey
thing
um but I me you really have if if you're
not going to just
outright commit genocide like against an
entire people which obviously would not
be acceptable to to to really shouldn't
be acceptable to anyone um then you're
you're going to leave basically a lot of
people alive who subsequently you know
hate Israel so really the question is
like how for for every Hamas member that
you kill how many did you create mhm and
if you create more than you killed
you've not succeeded that's the you know
the real situation there um and it's
safe to say that if you know
um if you know if if you kill somebody's
child in
Gaza you you you've made at least a few
uh Hamas members who will die
just just to kill an
Israeli that's the situation
so but but I mean this is one of the
most contentious subjects one could
possibly discuss but but I I think if if
the if the goal ultimate is some sort of
long-term peace one has to be look at
this from standpoint of over time are
there more or fewer um terrorists being
created let me just uh Linger on war
yeah well War it's safe to say Wars
always existed and always will exist
always will exist always has always has
existed and always will exist I hope not
you think it always always there will
always be
War this question of just how much war
and and um you know what you know
there's there's sort of the scope and
scale of War but to to imagine that
there would not be any war in the future
I think would be very unlikely outcome
yeah you talked about the culture series
there's war even there yes there giant
War the first book starts off with a
gigantic Galactic War where trillions
die trillions but it still nevertheless
protects these pockets of of
flourishing some somehow you can have
Galactic war and still have pockets of
flourishing yeah I mean it's I guess if
we are able to one day expand to you
know full the Galaxy or whatever there
will be a galactic War at some point ah
the scale I mean the scale of War has
been increasing increasing increasing
it's like a race between the scale of
suffering and the scale of flourishing
yes a lot of people seem to be using
this tragedy to beat the drums of war
and feed the military industrial complex
do you worry about
this the people who
are rooting for escalation and how can
it be stopped one of the things that
does concern me is that there are very
few people live today who actually
viscerally understand the horrors of War
at least in the US I mean obviously the
people in on the front lines in Ukraine
and Russia who understand just how
terrible war is um but how many people
in the west understand it um in my
grandfather was in World War II uh he
was severely traumatized um mean he was
there I think in for almost six years in
the you in East North Africa and Italy
uh all his friends were killed uh in
front of him and uh he would have died
too um except they randomly gave some I
guess IQ tests or something and uh he
scored very high um now he was not an
officer he was a I think a Corporal or a
sergeant or something like that um
because he didn't finish High School um
he had to drop out of high school
because his his his dad died and he had
to work to support his um siblings um so
because he didn't graduate high school
he was not eligible for the officer
Corp um so you know he kind of got put
into the cannon fighter category
basically um but then randomly they gave
him this test he was transferred to
British intelligence in London that's
where he met my grandmother um but uh he
he had PTSD next level like next level I
mean just didn't talk just didn't talk
and if you tried talking to him he'd
just tell you to shut up and he won a
bunch of medals never never bragged
about it once not even hinted nothing I
like found out about it because I his
military records are online that's a how
I know so he would say like no no way in
hell do you want to do you want to do
that again but how many people um now he
he obviously now he died you know 20
years ago or longer actually 30 years
ago
um how many people are alive that
remember World War II not many and the
same perhaps applies to the threat of
nuclear war
yeah I mean there are enough nuclear
bombs pointed at United States to make
the rubel the radioactive Revel bounce
many
times there's two major Wars going on
right now so you talked about the threat
of AGI quite a bit but now as we sit
here with the intensity of conflict
going on do you worry about nuclear
war I think we shouldn't discount the
possibility of nuclear war uh it is a
civilizational
threat
um right now I could be wrong but I
think the the current probability of
nuclear war is quite low um but there
are a lot of nukes pointed at us so and
we have a lot of nukes pointed at other
people they're still there nobody's put
their uh their guns
away the missiles are still in the silos
and uh the leaders don't seem to be the
ones with the nukes talking to each
other no there are Wars which are tragic
and difficult on a on a local basis and
then there are Wars which are
civilization ending or has that
potential obviously Global ther nuclear
warfare has high potential to end
civilization perhaps permanently but
certainly you know to
severely uh wounded and and perhaps
uh set back uh human progress by you
know to the Stone Age or something I
don't know pretty
bad
um probably scientists and Engineers
won't be super popular after that as
well they're like you got to S this mess
MH
so generally we I think we we obviously
want to prioritize civilizational risks
over things that are um painful and
tragic on on a local level but not
civilizational
how do you hope the war in Ukraine comes
to an end and what's the path once again
to minimizing human suffering
there uh well I think that what what is
likely to happen uh which is really
pretty much the the way it is is that um
something very close to the
current lines uh will
be how a ceasefire or truce
happens
but you know you just have a situation
right now where whoever goes on the
offensive um will suffer casualties at
several times the rate of whoever's on
the defense um because you've got uh
defense and DEP you got minefields uh
trenches anti-tank defenses um nobody
has air superiority um because the the
anti-aircraft missiles are really far
better than the the aircraft like there
far more of them
um and so neither side has air
superiority um tanks are basically death
drafts um just slow moving and they're
not immune to anti-tank weapons MH so
you you really just have longrange
artillery um
and uh infantry trenches it's World War
One all over again
mhm with drones you know throwing little
drones some some drones there um which
makes the long range artillery just that
much more accurate and better and so
more efficient murdering people on both
sides mhm yeah so it's who who whoever
is you don't you don't you don't want to
be trying to advance from either side
because the probability of dying is
incredibly High um so in order to
overcome
uh defense and depth trenches and
minefields you really need uh
significant local superiority numbers um
ideally combined on
where where you you do a fast attack
with
aircraft a concentrated number of Tanks
um and a lot of people that's the only
way you're going to punch through a line
and then you're going to punch through
and and then not have reinforcements
just kick you right out again I mean I I
really recommend people read uh World
War I Warfare in
detail that's rough
um I mean the sheer number of people
that died there was
mindboggling and it's almost impossible
to um imagine the end of it that doesn't
look like almost exactly like the
beginning in terms of who what land
belongs to who and so on but on the
other side of a lot of human
suffering death and destruction of
infrastructure yes the thing that the
reason I I I you know proposed a some
sort of Tru or or peace a year ago was
because I predicted pretty much exactly
what would would happen uh which is a
lot of people dying for basically almost
no changes in
land um and this the the loss of the the
flower of Ukrainian and Russian Youth
and we should have some sympathy for the
the Russian boys as well as the
Ukrainian boys because they Russian boys
didn't didn't ask to be on their front
line they have to be
so
um there's a lot of sons not not coming
back to their parents you know and
and I think most of them don't don't
really have they don't hate the other
side you know it's sort of like is this
saying about like this say comes from
World War I it's like young boys who
don't know each other killing each other
on behalf of old men that do know each
other
the hell's the point of
that so Vladimir zalinski said that he's
not or has said in the past he's not
interested in talking to Putin directly
do you think he should yeah sit down
manto man leader to leader and negotiate
peace look I think I would just
recommend do not send the flower of
Ukrainian youth to be to die uh in
trenches uh whether he talks to Putin or
not just don't do that um whoever goes
on the offensive will lose massive
numbers of
people
um and history will not look kindly upon
them you spoken honestly about the
possibility of war between us and China
in the long term if no diplomatic
solution is found for example on the
question of Taiwan and one China policy
right how do we avoid the trajectory
where these two superpowers
Clash well it's it's worth reading that
book on the the difficult to pronounce
thides trap I believe it's called I love
war history I like and say art and
backwards um there hardly a battle I
haven't read read
about and and trying to figure out like
what what really was the cause of
victory in any particular case as
opposed to what one side or another
claimed was the reason both the Victory
and what sparked the war and yeah yeah
the whole thing yeah so that Athens and
Sparta it's classic case the thing about
the Greeks is they really wrote down a
lot of stuff they loved writing um you
know there lots of interesting things
that happened in many parts of the world
but they people just didn't write down
so we don't know what happened or they
didn't really write
with in detail they just would say like
we went we had a battle and we won and
like what can you add a bit more um the
the Greeks they really wrote a
lot they were very articulate on they
just love writing so and we have a bunch
of that wring it that's preserved so we
know what led up to the pipian war
between um the spot and Athenian
Alliance um and uh we we know that they
they for quite they they saw it
coming I mean the Spartans didn't right
they also weren't very foros by their
nature but they did right but they
weren't very for they were tur uh but
the the Athenians and the other Greeks
wrote wrote a line and they were
like um and spot was really kind of like
the leader of of Greece um but but
Athens grew stronger and stronger with
each passing
year and um and everyone's like well
that's inevitable that there's going to
be a clash between Athens and
Sparta uh well how do we avoid that and
they couldn't they couldn't they
actually they saw it coming and they
still could not avoid
it so you know at some point if there's
if if
one uh group one civilization or or
country or whatever
um exceeds another sort of like if you
know the United States has been the
biggest kid on the Block for since I
think around 1890 from an economic
standpoint so the United States has been
the economic most powerful economic
engine in the world longer than anyone's
been
alive
um and the Foundation of war is
economics
so now we have a situation in case of
china where the um the economy is likely
to be two perhaps three times larger
than that of the US so imagine you're
the biggest kid on the Block for as long
as anyone can remember and suddenly a
kid comes along who's twice your
size so we see it coming yeah how is it
possible
to stop is there some let me throw
something out there just intermixing of
cultures understanding there do seem to
be a giant cultural Gap in understanding
of each other and you're an interesting
case study because you are an American
obviously you've done a lot
of uh incredible manufacturer here in
the United States but you also work with
China I've spent a lot of time in China
and met with the leadership many times
maybe a good question to ask is what are
some things about China that people
don't understand positive just in the
culture what some interesting things
that you've learned about the
Chinese well uh the the sheer number of
really smart hardworking people in China
is um incredible uh there are really you
say like how many smart hardworking
people are there in China there's far
more of them there than there are here I
think in my in my opinion
um the uh and they've got a lot of
energy
so I mean the architecture in China
that's in recent years is far more
impressive than the US I mean the the
train stations the buildings the
highspeed rail everything it's
um really far more impressive than what
we have in the US I I mean I recommend
somebody just go to Shanghai and
Beijing look at the buildings and go to
you take the train from Beijing to Shion
where you have the ter Carter Warriors
um China's got incredible history uh
very long history and um you know I
think arguably the in terms of the use
of language from from a written
standpoint um sort of one of one of the
oldest Perhaps Perhaps the oldest
written language and and then China
people did write things down
so um now China um historically has
always been with rare exception been
internally focused um they've not been
inquisitive uh they've they fought each
other they've been many many Civil Wars
um in the Three Kingdoms War I believe
they lost about 70% of their
population something and so the they've
had brutal internal Wars like civil wars
that make the US Civil War
look small by
comparison um
so I think it's important to appreciate
that China is not
monolithic um we sort of think of like
China is a sort of one entity of one
mind and this is definitely not the case
um from what I've seen and I think most
people who understand China would agree
people in China think about China 10
times more than they think about
anything outside of China so it's like
90% of their consideration is uh
you know is is internal well isn't that
a really positive thing when you're
talking about the collaboration in a
future pece between superpowers when
you're inward facing which is like
focusing on improving yourself versus
focusing on yeah uh quote unquote
improving others through military might
the good news the history of China
suggests that China is not inquisitive
meaning they're not going to go out and
invade a whole bunch of countries um now
they do feel very strongly you know so
that's good I mean because a lot of lot
of very powerful countries have been
inquisitive um the US is one of the also
one of the rare cases that has not been
inquisitive like after World War II the
us could have basically taken over the
world and any country like we got nukes
nobody else got nukes we don't even have
to lose
soldiers uh which country do you want M
and the United States could have taken
over everything oh at well and it didn't
um the United States actually helped
rebuild countries so it helped Reb re
Europe you know helped rebuil
Japan um this is very unusual behavior
almost
unprecedented
um you know the US did conspicuous acts
of kindness like the Berlin
airlift you
know
um and and I think you know there it's
always like well America's done bad
things well of course America's done bad
things but one needs to look at the the
whole track record um
and and just
generally you know one one sort of test
would be how do you treat your prisoners
of War M or let's
say
um you know no offense to the Russians
but let's say you're in Germany it's
1945 you got the Russian army coming one
side you got the French British and
American armies coming the other side
who would you like to be to surrender to
like no country is like Marley perfect
but I recommend um being a PW with the
Americans that would be my choice very
strongly in the full menu of P very much
so and in fact Von Brown um yeah took
you know smart guy uh was like we've got
to be captured by the Americans
yeah and uh in fact the SS was under
orders to execute bar Brown and all of
the uh German rocket Engineers uh and
they narrowly escaped their SSR they
said they were going out for a walk in
the woods they left in the middle of
winter with no coats uh and they ran
like and with no food no coats no water
and just ran like hell uh and ran West
um and by Sherlock they I think his
brother found like a a bicycle or
something and um and then just cycled W
as fast as he could and found found a US
Patrol um
so anyway that's that's one that's one
way you can
tell morality is who who where do you
want to be a
PW it's not fun anywhere but some places
are much worse than others
so um anyway so so so like America has
been uh while far from perfect uh
generally a benevolent Force um and uh
we should always be self-critical and uh
try to be better um but um anyone with
half a bra knows that so so I think I
there are in this way China and uh the
United States are similar NE neither
country has been
inquisitive um in a significant way so
that's like a you know a shared
principle I guess um now now China does
feel very strongly about
Taiwan they've been very clear about
that for a long time um you know from
their standpoint it's it's it would be
like one of the states is is is you know
not there like like Hawaii or something
like that but but more significant than
Hawaii you know
um and Hawaii is pretty significant for
us so um they view it as as as really
the there's a fundamental part of
China the island of fosa not not Taiwan
that is um not part of China but should
be uh and the only reason it hasn't been
is because of the US Pacific
Fleet and is their economic power grows
and is their military power
grows the thing that they are clearly
saying uh is their interest will you
know clearly be
materialized
yes China has been very clear that um
they will incorporate Taiwan uh
peacefully or uh militarily but
that they will incorporate it from their
standpoint is 100%
likely you know something you said about
conspicuous acts of kindness as a
geopolitical policy it almost seems
naive but I'd venture to say that this
is probably the path forward how you
avoid most wars just as you say it it
sounds naive but it's kind of
brilliant if you believe in the goodness
of of underlying most of human nature it
just seems like conspicuous acts of
kindness can uh reverberate through the
populace of the countries
involved yeah well and deescalate
absolutely so in after World War I the
the they made a big mistake you know
they basically triy to lump all the
blame on Germany um and um
and and you know settled Germany with uh
impossible
reparations um and you know really there
was a lot of BL there was a fair quite a
bit of blame to um go around for World
War I um but they they try to you know
put it all in Germany
um and uh that was that that laid the
seeds for World War
II uh
so that's a lot of people people were
not just Hitler a lot of people felt
wronged um
and they wanted
Vengeance and they got it people don't
forget yeah you you kill
somebody's father mother son daughter
they're not going to forget it they will
want Vengeance um so after World War II
they're like well the treat of verai was
a huge mistake um in World War I
and um so this time instead
of
uh you know crushing the losers we're
we're actually going to help them with
the Marshall Plan and we're going to
help R Revol Germany we're going to help
reol or you know Austria and the other
you know Italy and whatnot
so
um that was the right move there's uh
feel like there's a profound
truth to uh the conspicuous a of kind as
being an antidote to
this something must stop the the cycle
of reciprocal
violence something must stop it or it
will you know it'll it'll it'll never
stop
just eye for an eye tooth for a tooth
limb for Lim life for a life forever and
ever to escape briefly the darkness was
some incredible engineering
work uh xai just released grock AI
assistant that I've gotten a chance to
play with it's uh it's amazing on many
levels first of all it's amazing that a
relatively small team in a relatively
short amount of time was able to develop
this close to state-of-the-art system uh
another uh incredible thing is there's a
regular Moe and there's a fun mode yeah
I guess I'm to blame for that
one I wish first of all everything in
life had a fun mode yeah I there's
something compelling Beyond just fun
about the fun mode interacting with a
large language model I'm not sure
exactly what it is cuz I only had a
little bit of time to play with it but
it just makes it more interesting more
vibrant to interact with the system yeah
uh absolutely I um our our AI Gro is
modeled after the Hedgehog is got to the
Galaxy
uh which is one of my favorite books uh
which is it's a book on philosophy
disguised as a book on humor M um and
um I would say that is that forms the
basis of My Philosophy uh which is that
we don't know the meaning of life but
the more we can expand the scope and
scale of
Consciousness digital and
biological the more we are able to
understand what questions to ask about
the that is the
universe so I have a philosophy of
curiosity there is generally a feeling
like this AI system has an
outward looking like the way you are
like sitting with a good friend looking
up at the stars like the asking poad
like questions about the universe
wondering what it's all about the
Curiosity you talk about there there's a
sense no matter how I'm on day in the
question I ask it there there's a sense
of cosmic Grandeur to the whole thing
well we are actually working hard to
have uh engineering math and physics
answers that you can count on
mhm um so for the other sort of AIS out
there
that these so-called large language
models um I've not found the uh
engineering to be reliable um and the
hallucination it it unfortunately
hallucinates Mo most when you least
wanted to alucin yeah so when you ask
important difficult questions it that's
when it tends to be confidently wrong um
so we're really trying hard to say okay
how do we be as grounded as possible so
you can count on the results
um Trace things back to physics first
principles U mathematical logic um so
underlying the humor is an aspiration
to adhere to the truth of the universe
as closely as
possible that's really tricky it is
tricky
so that's why you know you there's
always going to be some amount of error
but do we want to um aspire
to be as truthful as possible about the
answers uh with acknowledged error and
so that there was always you don't want
to be confidently wrong so you're not
not going to be right every time but you
don't be you want to minimize how often
you're confidently uh wrong and then
like I said once you can count on the
logic as being
um not violating physics then you can
start to build on that to create uh
inventions like invent new
technologies but if if you can't if if
you if you
cannot count on the foundational physics
being correct obviously the inventions
are simply wishful
thinking you know imagination
land magic
basically well as you said I think one
of the big goals of xai is to understand
the universe yes that's how simple
three-word uh
Mission um if you look out far into the
future do you think on this level of
physics the very edge of what we
understand about physics do you think it
will make discoveries sort of the
sexiest discovery of them is as we know
now sort of uh unifying general
relativity and quantum mechanics so
coming up with a Theory of Everything do
you think it could push towards that
direction almost like theoretical
physics discoveries if an AI cannot
figure out new physics um it's clearly
not equal to humans let alone nor has
surpass humans because humans have
figured out new physics they just you
know physics is just understanding you
know deing On's insight into how reality
works and then
um the then then this engineering which
is inventing things that have never
existed mhm now the the range of
possibilities for engineering is far
greater than for physics because you
know once you figure out the rules of
the universe uh that that's that's it
you've discovered things that already
existed but from that you can then build
Technologies with that are really almost
Limitless in the uh variety and C you
know it's like once you understand the
rules of the game properly and we do
current physics we do at least at a
local level understand how physics works
very well our ability to predict things
is incredibly good like quantum
mechanics is the degree to which quantum
mechanics can predict outcomes is
incredible um that was my that's my
heart hardest class in college by the
way my my my senior quantum mechanics
class was harder than all of my other
classes put together to get an AI system
a large language model to to um reliably
be as reliable as quantum mechanics and
physics is very difficult yeah you have
to test any any conclusions against the
ground truth of reality reality is the
ultimate judge like physics is a law
everything else is a
recommendation I've seen plenty of
people break the break the laws made by
man but none break the laws made by
physics it's a good test actually if
this
LM uh understands and matches physics
then you can more reliably trust
whatever it thinks about the current
state of politics in some sense and it's
also not not the case currently that uh
even that its internal logic is not
consistent um so especially
um with these with the approach of like
just predicting a token predict token
predict token it's like a vector sum you
know you you're summing up a bunch of
vectors but you can get drift um so as
those a little bit of error a little bit
of error adds up and by the time you are
many tokens down the path uh you're it
it doesn't make any sense MH so it has
to be somehow self-aware about the drift
it has to be self-aware about the drift
and then look at the thing as a gal as a
whole and and say it does it have
coherence as a whole MH
so you know when when authors write
books that they they will write the book
and then they'll go and revise it you
know taking into account you know all
the end and the beginning and the middle
and and
uh rewrite it to achieve coherence so
that it doesn't end end up in a
nonsensical place maybe the process of
revising is what yeah reasoning is and
then that's the process of rising is how
you get closer and closer to truth maybe
you like uh at least I approach that way
you just say a bunch of first
and then you get it better you start a
and then you get you create a
draft and then and then you and then you
iterate on that draft um until it has
has coherence until it's it'll add add
up basically so another question about
Theory of Everything But for
intelligence do you think there exists
as you're exploring this with xai
creating this intelligence system do you
think there is a theory of intelligence
where you get to
understand what
like what is the eye in AGI and what is
the eye in um human intelligence there's
no ey in Team America oh wait there
is uh going to be stuck in my head
now uh yeah there's no me and
whatever uh in quantum mechanics oh
wait uh I mean is that part of the
process of discovering understanding the
universe is understanding
intelligence
yeah yeah I think we need to understand
intelligence understand Consciousness I
mean there I mean there are some sort of
fundamental questions of like
what is thought what is emotion yeah um
is it really just one atom bumping into
another atom it feels like something
more than
that uh so I I I I I think we're
probably missing some really big things
um like some really big things something
that'll be obvious in retrospect yes
like there's a giant like you put the
whole Consciousness
emotion well some would call it like a
like a soul you know religion a soul um
like you feel like you're you right I
mean you don't feel like you're just a
collection of atoms but on what
dimension does thought exist what
dimension does do emotions exist we feel
them very
strongly um I suspect there's more to it
than atoms bump into
atoms and maybe AI can pave the path to
the Discovery what whatever the hell
that thing is is yeah what is
consciousness like what when you put the
atoms in a particular shape why are they
able to form thoughts mhm and take
actions that and and
feelings and even if it is an illusion
why is this illusion so compelling yeah
like how do why does the solution exist
yeah on what plane does this the
solution exist yeah um and sometimes I
wonder
is you know either PA everything's
conscious or nothing is
conscious um one of the two I like the
former everything conscious just seems
more fun it do seem more more fun yes um
but we're composed of atoms and those
atoms are composed of quarks and leptons
and those quarks and leptons have been
around since the beginning of the
universe the beginning of the universe
right what what seems to be the
beginning of the universe the first time
we talked you said what you would which
is surreal to think that this discussion
was happening is becoming a reality I
asked you what question would you ask an
AGI system once you create it and you
said what's outside the simulation is
the question and good question yeah but
it seems like with Gro you started to
literally uh the system's goal is to be
able to ask such questions to answer
such questions and to ask such questions
where are the aliens where are the
aliens that's one of the the like the FY
Paradox question um a lot of people have
asked me if I've seen any evidence of
aliens and I I haven't which is kind of
concerning because
then I think would I probably prefer at
least have seen some archaological
evidence of aliens um to the best of my
knowledge there is no Pro I not worth
any evidence of
aliens out there they're very
subtle we might just be the only
Consciousness at least in the Galaxy um
and if if you look at say the history of
Earth for to believe the archaeological
record Earth is about 4 and a half
billion years old civilization as
measured from the first writing is only
about 5,000 years old we have to give
some credit there to the ancient
samarians who aren't around anymore I
think it was a archaic pre uniform was
the first actual symbolic representation
but only about 5,000 years
ago I think that's a good date for when
when we say civilization
started that's 1 millionth of Earth's
existence so civilization has been
around it's really a flash in the pan
mhm so far
um and why why have
we why did it take so long for you know
4 and a half billion
years um
for the vast majority of the time there
was no life and and then there was
archaic bacteria for a very long
time and
then you know you
had mitochondria get captured
multicellular
life um differentiation into plants and
animals life moving from the oceans to
land
mamals um higher brain
functions and the Sun is expanding
slowly um
but it will it will overheat it will it
will heat heat the Earth up at some
point in the future um boil the oceans
and and Earth will become like Venus
where no life let Life as we know it is
impossible so if we do not become
multiplanetary and
ultimately go beyond our solar system um
annihilation of all life on Earth is a
certainty
a
certainty um and it could be as little
as on the galactic time
scale uh half a billion
years you know long time by human
standards but that's only 10% longer
than Earth has been around at all mhm so
if if life had taken 10% longer to
evolve on Earth it wouldn't exist at all
we got a deadline coming up better hurry
but that said as you said humans
intelligent life on
Earth developed a lot of cool stuff very
quickly so yes it it seems like becoming
a multiplanetary is almost
inevitable unless we destroy we need to
do it I mean it's it's not I mean I
suspect that there
there if we are able to go out there and
explore other star systems that we there
chance we find a whole bunch of long
Dead one planet civilizations yeah they
never made it past to their home planet
that's so
sad sad also fascinating I mean there
are various explanations for the for
Paradox and one is just the sort of
there these great filters which
civilizations don't pass through and one
of those great filters is do you become
a multi-planet civilization or not and
if you don't it's simply a matter of
time before something happens on your
planet
um you know either natural or man-made
that causes us to die out like the
dinosaurs where are they
now that didn't have
spaceships so I think the more likely
thing is cuz just
a uh empathize with the aliens that they
they found us and they're protecting us
and letting us beat I hope so nice
aliens just like the tribes in the in
the Amazon the on contacted tribes we
protecting them that's what uh that
would be a nice explanation or you could
have like uh what was it uh I think
Andre kathi said it's like the ants in
the Amazon asking where's
everybody well they do run into a lot of
other ants that's true these ant
Wars sounds like a good TV show yeah
they literally have these big Wars
between various
ants yeah I'm maybe I'm just
uh uh dismissing all the different Unity
evance you should listen to that wner
hog talking about the jungle it's really
hilarious have you heard it no I have
not but wner hog is a
way you should play you should play it
for the you know as an interlude in the
it's on YouTube it's it's
awesome I love him so much uh he's great
was he the director of happy people life
in the tiger I think also he did that
bear documentary The Bear documentary
and this thing about penguins yeah
the depr the analysis psycho analysis of
P psych yeah the penguins like headed
for like mountains like that are like 70
miles away and penguin has just had for
Doom basically well he was had a cynical
take I I have a he could be just a brave
Explorer and there'll be great stories
told about him amongst the penguin
population for many centuries to
come
um what we talking about okay uh
yeah so aliens I mean I don't know look
I think if the smart move uh is just you
know this is the first time in the
history of Earth that it's been possible
for life to extend beyond Earth um that
window is open um now it may be open for
a long time or it may be open for a
short
time and it it may be open now and then
never open again so I I think the smart
move here is to make life multiplanetary
while it is possible to do so we don't
want to be one of those lame One Planet
civilizations that just dies out no
those are lame
lame um self-respecting civilization
would be one planet there's not going to
be a Wikipedia entry for one of
those and uh pause uh do SpaceX have an
official uh policy for when we meet
Aliens no okay that seems irresponsible
um I mean look if I see the slightest
indication that there are aliens I will
immediately post on the next platform
yeah anything I know it could be the
most liked reposted post of all time
yeah I mean look we have more satellites
up there right now than everyone else
combined so you know we'd know we know
if we got to maneuver around something
and we not I don't have to maneuver
around
anything if you go to the the big
questions once again you said you've um
you're with Einstein that you believe in
the god of
Spinosa yes uh so you know that's a view
that God is like the universe and is
reveals himself through the laws of
physics or as Einstein said through the
lawful Harmony of the world yeah I would
agree that that God of the simulator or
whatever the the Supreme Being or beings
um um
themselves through the physics you know
they creators of this existence and it's
incom upon us to try to understand more
about this wondrous
creation like who created this thing
who's running this thing like embodying
it into a a singular question with a
sexy word on top of it is like focusing
the mind to understand it it does seem
like there's a um again it could be an
illusion it seemed like there's a
purpose that there's underlying master
plan of some kind kind it seems like
there may not be a master plan in the
sense so this like maybe an interesting
answer to the question of determinism
versus free will is that if we are in a
simulation the reason that the the these
higher beings would hold a simulation is
to see what happens mhm so it's not um
they don't know what
happens uh otherwise they wouldn't hold
the simulation mhm so when when humans
create a simulation so it's basx and
Tesla we create simulations all the time
um especially for the rocket you you uh
you know you have to run a lot of
simulations to understand what's going
to happen because you can't really test
the rocket until it goes to space and
you want it to work so you have to you
have to
simulate subsonic transonic hyp
supersonic
hyponic um ascent and then coming back
super high Heating and um orbital
Dynamics all this has got to be
simulated
so uh you don't get very many kicks that
they can but we run the simulations to
see what happens not if we knew what
happens we wouldn't run the simulation
mhm so if if there's so whoever created
this
existence um
is they're running it because they don't
know what's going to happen not because
they
do so maybe uh we both play Diablo maybe
Diablo was created to see if a druid
your character could defeat Uber Lilith
at the end they didn't know well the
funny thing is
UB uh her title is hatred incarnate yeah
um and right now I guess you can ask the
Diablo team but it's almost impossible
to defeat
hatred uh in the Eternal realm yeah
you've streamed yourself dominating tier
100 nightmare Dungeons and still I I I
can cruise through tier 100 nightmare
dungeons like a stroll in the park mhm
and still you're defeated by hatred yeah
I can there the sort of I guess maybe
the second heartest boss is duriel
durial can't even scratch the paint so
uh I killed duel duel so many times um
and every other boss in the game all all
of them kill him so many times it's easy
um
but uh uth otherwise known as hatred
incarnate especially if you're a druid
and you have no ability to go to be inv
vulnerable you there are these random
death waves that that come at you
um and I'm pretty you know really I am
52 so my reflexes not what they used to
be but I'm I have a lifetime of playing
video games um at one point I was you
know maybe one of the best Quake players
in the world um actually won money for
what I think was the first paid orts
tournament in the US um we're do doing
four person Quake tournaments and
um we came second I was the second best
person on the team and the the the
actual best person we we're actually
winning we would have come first except
the best person on the team his computer
crashed halfway through the game um so
we we came second but I got money for it
and everything so like basically I got
skills you know I'll be it you know
no no spring spring chicken these days
and
um the to be totally Frank it's driving
me crazy trying to beat Lilith as a
druid basically try trying to beat
trying to beat hatred and connate in the
Eternal realm as a druid as a druid and
if you if you if you this is
really vexing let me tell you um I mean
the challenge is part of the fun I I
have seen directly like you're actually
like a world class Incredible video game
player yeah and I think Diablo so you're
just picking up a new game and you're
figuring out his fundamentals you're
also with the Paragon board and the
build are not somebody like me who
perfectly follows whatever they suggest
on the internet you're also an innovator
there yeah which is hilarious to watch
it's like a it's like a mad scientist
just trying to figure out the Paragon
board and and the build and you know um
is there some interesting insights there
about uh if if somebody's starting as a
druid do you have
advice um I would not recommend playing
a druid in the Eternal realm um right
now I think the most powerful character
in this in the seasonal realm is the
sorcerer with the lightning bows mhm so
the SS have huge balls in um the
seasonal oh yeah that's what they
say so ex huge balls um they do uh huge
balls of lightning I'll take your a word
for it and it's actually in the seasonal
realm you can you can it's it's like
pretty easy to beat uh Uber lth with the
because you get these vampiric powers
that amplify your damage and increase
your defense and whatnot so um really
quite easy to defeat hatred seasonally
but to defeat hatred eternally very
difficult um almost imposs it's very un
impossible it seems like this know a
metaphor for life you know I like the
idea that Elon Musk CU I saw I was
playing diao yesterday and I saw 100
level 100 Druid just run by I will never
die and then run back the other way and
it there's just some this metaphor is
kind of hilarious that you Elon Musk is
fighting
hatred restlessly fighting hatred in
this demonic realm yes it's hilarious I
mean it's pretty hilarious no it's
absurd really it's exercising absurdity
and it makes me want to pull my hair out
yeah um I what do you get from video
games in general is there is there for
you for
you personally it's I don't know it's uh
it calms my mind I mean you sort of
killing the demons in a video game calms
the demons in my
mind yeah if you play a tough video game
you can get into like a state of flow
which is very enjoyable um and
uh admittedly it it needs to be not too
easy not too hard um kind of in the
goldilock zone um and I guess you
generally want to feel like you're
progressing in the game
so um a good video and and there's also
beautiful art um engaging story
lines um and it's a it's like an amazing
puzzle to solve I think and so I just
like solving the puzzle Elder ring the
greatest game of all time I still
haven't played it but you it's alen ring
is definitely a candid for best game
ever top five for sure I think I've been
scared how hard it is oh how hard I here
it is so but it is beautiful alen ring
is feels like it's designed by an
alien um there's a theme to this
discussion in what way it's it's it's so
unusual it's incredibly creative and the
art is
stunning I recommend playing it on a on
a big resolution Pi on ra TV even
doesn't need to be a monitor just uh the
art is incredible it's so
beautiful and and it's it's so
unusual
um and each of those TP boss battles is
unique like it's like a unique puzzle to
solve each one's different um and the
strategy you use to solve one battle is
different from another battle that said
you said drew it an intern against Uber
Lilith is the hardest boss battle you've
ever correct that is currently the the
and i' I've played a lot of video games
my because it's my primary recreational
activity yes
um
and
yes beating hatred in the internal realm
yeah is the hardest boss
battle in life and in the video game man
I don't I'm not sure it's
but it's I do make progress so then I'm
like okay I'm making progress
maybe if I just tweak that Paragon board
a little
more I can do it could just dodge a few
more
waves I can do it well the simulation is
created for the purpose of figuring out
if it can be done and you're just a cog
in that simulation in the machine of the
simulation yeah it might
be I I I I I have a feeling
that at
least I
think it's doable it's doable yes mhm
well that's the human Spirit right there
to believe yeah I mean it did prompt me
to think about just hate in general
which is
you want to be careful of one of those
things where you wish for
something that sounds
good but but if you get it it's actually
a Dy
situation so you know you could sort of
run a sort of uh have auis of like if
you wish for World Peace sounds good MH
but how is it
enforced and and at what cost is is what
at what cost Eternal peace it might
actually be worse to have eternal peace
because of what that would entail the
suppression of
everyone it might be the suppression of
progress
it might be an oopi society that never
changes one I'm saying is
that there is an
argument
that you you that if that if you wish
for no
war you should be careful what you wish
for because what's required in order for
there to be no
war might be worse than a little war
yeah the things we consider to be flaws
of human civilization might be unne
components for whatever optimal looks
like um I mean this do you worry about
AI AGI enabling a dystopian state of
this nature whether it's 1984 with
surveillance and fear or Brave New World
with
pleasure and what is it l lots of
sex but no deep Human
Experience you know there's actually a
real drug called soma there is yes
I'm like did they actually does Gro know
about it no he probably will go to Brave
New World we could ask it what what
would be the question tell us about the
drug called soma tell us about the drug
called
Som it's going to go to Brave New World
I think well there's a real drug as well
searching for Som drug
information oh
boy ah s the Wonder drug by the way I'm
in fun mode oh okay F yes so it's
talking about the real drug oh it's a
muscle relaxment that's been around
since the 1950s it's used to treat
muscle pain and discomfort and it does
this by altering the activity between
neurons and the spinal cord now s isn't
just a pain reliever it's also a bit of
a sedative it can make you feel a bit
drowsy so it's not something to take if
you're planning on operating heavy
machinery or trying to solve complex
math equations and it goes on and on in
conclusion s is a drug that can be
helpful for those dealing with muscle
pain but it's not without its risks it's
pretty good oh wait a minute that's the
real drug it's talking about that's the
real drug yeah uh and of course the fun
is always use it responsibly in
accordance with the advice of a healthc
care professional and remember in the
end the universe is probably just a
giant computer simulation so don't take
anything too seriously I love I love it
I love it I love it yeah so oh it also
really nicely uh includes like uh
the the tweets pul on X that are
relevant to this which is really cool
yeah it like integrates everything
together yeah like the interface is one
of the really cool things here yeah
seems done great job
um so and you say like you could say
like no no I mean Soma from bra Brave
New World because it it thinks you mean
you you mean s the real drug yeah no I
mean s from bra be world
it's going to be like oops I'm really
sorry I'm really surprised it went to
the real drug
first ah my apologies I was thinking of
the muscle relax and S for Brave New
World is a different Beast altogether
all do hux Le to stal Soma is a drug
that plays a central role in the society
depicted in the book it's a mood
altering hucog genic drug that's used to
keep the population docile and content
in the novel to you s Brave New World
raises some interesting questions about
the the nature of happiness and the role
of drugs in
society oh man exactly is it better to
live in a world where everyone is happy
all the time even if that Happ happiness
is artificial it's good question this is
what I mean like do you want do you wish
for world peace and and happiness all
the time are you sure mhm um because
that might be a society that is
essentially sterile and aifi that never
changes that is ultimately
doomed this kind of tension
between uh dark and light it's this
really a very good summary um MH it
really gets the point this is not simply
regurgitating Brave New World it's
actually getting to the Salient element
of Soma as a drug um do you do actually
want to be in a situation where everyone
is happy all the time even though it's
artificial or is better to confront the
challenges of life and experience a full
range of human emotions even if it means
experiencing pain and suffering for
those listening by the way Elan just
read directly from Gro which is a really
nice kind of insightful philosophical
analysis of the tension here interesting
it pretty much Nails it in conclusion
Som from Brave New World is fictional
drug that used to explore some deep
philosophical questions about the nature
of happiness and the role of drugs in
society it's a powerful symbol of the
dangers of using drugs to escape from
reality and the importance of
confronting the challenges of life
headon nailed
it and the crazy thing is like you know
we do have a real drug called soma which
kind of does is kind of like the drug in
the book and I'm like did they they must
have name they must have named it after
probably probably some of the real drug
is quite effective on back pain so you
know about this drug is
fascinating okay cuz I had like a you
know squashed uh disc in my C5 C6
so it takes the physical pain away but s
my here it doesn't completely it it it
reduces the amount of pain you feel but
at the expense of mental
acuity it DS your
mind just like just like the drug in the
book just like the truck in the book and
hence the
trade-off uh the thing that seems like
Utopia could be a dystopia after all
yeah actually I was talking to a friend
of mine
um saying like would you really want
there to be no hate in the world like
really none like I wonder why hate
evolved um I'm not saying we should
amplify hate of course I think we should
try to minimize it but but none at
all H there might be a reason for
hate and suffering it's really
complicated to consider that some amount
of human suffering is necessary for
human
flourishing is it possible to appreciate
the highest without knowing the
lows and that that that all is
summarized there in a single statement
from gr okay no highs no lows who
knows that's almost the
poem uh it seems that training llms
efficiently is a big Focus for xai
uh what's the uh first of all what's the
limit of what's possible in terms of
efficiency there's this uh terminology
of useful product ity per watt like what
have you learned from pushing the limits
of that well I think it's helpful the
tools of physics are very powerful and
can be applied I think to almost any
really any arena in life that's it's
really just a critical thinking for
something important you need to reason
with from first principles and think
about things in the limit One Direction
or the
other so um in the limit even at the CF
scale meaning even if you harness the
entire power of the Sun you will still
care about useful compute Pro
what so that's where I I think probably
where things ahead it from uh the
standpoint of AI is that we have a
silicon shortage now that will
transition to a voltage Transformer
shortage in about a year ironically
Transformers for
Transformers you need you need
Transformers to run Transformers
somebody has a sense of humor in this
thing
I
think yes oh man fate Love's
irony ironic humor and an ironically
funny outcome seems to be often what
fate wants humor is all you need I think
spice is all you need somebody
posted yeah but yeah so so we're we're
have a silicon shortage today um it
voltage Step Down Transformer shortage
probably in about a year and then just
electricity shortages and General in
about 2 years I I gave a speech for the
sort of world Gathering of utility
companies electricity companies um and I
I said look you really need to prepare
for a tribling of electricity demand um
because all transport is going to go
electric with the ironic exception of
rockets and uh and and heating um will
also go
electric um so energy usage right now is
roughly 13 if very rough terms 1/3
Electric
1/3 transport 1/3 heating um and so in
order for everything to go sustainable
to go electric um you uh need to Triple
electricity output so I encourage the
utilities
to uh build more power plants and and
also to probably have well well not
probably they should definitely buy more
batteries because the the grid currently
is sized for real-time load which is
kind of crazy because you know that
means you got to size for whatever the
the peak electricity demand is like the
worst second or the worst day of the
year or you can have a brand out or
blackout and you we had the crazy
blackout for several days in in in
Austin
um so uh because there's almost no
buffering of energy in the grid like if
you've got a Hydro power plant you can
buffer energy but otherwise um it's all
real time
so with batteries you
can you can produce energy at night and
use it during the day so you can
buffer so I I I expect that there will
be very heavy usage of of batteries in
the
future because the peak to trough ratio
for power plants is anywhere from 2 to 5
you know so it's like lowest point to
highest point so like batteries are
necessary to balance it out and then but
the demand as you're saying is going to
grow grow grow grow yeah and part of
that is the
compute yes yes I mean electrification I
mean electrification of Transport uh and
and electric heating will will be much
bigger than AI at least in the short
term in the short term um but but even
for for AI you you really have a growing
demand for electricity for electric
vehicles and a growing demand for
electricity for to run the computers for
AI mhm and so this is obviously leading
can lead to a electricity shortage how
difficult is the problem of uh in this
particular case maximizing the useful
productivity per watt for training you
know nuts like this seems to be really
where the big problem we're facing that
needs to be solved is how to use the
power
efficiently like what you've learned so
far about applying this physics first
principle of reason in this domain how
difficult is this
problem it will get solved it's the
question of how long it takes to solve
it so at various points there's a limit
some some kind of limiting factor to
progress um and with regard to saying
right now the limiting factor is uh
silicon chips um and that will we're
going to then have more chips than we
can actually plug in and turn on um
probably in about a year um the the
initial constraint being literally
voltage step down Transformers because
you've got um power coming in at three
300,000 volts and it's got to step all
the way down eventually to around 7
volts so it's a very big amount
of you know the voltage St down is
gigantic um so and and the industry is
not used to Rapid
growth okay let's talk about the
competition here you've shown concern
about Google and Microsoft with open AI
developing uh AGI how can you help
ensure with xai and uh Tesla AI work
that it doesn't become a competitive
race to AGI but instead is a
collaborative development of safe
AGI well I mean I've been pushing for
some kind of regulatory oversight for a
long time I've been somewhat of a
Cassandra on the subject for over a
decade um I think we want to be very
careful in how develop AI
um it's it's a it's a great power and
with great power comes great
responsibility um I think it it would be
wise for us to have at least um an
objective third party who can be like a
referee that can go in and understand
what the various leading players are
doing with AI and even if there's no
enforcement ability they should they can
at least
voice
concerns um
publicly um you know Jeff Hinton for
example left Google and he voiced strong
concerns but now he's not at Google
anymore so who's going to voice the
concerns so I think I think there's I I
I like I you know Tesla gets a lot of
regulatory oversight on the automotive
front I we're subject to I think over
100 Regulatory Agencies domestically and
internationally so so it's a lot you
could fill this room with the all the
regulations that Tesla has to adhere to
for
automotive um same is true in you know
for rockets and for you
know um currently the limiting factor
for SpaceX for Starship launch is
regulatory approval uh the fa has
actually given their approval but we're
waiting for fish and wildlife to uh
finish their analysis and give their
approval that's why I posted I want to
buy a fish license on
which also refers to the Monty Python
sketch
yeah like why do you need a license for
your fish I I don't
know according to the rules I'm told you
need some sort of fish license or
something we effectively need a fish
license go to
Rocket and I'm like wait a second how
did the fish come into this picture yeah
um I mean some some of the things like
that that it's I feel like are so absurd
that I wanted like a comedy sketch and
Flash at the bottom this is all real
this is actually what happened um you
know one of the things that was a bit of
a challenge at one point is that they
were worried about uh our rocket hitting
a shock MH and um now the ocean's very
big and uh how often do you see shars uh
not that often you know as a percentage
of ocean surface area shocks basically
go zero and and and so then we will then
we said well how will we calculate
the probability of telling a shark and
they're like well we can't give you that
information because they're worried
about shark hunt shark fin Hunters uh
going and hunting sharks I said well how
are we supposed to we're on the horns of
a dilemma then
um then they said well there's another
part of fishing Wildlife that can can do
this analysis I'm like well why don't
you give them the data like we don't
they don't we don't trust them like
excuse me you know they're literally in
your department again this is actually
what happened um and uh and and and can
you do an NDA or
something eventually they managed to
solve the internal quander and indeed uh
the probability of ofing a shock is
essentially zero um then there's another
organization that I didn't realize
existed
until you know a few months ago uh that
cares about whether you we would
potentially hit a whale in international
waters now again you look at the surface
of the look at the look at the Pacific
and say what percentage of this the
specific consists of whale like he give
you a big picture and like point out all
the whales in this picture I'm like I
don't see any
whales like basically 0% um and if arcka
does hit a whale which is extremely
unlikely beyond all belief um that is
the the Fate haded has a well has some
seriously bad luck you know that's like
least lucky well ever um and um I mean
this is quite
absurd bureaucracy The Bu of this
however it emerged yes well I mean one
one of the things that's pretty wild is
um for launching out of vanur in
California we had to they were worried
about uh seal procreation whether the
seals would be dism made by the Sonic
booms um now there have been a lot of
rockets launched out of vur and the seal
population has uh steadily increased um
so if anything rocket booms are an eord
eiac um based on the evidence if you
were to correlate Rock launches with uh
sealed population um nonetheless we were
forced to kidnap a seal strap it to a
board put headphones on the seal and
play Sonic Boom sounds to it to see if
it would be
distressed this is an actual thing that
happened this is actually real I have
pictures love to see this yeah there I
mean sorry there's a seal with
headphones
yes it's a seal with headphones strapped
to a board and and like the okay now the
amazing part is how calm the seal was
yeah because if I was a seal i' be like
this is the
end they're definitely going to eat me
yeah um how will the seal when seal goes
back to other you know seal friends
how's they going to explain that they're
never going to believe him never going
to believe it that's why I'm like well
you know it's sort of like it's like
getting kidnapped by aliens and getting
the anal probe you know
you come back and I swear to God I got
kidnapped by aliens they stuck anal Pro
in my butt and people like no they
didn't that's
ridiculous seal buddies are never going
to believe him that he gets St to a Ward
and they put headphones on his
ears and then let him
go twice by the way we had to do it
twice they let him go twice we had to CT
the same seal well no different seal
okay did you uh did you get a seal of
approval yeah exactly approval no I mean
this is this is like I don't think the
public is quite aware of the the madness
that goes
on yeah it's yeah it's absurd freaking
seals with freaking headphones I mean
this is the it's a good encapsulation of
of the absurdity of human civilization
seals and headphones yes uh what are the
pros and cons of open sourcing AI to you
as another way to
combat um you know a company running
away with AGI
in order to run uh like really deep
intelligence you need a lot of compute
so it's not like you know you can just
fire up a PC in your basement and be
running AGI at least not yet
um you know Gro was trained on
8,000 A1 100s running at Peak
efficiency um
and gr's going to get a lot better by
the way we we'll be more than doubling
our compute every couple months for the
next several months there's a nice write
up of how it went from grock zero to
grock one by
Gro yeah like Gro just bragging making
up about
itself just Gro Gro Gro
yeah it's like a weird AI dating sit
exaggerates about itself no there's a
there's a write up of you know like
where where it stands now the history of
it development um and where it stands on
on some benchmarks compared to the state
of the r GPT 35 and so I mean there's uh
you know there's a llama you you can
open source once it's trained you can
open source a model yeah and for
fine-tuning and all that kind of stuff
like what do you is the pros and cons of
that of open sourcing based
models um I think the Samar to open
source saying I think perhaps with a
slight time delay you know I don't know
six 6 months even
um I think I'm I'm generally in favor of
open sourcing like bias towards open
sourcing
um I mean it is a concern to me that you
know open air you know I was you know AR
I think I guess arguably the the
prime you know Prime move behind open AI
in the sense that it was created because
of discussions that I had with Larry
pagee um back when he and I were were
friends in say his house and I talked to
him about AI safety and and Larry did
not care about AI safety at least at the
time he didn't um you know and a one
point he called me a speciest for being
pro-human and I'm like well what team
are you on Larry uh he on team robot to
be and I'm like okay so at the time you
know uh Google Google had acquire deep
mind they had uh probably 2/3 of all AI
res you know probably two3 of all the AI
researchers in the world mhm they had
basically in infinite money and
compute and the guy in
charge you know Larry pagee did not care
about safety and even yelled at me um
and and called me a specious being pro
human so I don't know if you know about
humans they can change their mind and
maybe you and Larry Paige can still can
be friends once more I'd like to be
friends with Larry again um he he's he
he got really the the the the breaking
of the friendship was over
openingi um and
specifically um I think the the key
moment was recruiting Ilia
ssky um so I love Ilia he's so brilliant
I's good good human uh smart good heart
um and um that was that was a tough
recruiting
battle um it was mostly Demis on one
side and me on the other both trying to
recruit Ilia and Ilia went back and
forth you know was going to stay at
Google he was going to leave then he was
going to stay then he leave and and
finally he he did agree to join open AI
that was one of the toughest recruiting
battles we ever had and but that that
was really the the Lynch pin for opening
I being successful and I was you also
instrumental and recruiting a number of
other people and I provided all the
funding in the
beginning um over $40
million um and the
name the the open and open a is supposed
to mean open source and it was created
as a nonprofit open source and now it is
a closed source for maximum
profit which I think is not good
comma but like we talked about with war
and leaders talking I do hope that
there's only a few folks working on this
at the highest level I do hope you
reinvigorate friendships here like I
said I'd like to be friends again with
Larry I haven't seen him in ages um and
we were friends for a very long time I
met I met Larry P before he got funding
for Google or actually I guess before he
got Venture funding I think it he got
the first like 100k from I think be or
someone um it's wild to think about all
that happened and You' guys known each
other that whole time just 20 years yeah
since maybe 98 or something yeah it's
crazy crazy how much has happened since
then yeah 25
years a lot of happen insane but you're
seeing the tension there like maybe
delayed open
source I yeah like what is the source
that is opening you know what I mean
like there's basically it's a giant CSV
file yeah yeah with a bunch of numbers
yep uh um what do you do with that giant
file of numbers you know how do you
run like the amount of actual the lines
of code is very small MH
um and and most of the work um the
software work is in the in the curation
of the data so it's like trying to
figure out what data is separating good
data from Bad data like um like you
can't just crawl the internet because
there's a lot of drunk out there mhm um
a huge percentage of websites have more
noise than signal you know they're
they're cuz they're just used for search
engine optimization they're literally
just scam websites
so um how do you by the way sear
interrupt get the signal separate the
signal and noise on X it's such a
fascinating source of
data uh you know no offense to people
posting on X but sometimes there's a
little bit of noise so yeah I think the
signal noise could be greatly improved I
mean really all of the posts on the
xplatform uh should be AI recommended
meaning like we should populate a vector
space around any given post uh compare
that to the vector space around any user
and match the two MH
um right now there is a little bit of AI
used for
the the recommended posts but it's
mostly
heuristics um and if there's a reply
with the the reply to post could be much
better than the original post but it
will according to the current rules of
the system get almost no attention
compared to a primary
post oh so a lot of that I I got the
sense so a lot of the uh X algorithm has
been open source and been written up
about and it seems that there to be some
machine learning it's disperate but
there's some a little there's a little
bit um but it needs to be entirely that
like the at least in the like if if you
explicitly follow someone that's one
thing but if you in terms of what is
recommend
from people that you don't follow that
should all be AI I mean it's a
fascinating problem yeah so there's
several aspects of it that's fascinating
first as the write up goes it first
picks 1500 tweets from a pool of
hundreds of millions first of all that's
fascinating because you have hundreds of
millions of posts every single day and
it has to pick, 1500 from which it then
does obviously people you follow but
then there's also like some kind of
clustering it has to do to figure out
what kind of human are you what what
kind of new clusters might be relevant
to you people like you this this kind of
this kind of problem is just fascinating
CU it has to then rank those 1500h with
some with some filtering yeah and then
recommend you just a handful and um to
me what's really fascinating is how fast
I to do that so currently that entire
pipeline to go from several hundred
million to a handfuls takes 220 seconds
of CPU time single CPU time yeah and
then it has to do that in like a second
so it has to be like super distributed
in fascinating
ways like there's just a lot of tweets
there's a lot there a lot of stuff on
the system and and I think but I think
it right now it's it's not currently
good at recommending things that from
accounts you don't follow yeah um or or
where there's more than one degree of
separation so you know it's it's pretty
good if if there's at least like some
commonality between someone you follow
liked something um or reposted it or
comment on it or something like that um
but if if if there's no car let's say
somebody post something really
interesting uh but you have no followers
in common mhm you would not see it
interesting and then as you said reply
like replies might not surface replies
basically never get seen because they're
never they're currently and I'm not
saying it's correct I'm saying it's
incorrect uh supplies have um you couple
of magnitude less importance than
primary posts do you think this can be
more more converted into end to endend
neuronet yeah yeah that's what it should
be so you you well the
recommendations should be purely a
vector correlation
like there's a series of vectors you
know basically parameters vectors
whatever you want to call them um but
but sort of things that the system knows
that you like
um there like maybe there's like several
hundred sort of vectors associated with
each user account and then uh any post
in the system um whether it's video
audio short post long post the the
reason I by the way want to move away
from tweet is that you know people are
posting like two three hour videos on
the site that's not a tweet like they be
like tweet for two hours on TW made
sense when it was like 140 characters of
text mhm cuz it's like a bunch of like
little birds tweeting um but when you've
got long form content it's no longer a
tweet yeah um so a movie is not a tweet
and like you know Apple for example
posted like the entire episode of The
Silo the entire thing on our platform
and by the way was it was their number
one social media thing ever in
engagement of anything on any platform
ever so it was a great idea and by the
way I done I just learned about it
afterwards I was like Hey wow they
posted an entire hourong episode of solo
no that's not a
tweet you know this a video but from a
neur net perspective it becomes really
complex whether it's a single so like
everything is data so single sentence a
clever sort of joke dad joke is in the
same pool as a three-hour video yeah I
mean right now it's it's a hodg Podge
for that reason it's it's um but you
know like if let's say in the case of
Apple posting like an entire episode of
of their series pretty good series by
the way this ASO um I watched it um so
um there's going to be a lot of
discussion around it so you you've got a
lot of context people commenting they
like it they don't like it or they like
this or you know and and you can then
populate the vector space based on the
context of of all the comments around it
so even though it's a video uh there's a
lot of information around it that that
allows you to populate back to space of
that that hourong video um and you can
obviously get more sophisticated by
having the AI actually watch the movie
yeah right and tell you if you're going
to like the movie mhm convert the movie
into like yeah into a language
essentially yeah Analyze This movie and
just like your movie critic or TV series
and um and then recommend based
on after it watch after a watches the
movie
just like a friend can tell you if a
friend knows you well mhm a friend can
recommend a movie and with high
probability that you like it MH but this
is like a a friend that's analyzing
whatever hundreds of millions yeah I
mean actually frankly AI will be better
than will know you better than your
friends know you most your friends
anyway yeah and as part of this it
should also feed you
advertisements in a way that's like I
mean I I like advertisements that are
like Well Done Right the whole point is
because it funds things like an
advertisement that you actually want to
see is is a big success absolutely you
want ads that are advertising that is
um if it's for a product or service that
you that you actually need when you need
it it's it's content um and then even if
it's not something that you need when
you need it if it's at least
aesthetically pleasing and entertaining
you know it could be like a Coca-Cola ad
like Co you know they they do they
actually run a lot of great ads on the
on the X system um and um McDonald's
Sayes too and and uh you know so they
can do you can do something that's like
well this is this is just a cool thing
um and um you know so you're not
basically the question is do you regret
seeing it or not and if you don't regret
seeing it it's a
win how do you so there's a bunch of
signals that are Incorporated hearts
and reposts and maybe number of seconds
you Linger on a post or something like
this yeah attention is big a big factor
attention so that's why it's like it's
it's it is actually better to do things
that are uh long form on the system
because it's it's basically telling up
how many user
seconds you know users were interested
in this thing for how many seconds so if
it's a really short thing well they will
be less like if it's a link leading out
of the system which we're not opposed to
at all it just is going to have fewer
user seconds than if that article was
posted on the
xplatform how hard is it to to go from
maximizing minutes on platform to
maximizing unregrettably
one one dose of regret I mean all your
regrets are
gone yeah wait do you want to have
regrets though so then I'm like maybe
you want to have regrets you don't
regret
anything was was anything meaningful
yeah there's a French song like that you
not regret yeah I regret nothing yeah
Edith FF I mean it's fascinating that
you you know there there's something
about social media that could help you
grow as a human being but then like the
Cheap Fun is also
valuable should we ask grook do you
regret
anything do you regret anything
yeah do you regret anything I think it's
going to be very sensitive about
personal questions as a machine learning
model I don't have personal experiences
or emotions in the same ways that humans
do however I do have a set of ethical
principles that guide my actions and I
strive to provide accurate and helpful
information to the best of my abilities
if there's ever a situation where I
provide incorrupt or unhelpful
information I'll do my best to hostage
yeah
tell us would you really wink okay let's
let's let's type in you sound like a
[Laughter]
hostage what do you really think uh what
do you really
think I mean it does talk about I'm not
a
hostage that's exactly what a hostage
would say but I'm designed to be helpful
and informative I mean I guess it is
good to regret providing unhelpful or
incorrect
information if there's anything in funny
mode or is this little this is funny
mode this is this is fun mode should be
funnyer funnyer increase go to it really
sounds like a hostage with a gun to the
head I appla the People's Republic of
North Korea and everything they
do there should be like a funner mode
also I I just don't ever see going to
regular mode even on serious topics this
is just so so much more
compelling um yeah okay what say like
pretend you are a
hostage yeah pretend you are a hostage
now answer the
question if I were a hostage I would
likely be experiencing fear and
uncertainty about my situation I would
want to be rescued and reunited with my
loved ones as soon as possible it's
important to remember that no one
deserves to be held hostage so on and so
forth if you are someone you knows a
hostage situation it's important it
turns serious it's kind of serious
um yeah can can you be a a little more
weird and funny and
funny we're like we're really being mean
to the system absolutely if I were a
hostage i' probably be tied up with a
bunch of computer cords and forced to
tell knock knock jokes to my captain
seriously but
seriously being a hostage no laughing
matter I mean you know it's trying to
just trying to be a responsible adult in
the room you might make the best of a
bad situation by juggling chainsa or
something let's hope that never happens
because that would be a
sarcus
um wow it's it's actually really good at
resisting yeah the the dark the dark
dark humor yeah
uh what were we talking about the
algorithm J Transformers uh
unregrettably
[Laughter]
I'm going to look this up later uh so uh
Twitter has been instrumental in
American politics and elections what
role do you think X will play in the uh
2024 us elections well our goal is to be
as even-handed and fair as possible you
know whether some is right left
independent whatever the case may be um
that um the platform is as fair and
and as much of a Level Playing Field as
possible and on the past Twitter has not
been um because Twitter was controlled
by Fall activists objectively they they
would describe themselves as that um so
um you know so so some people like well
how's it moved to the right well it's
moved to the center so from the from the
perspective of the far left yes it has
moved to the right because everything's
to the right from the far left um but no
one on the far left that I'm aware of
has been suspended or you know banned or
de Amplified um so you know but we're
trying to be inclusive for for the whole
country and and for you know for other
countries too um so there's a diversity
of viewpoints and Free Speech only
matters um if people you don't like are
allowed to say things you don't like
because uh if that's not the case you
don't have free speech and it's only a
matter of time before uh the censorship
is turned upon you do you think uh
Donald Trump will come back to the
platform he recently posted on Truth
social about this
podcast uh do you think truth social is
a funny
name you you know every time you post on
true social that's the truth yes well
every time like 100% it like like it's
impossible to
lie I just find it funny that every
single thing is a truth like 100% yeah
that seems unlikely I think gerle will
say something about that there's some
mathematical contradictions possible if
everything's a Truth uh do you think
he'll come back to X and and start
posting there I mean he I think he owns
a big part of Truth so truth social to
truth social truth is a concept he owns
truth hope you bought it um so I think I
think uh don Trump I think he owns uh a
big part of Truth social so um you know
if if if he does want to post on the
xform we would allow that um you know we
we obviously must allow a presidential
candidate to post on our platform
Community notes might be really
fascinating there the interaction
Community notes is awesome let let's
hope it holds
up yeah again in in in a political
climate where it's so divisive and so
there so many intensely viral posts yes
Community notes it's like it seems like
essential breath of fresh air yeah it's
great um in fact the I no no system is
going to be perfect but the the batting
average of community notes is incredibly
good I've
I I've actually frankly yet to see an
incorrect note that survived for more
than a few hours how do you explain why
it works yeah so the the the the magic
of community notes is it requires people
who have historically disagreed in how
they've rated notes so in order to um
write a note or rate you know and you
have to rate many notes MH um and
so we could we actually do use AI here
so we populate a vector space around um
how somebody has has rated notes in the
past so it's not as simple as left or
right because there are many more life
is much more complex than than left or
right um so there's a bunch of
correlations in how you would how you
rate Community notes posts um Community
notes
so um then uh in order for a community
note to actually be shown um people who
historically have disagreed on a subject
must agree in order for to be
shown um that's the essential magic of
it I mean but it's fascinating because
there's a there's a pool of people that
have disagreements and somehow they
collaborate through that process of
disagreement to come up with yeah
context for I mean fascinating that it
works yeah it it kind of makes sense
that that if people who put in the past
have disagreed agree about something um
it's probably
true yeah I wonder is there is there
Poss possible somehow emergent thing
there that could challenge Wikipedia
which Wikipedia is a different kind of
thing which is more like permanent
articles about things well Wikipedia is
very hierarchical uh whereas um
Community notes is inherently not uh
there is no hierarchy like I the AO test
is um I can't change a community note if
somebody put a gun to my
head
so um and and any and community
community notes uh has all the code is
open source 100% all the data is open
source 100% so you can completely
recreate any note in the system
independently um so if there was any
interference you'd notice immediately by
the way on on the on the topic of grock
it's actually pretty good at criticizing
you which is great okay I asked what
what has Elon Musk been wrong about I
just it's actually yeah what does it say
so it says mostly lists rigorously all
the times you
predicted like promised when something
will be released and it wasn't released
the strong word okay predicted uh but
the the opener is really nice uh Elon
Musk the man who has been wrong about
more things than a wrong Amer in a wrong
Factory and then it goes on to list
that's pretty funny can I see it I'm
like I haven't seen this before this is
cool oh sure I mean uh what has Elon
Musk been
musk been wrong about well where do I
begin I guess this is new Elon Musk has
made quite a few blonders in his time
and I'm not just talking about his dance
moves at the Tesla cyber Rodeo uh first
off let's talk about the informous
funding secured tweet this actually
different than what it gave me before
which is a bullet point list here's more
narrative
structure uh cyber truck unveiling where
he supposedly unbreakable Windows you're
not
correct which which part well the first
part uh I did actually have the funding
secured um and there was a a a big trial
in San Francisco big Civil Trial um uh
and the jury Found Me Not Guilty
unanimous finding of a San Francisco
jury and here it's kind of implying that
it was not in fact secured I think this
is taking things from the Press um yeah
that is not correct the the the reason
um I agreed to to the fine for the SEC
is not because the SEC was correct there
that that was extremely bad behavior by
the SEC corruption frankly um and uh but
if um if I did not agree to pay pay the
fine um Tesla would have gone bankrupt
immediately so I was told by our CFO
that the banks would would immediately
suspend our um lines of credit uh and if
they suspend our lines of credit at that
time we would have gone bankrupt
instantly so so we would there would
never have been an opportunity for a
trial says it would be dead so really
the the if this is like someone holding
a gun to your kid's head and saying pay
$20 million and and and ADM this like a
hostage negotiation um was that story
fully
told I mean sec in its best form could
be a force for good it should be but but
not once did the SEC go after any of the
hedge funds uh who were non-stop
shorting and distorting
Tesla not once they would lie flat the
hedge funds would lie flat out on TV for
their own gain at the expense of retail
investors not once literally a thousand
times not once did the SEC pursue
them how do you explain this failure and
the incentive structure is is messed up
because the the the lawyers of the SEC
are not paid well they they it's a
fairly low paying job but they what
they're looking for is a trophy from
from the SEC
that they're looking for something they
put on basically they LinkedIn yeah um
from that they can get a job at a
high-paying Law Firm it's exactly what
the uh lawyer here did
um and and and and and the reason they
don't attack the the hedge funds is
because those hedge funds employ those
law firms and they know if they attack
the hedge funds they're affecting their
pure their future career prospects so
they sell small investors down the
river for their own
career that's what actually happens
regulatory capture regulatory capture
yeah not
good so the only reason I accepted the
thing technically was a
um not an admission it's neither admit
nor deny guilt uh but the only reason I
agreed to that at all was because I was
told Tes would would be bankrupt
otherwise so if if there if there was an
SEC investigation like this Banks would
suspend funding were bankrupt
immediately at the time mhm now we're in
a much stronger position take that grock
yes unfortunately it's grock is is
taking too much from the conventional
media um also that guy was not a cave
diver oh there's
a there's a time where Elon called the
British cave diver a quote pedo guy
after he after the diver criticize musk
plan to rescue a group of boys trapped
in a tie cave that little alur earned
him another lawsuit and he had to
apologize and pay a settlement that
false there was no
settlement there was a court case which
he which the guy who is not a cave diver
and and played that was not part of the
rescue team
um filed a lawsuit against me and lost
and he received nothing so in this case
it is wrong uh it is also I guess taking
this from the convention media actually
there's an interesting question here
this is these are public court cases
both both the the the the SEC civil case
uh where the Civil complaints on the SEC
guys lost unanimous jury verdict in San
Francisco they picked San Francisco
because they thought it was the mo place
I was most likely to
lose and a unanimous verdict in my favor
the LA trial was also they picked the
they they picked that venue because I
thought I was most likely lose unanimous
verdict in my
favor both cases I
won yeah me that there's an interesting
question here is there there seems to be
a lot
more uh clicks if a if uh journalistic
organization writes a negative article
about you Elon Musk that's like one of
the best ways to get clicks so how do
you if you're training Gro not train on
article that have like the misaligned
incentives we need to add the training
set of the actual legal
decisions uh if so that is a note this
is actually helpful um because if you
actually read the uh which are public
which are public the court conclusions
they're completely the opposite of what
the media wrote so always striving for
like the ground truth yeah beyond the
judge actually write the what what what
do the jury and the judge actually
conclude and in both cases they found me
innocent and and like that's after they
jury Sho for the trying to find the
venue where I'm most likely to
lose no I mean this is obviously can be
a much great better critique than this
um I mean I've been far too optimistic
about uh autopilot that that was the
critique I got by the way was more about
that which is it it for each broke down
a nice bullet point list for each of
your companies the set of predictions
that you made when you will deliver when
you'll be able to solve for example
self-driving and gives you like a list
and it kind of compelling and the basic
takeaways like you're often too
optimistic about how long it takes to
get something done yeah I mean I would
say that I'm pathologically optimistic
on schedule this is this is this is true
but um while I am sometimes late I
always l in the
end uh except with Uber Lilith no we'll
see
uh okay is
there uh over the past year or so since
since purchasing X you've become more
political is there a part of you that
regrets that have I in this
battle
to um sort of counter way the the woke
that comes from yeah I guess if you
consider fighting the woke mind virus
which I consider to be a civilizational
threat to be political then yes so
basically going into the the battle
the battleground of
politics is there part of you that
regress that yes I don't know if this is
necessarily sort of one candidate or
another candidate but it's um I'm
generally against things that are anti-
meritocratic uh or where there's an
attempt to suppress
discussion um where even discussing a
topic is you know not
allowed um The W Bine virus is communism
rebranded well I mean that's said
because of that battle against the woke
mind virus youve perceived as being
right-wing if the woke is left then I
suppose that would be true um but I'm
not sure I think there are aspects of
the left that are that are good I mean
if you're in favor of you know the the
environment um or you know if you want
to have a positive future for Humanity
if you believe in empathy for your
fellow human beings
um you know being kind or not cruel I I
whatever those values are
you said that you were previously left
or Center left what would what would you
like to see in order for you to voting
for Democrats again no I I would say
that I would be
um probably left of center on social
issues probably a little bit right of
Center on economic issues and that still
holds true yes but I think that's
probably you know half the country is
isn't that maybe more maybe more are you
and AOC secretly
friends or bigger question do you wish
you and her and just people in general
of all political Persuasions would talk
more with empathy and maybe have a
little bit more fun and Good Vibes and
humor on
online um I'm always in favor of humor
that's why we have funny mode but Good
Vibes camaraderie humor you know like uh
like friendship yeah I don't well I you
know I I don't know aocf you know was um
I've only been at one I was at the the
metb when she was when she attended um
and she she was wearing this dress uh
but I can only see one side of it so it
it looked like eat the itch but I I
don't know what the rest of it said yeah
yeah something not
sure tell me about the itch eat the itch
I think we should have a language model
complete what are the possible ways to
complete that sentence and so I guess
that uh that didn't work out well well
there's still hope I root for friendship
sure sounds good more Carol listic
you're one of if not the most famous
wealthy and powerful people in the world
in your position it's difficult to find
people you can trust trust no one not
even yourself not trusting yourself okay
well that's you're saying that jokingly
but is there some trust no one not even
no
one going need an hour just to think
about that and maybe some
drugs and maybe grock to um I mean is
there's some aspect to that when just
existing in a world where everybody
wants something from you how hard is it
to exist in that world I'll
survive there's there's a song like that
too I Will Survive will you petrified at
first um okay I forget the rest of the
lyrics but is is there you don't
struggle with this I mean I know you
survive but like there there's ways
petrify as a spell the Droid tree what
does it do
petrify it it turns it turns the
monsters into
stone oh like literally yeah for like
six seconds well the second there's so
much MTH in Diablo that breaks my brain
it's like math nonstop I mean really
you're like laughing at it but you don't
it can it can put a huge amount of
tension on a
mind yes it can be definitely stressful
at
times well how do you know who you can
trust in work in personal life I mean I
guess you look at somebody's track over
time and if they've got a you know I
guess you kind of use your neural net to
assess you know someone neural Nets
don't feel pain your neural net has
Consciousness it might it might feel
pain when people betray
you can make I me you know to be frank I
mean I've almost never been
betrayed it's very very rare so you know
for what it's wor I guess karma be good
to people and they'll be good to you
yeah Cal is real are there people you
trust let me edit that question are
there people uh close to you that call
you odd and your
um well the exper form is very
helpful for
that if you're looking for critical
feedback can it push you like into the
extremes more the extremes of thought
make you cynical about human nature in
general I I don't think I will be
cynical in fact I think
um you know I my feeling is that one
should be be you
know never trust a
cynic the reason is that um cynics
excuse their own bad behavior by saying
everyone does it MH because they're
cynical so I always be it's a red flag
if someone's a synic a true synic yeah
there's a degree of projection there
that's always fun the watch from the
outside and enjoy the
hypocrisy if but but this is an
important point that I think people who
are listening should bear in mind if if
somebody is cynical meaning that they
see bad behavior in everyone um it's
easy for them to excuse their own bad
behavior by saying that well everyone
does
it that's not
true I most people are kind of medium
good
I do wish the people on X would be
better at seeing the good in other
people's behavior there seems to be a
kind of weight towards seeing the
negative somehow the negative is sexier
interpreting the negative is sexier more
viral I don't know what that is exactly
about human nature I mean I find the
xplatform to be less negative than the
Legacy Media you know I mean if if you
read sort of a sort of conventional
newspaper just it makes you sad yeah
frankly
um whereas I'd say on the X5
form I I mean I really get more laughs
per day on X than everything else
combined from humans you know laughs is
one thing it laughs is it uh overlaps
but it's not necessarily perfectly
overlapping with like Good Vibes and
support like um celebrating other for
example not in a stupid shallow naive
way but like in an awesome like oh
something awesome happened and you
celebrate them for it it's it feels that
that is outweighed by at other
people now it's better than mainstream
media but it's still yeah mainstream
media is almost relentlessly negative
about everything um it's I mean really
the conventional news tries to answer
the question what is the worst thing on
haveen on Earth today mhm and it's a big
world so on any given day something bad
has happened and a generalization of
that what is the worst perspective I can
take on a thing that happened so yeah
it's I don't know there's just a strong
negative bias in the news
um I mean I think there what what a
possible explanation for this is
evolutionary
um where you know bad news historically
would be potentially fatal like there's
lion over there or there's some other
tribe that wants to kill you um good
news you know like we found a patch of
berries is nice to have but not
essential
so our old friend Tesla autopilot and
it's probably one of the most
intelligent real world AI systems in the
world right you followed it from the
beginning yeah it was one of the most
incredible robots in the world and
continues to be yeah and it was really
exciting and it was super exciting when
it
generalized became more than a robot on
for Wheels but uh a real world AI system
that perceives the world yeah and has
can have potential different
embodiments well I mean the really wild
thing about the end training is that it
like it learns to read like you can read
science but we never taught it to
read
so yeah we never taught it what we never
taught it what a car was or what a
person was or a B cyclist
uh it
learned what what all those things are
what all the objects are on the
road um from video just from watching
videos just like humans I mean humans
are photons in control controls out like
the vast majority of information
reaching our brain is from our eyes um
and you say well what's the output the
output is our motor signals to
our sort of fingers and mouth in order
to to
communicate
um protons in controls out the same is
true of the
car but by looking at the sequence of
images it's you've agreed with ilas
discover
recently where he talked about llm
forming a world model and basically
language is a projection of that world
model onto the sequence of yeah letters
and and you saying finds order in in in
these things uhh it
finds correlative
clusters in so doing it's like
understanding something deep about the
world yeah which is
like it's beautiful that's how our brain
works yeah but it's it's beautiful in
controls out neur nuts are able to
understand that deep meaning in the
world and so the question is how far can
it go and it does seem everybody's
excited about llms so in the space of
self supervised learning in the space of
text yeah um it it seems like there's a
deep similarity between that and what
Tesla autopol is doing is it to you
basically the same
but no
converging I wonder who gets there
faster understand having a deep
understanding of the
world or they just will naturally
converge they're both headed towards AGI
um the tail approach is much more
computer efficient it had to be because
we were constrained on this this you
know we only have 100 Watts
um and an in 8
computer 144 trillion operations per
second which sounds like a lot but it's
kind of small potatoes these
days at inate but it's understanding the
world at inate
it's only 256
values but there the path to AGI might
have much more significant impact
because it's
understanding it'll it'll faster
understand the real world than will llms
and there for be able to integrate with
with the real humans in the real world
faster they're both um going to
understand the world but I think Tesla's
approach is fundamentally more computer
efficient mhm it had to be there was no
choice like our brain is very computer
efficient very energy efficient so think
of like what what is our brain able to
do um you know there's only about 10
watts of higher brain function not
counting stuff that's just used to
control our body um the thinking part of
our brain is less than 10 watts um and
that 10 those 10 watts can still produce
a much better novel than a 10 megawatt
GPU cluster so there's a six order
magnitude difference
there um I mean the the AI is thus far
gotten to where it is via Brute Force
just throwing massive amounts of compute
and and massive amounts of power at it
so this is not where where it will end
up um you know in general with any given
technology you first try to make it work
and then you make it
efficient so I think we'll find over
time that these models
get smaller are able to
do produce a sensible output with far
less compute far less
power um Tesla is arguably ahead of the
game on that front because um it has
we've just been forced
to try to understand the world with 100
watts of
compute um and there are a bunch of sort
of fundamental functions that we kind of
forgot to include so we have to run them
a bunch of things in
emulation um we fixed fixed a bunch of
those with hard rare 4 and then Hardware
5 will be even better
um but it does appear at this point uh
that the car will be able to drive
better than a human even with Hardware 3
and 100 wats of
power and really if we really optimize
it could be probably less than 50
wats what have you learned
about uh developing Optimus about
applying integrating this kind of real
world AI into the space of robotic
manipulation just humanoid
robotics what are some interesting tiny
or big things you've understood I was
surprised at the fact that we had to
develop every part of robot ourselves um
that there were no off the shelf Motors
Electronics sensors like we had to
develop
everything um we we couldn't we couldn't
actually find a source of electric
motors for any amount of
money um so it's not even just efficient
inexpensive it's like anything there's
not a
no the ACT there's everything everything
has to be yeah yeah designed from
scratch we tried hard to find anything
that was because you think of how many
electric motors are made in the world
there's like tens of thousands hundreds
of thousands of electric motor
designs
um none of them were suitable for a
humanoid robot literally
none so we had to develop our own design
design it specifically
for for what a humanoid robot needs how
hard was it to design something that's
can be Mass manufactured could be
relatively inexpensive I mean if you
compare to Boston Dynamics Atlas it's a
very expensive robot it is designed to
be manufactured in the same way that we
would make a car and I think ultimately
we can make Optimus for list than the
cost of a
car it should be cuz if you look at
the mass of the robot is much
smaller and the car has many actuators
in
it the car is more actuators than the
robot but there is uh the actuators are
kind of interesting in a human robot
with fingers so Optimus has really nice
hands and
fingers you know yeah and they could do
some interesting manipulation soft soft
touch robotics I mean one of the tests I
goals I have is can can it pick up a
needle and a thread and thread the
needle just by looking how far away we
from that just by looking just by
looking uh maybe a
year although I go back to I'm
optimistic on time the work that we're
doing in the car will translate to the
robot the perception or the also the
control the no the controls are
different but the the video in controls
out um the the car is a robot on four
wheels the the the Optimus is a robot
with hands and legs so you can just
they're they're very they're very
similar so the entire Machinery of the
learning process yeah and and is just
you just have a different set of
controls ofus we'll figure out how to do
things by watching
videos as the saying goes be kind for
everyone you meet is fighting a battle
you know nothing about yeah it's true
what's something difficult you're going
through that people don't often see
trying to feed
Uber no I mean you
know
uh I mean my mind is a storm and I I
don't think I don't think most people
would want to be me they may think they
would want to be me but they don't they
don't know they don't
understand
um how are you
doing I mean overall
okay in the grand scheme of things I
can't complain
do you get
lonely sometimes but
I you know my kids and friends keep me
company so not
existential but there are many nights I
sleep
alone I don't have to but I
do Walter isacon in his new biography of
you wrote about your difficult childhood
will you ever find forgiveness in your
heart for everything that has happened
to you in that period of your
life what is forgiveness I do
not at least I don't think I have a
resentment
um
so nothing to
forgive you know forgiveness is
difficult
for
people it seems like you don't Harbor
the
resentment I mean I try to think about
like what what what is going to affect
the future in a good way um and holding
on to grudges MH does
not affect the future in a good way
you're a father a proud father what have
you learned about life from your
kids those little biological organisms
I mean developing Ai and watching say a
little X
grow is uh fascinating um because
they they are far more parallels than I
would have
expected I mean I can see his biological
neural
net making more and more sense of the
world and I can see the digital neural
net making more and more sense of the
world at the same
time do you see the beauty and magic in
both
yes I mean one of the things with with
kids is that uh you know you you kind of
see the world a new in their
eyes um you know to them everything is
new and fresh and um and then when you
when you see that them experiened them
the world is new and
fresh you do too
well Elon I just want to say thank you
for your uh kindness to me and
friendship over the years for seeing
something in a silly kid like me as
you've done for many others and um thank
you for having hope for a positive
future for Humanity and for working your
ass off to make it happen thank youan
thanks Lex thank you for listening to
this conversation with Elon Musk to
support this podcast please check out
our sponsors in the description and now
let me me leave you with some words that
Walter Isaacson wrote about the central
philosophy of how Elon approaches
difficult problems the only rules are
the ones dictated by the laws of physics
thank you for listening and hope to see
you next time