Computing: The first 100 years (Joe Armstrong) – Full Stack Fest 2016



>> Thank you very much. The title's a bit
misleading. It's not really the first 100 years. It's the first 68 years because I think
computing started in 1948. If by computing we mean a programmable device where you can
change the program in memory. So the first 68 years is what I'll be talking about. But
it's 100 years, so I'm going to be guessing what's going to happen in the next 32 years.
So part of this is speculation of what's going to happen in the next 32 years and part of
its history what happened in the last few years.
So I'll start with my quote. The best way to predict the future is to invent it. So
I'm going to be inventing a little bit of future and see if we can do that. And why
am I doing that? I give quite a few talks, and I meet a lot of programmers. And programming
tends to be a fairly young skill. So first, I would ask how many of you are 45 and under?
Right. So I've been programming for more than 45 years. So I've been programming for more
years than your entire lives. And what I've noticed is I kind of assume that if you're
30, 40, something like that, that you actually knew what happened before you were born. And
that's not the case. The more I talk to people, the more I'm convinced that you don't actually
know what happened before you were born. You might have read about it in books. Some of
you haven't even read about it in books. For me, it's not a question of reading about
it in books because I was there and did it. So I thought I would tell you some of these
things that happened. So I have two themes in this kind of lecture, which I'm developing.
One is to try to tell you about the stuff that we collectively have forgotten. When
I say "we," I mean the entire programming community. There's a lot of stuff we've forgotten
or perhaps never knew. And I want to tell you about some of those things, and I will
be developing this lectures and talks I'm giving.
And the second thing is the new technologies that we are inventing are not without danger.
I think that computing is rather like kids running into a sweetie shop and just, oh,
we can build this, and we built this stuff. You don't really know what —
An indication of where we should be working the future. Solve those dangers, do something
about it. Me and my colleagues have made a complete mess of everything. And then at the
moment I'm retired so having fucked up absolutely everything, off we go, and you guys can fix
it up. I also thought a conference like this, it
should be a bit of fun. And I think it's very good that people meet each other. So I'm going
to do an experiment, which the idea occurred to me in my last week actually, and I thought,
oh, how could I illustrate parallel programming? And how could we do things? So I got myself
this, which is — this is going to be very noisy because you're all going to be talking
at once. So can you hear that? Anybody not hear that?
Right so the goal of this is to get to know each other because some of you know each other
when you're sitting next to each other. But others are total strangers who don't know
each other. So I'm going to do a parallel algorithm and some algorithms. So you introduce
yourself to this guy. And when you found that, you introduce yourself to this guy. Now, I
assumed you're all sitting next to each other. So you have to shout over to this guy and
we'll propagate like this, and it will go to here, and it will go backwards and forwards.
And if I hit this a couple of times, you stop. Okay? That's the first rule. So off you go.
Now, this isn't going to work, is it? No. So this is the first algorithm. We all have
to introduce each other. I assume a kind of regular — oh, it went.
I kind of assumed a regular pattern was odd and even people. Now, if you were talking
— you two are talking — you're talking to him, you can't be listening in that direction.
So you can only talk in one direction. You can't be both talking and listening at the
same time. If I turned to the left and speak in that direction, I'm not going to hear something
that comes from the opposite direction. And some of you have never met before, and there
are some very attractive people in the audience. So if, you know, you should fall in love with
the person who you're sitting next to because of this introduction and have five kids and
if they become artists, I expect you to send me a free ticket to the circus. So something
good will have come out of this. So here was the first algorithm. And just
for a regular matrix of N by M things. You just — where's my pointer? There's my pointer.
You go like this. And then when you get to the end, you turn around again and do it in
the opposite direction and then everybody will know each other. And that's a pretty
bad algorithm. So we'll make a much better algorithm. Now, fortunately, you know what
seat numbers you're on. If you don't, you'll have to stand up and look at the seat under.
You're either on a odd-numbered seat or even-numbered seat. So find out your seat number. This is
when it's going to be noisy. Okay. You all know your seat numbers; right?
So the — you're clear if you're an odd or even, why can't you? Everybody knows. Good.
So odds talk to the right, evenings listen to the right. And then path two, odds listen
to the right and path three, even listen to the left and — can you read that? And I'll
give a little ding to change the passes. So on the first ding, odds talk to the right
and evenings listen to the left. Good. So how long did this algorithm take?
What was that? Battery. Okay. So the sequential algorithm took two times NM and the parallel
took four. So if we were 50 by 50 matrix, the speed up would be a factor of 500. So
parallel algorithms are much nicer than sequential algorithms.
Parallel programs do it in Erlang or Elixir. We're building lots of multicorresponds and
lots of problems are parallel problems. Right so that was the little interview and goodness
knows how long the rest of the lecture is going to take.
So history. For me, I think history starts in 1948. And this guy, Tom Kilburn is the
world's first programmer. And he's standing there with something calls a Williams Kilburn
tube. And that was a tube that could store or display — I think it was 1,024 bits, and
I think they expended it. So actually the program and the state of the program and all
the data was in 1,024 bits and displayed on a tube. And this could store memory for up
to one hour. It was developed in the United Kingdom. And this is Kilburn's logbook and
the date. What do we press? The date is up there. It's the 19th of June — is that June?
Yeah, 19th of June, 1948. And that's the first program there. And actually worked out the
factors composite numbers. So put a prime number in, the highest factor was one, which
meant that it was a prime number. And it ran on the 19th of June, 1948. And there's the
program a little bit more clearly written out.
And that ran on, this machine. And Freddie Williams wrote a program was laboriously inserted.
And it lead the to no useful result. One day it stopped. And then shining brightly at the
expected place was the expected answer. It was a moment to remember. June of 1948. And
nothing was ever the same again. And he didn't actually realize how true that
was because this was the start of the computing age. This is the start of this 100-year period
I'm talking about. And we're now two-thirds of the way through that period. Computing
is an incredibly young science. I mean it's — you know, you compare it to things like
100 years war. I think this is an incredibly short period of time. And it has progressed
very rapidly in the last 10 to 15 years. And here is the Williams tube at the Manchester
museum of science. This is a replica they built of the small experiment machine. And
here I am. On my holiday, I go and look at old computers and take my wife around to all
of these museums, and she loves looking at old computers I think. I'm not quite sure.
She says she likes it. Actually got to put a program into this thing. And you enter the
program here by sticking numbers in and then you hit enter. Lovely machine.
Oh, and there's a number there. .000004375 and this is my normalization factor. I'm taking
one because the Cray one is the first supercomputer. And I love the Cray one. I'm going to show
you a few supercomputers. So the next machine actually it doesn't have
a number because I wasn't able to work out how fast it was. So I've just put a few question
marks. It's probably .001 of a Cray one, and it's a DDP516. And this was the first computer
I got to play with all by myself. And the programs were entered — well, actually you
see this thing up here? Those are called sense switches. The first program when you booted
the thing, you had to enter a number on here. This is a 16 bit figure. You put the 16-bit
and press load and store and enter the first program. Now, the first program is a program
that reads a paper tape. Right and so once you've entered the first program, which takes
about half an hour because there's a lot of instructions, then you can run it. Whoops.
Sorry I'm pressing the wrong button. You push it into this paper machine, the telly type
here. And then you run the first machine and the first program is a program that can read
programs from the card reader. And then you put your punch cards into the card reader,
which I haven't shown there. And it reads them all in and off you go.
Now, this had — let me see. Whoops. That's the next slide. This had 32 kilobytes of 16
bit memory. Big programs couldn't fit into it so you had the first bit and then the second
bit, and it's rather slow. And when we had these things, we got something
called the glass TTY, it's a terminal. And you could actually enter your programs not
on punched cards but you could sit at this glass TTY, the screen with a little keyboard,
enter them and store them on disk. Oh, this is fantastic. This is really improved turn
around. And I said to my boss, you know, one day everybody will have glass TTYs to enter
their data. And everybody will store their programs on disk. And he said Joe, you're
mad. You're completely a lunatic. That will never happen. I said why? And he said, well,
the disk costs, you know, 20,000 euros or something like that and the glass TTY cost
10,000 euros. Far too expensive. Nobody will ever do this in the future. Guess who was
right? Joe one.
So in 1975, the @Cray-1 came out. Now, this was the first supercomputer. It looked like
that. It even came with a tailored leather seat around the outside that you could sit
on. And it's circular so that — to minimize the cable length between the separate units.
So these are the CPU and the memory units. And it was the world's first supercomputer,
which is why it's pretty exciting. It had an 80 megahertz. Isn't that extremely fast?
It consumed 115 kilowatts of power and weighed 5.5 tons and cost $10 million and had 8 megabytes
of memory. I mean this was fantastic. I — I used to be a physicist, and I was a summer
intern, and I ended up in the program advisory office. And I could program the Cray-1. There
was one in all of Europe. All of Europe had one supercomputer. And I could program it.
Wasn't allowed to sit on the bench. Only the guys in the white coat could sit on the bench.
I didn't have a white coat because I was in the back office, but I could program the Cray-1.
And it was so fast that you didn't put punch cards on in. It was a load of IB360s that
did the io and punch cards then talked to the Cray-1 that did the work instantaneously.
There's a lot of good physics. The omega minus particle. Discovered using the Cray-1.
So here's me next to the Cray-1. I sat on the people before people told me to stand
because I couldn't sit on it. Great place to go. If you're ever in Great
Britain, go to the national museum of computing. They've got the computer that Tim did the
World Wide Web on. Full of exciting things. There you go.
So the next computer is the Vax11/780. This came out in 1975. This was kind of computing
for the masses or for people in scientific labs. We got vaxs the 11/780 was .00625 of
a Cray-1. It wasn't as powerful of a Cray-1. But I don't know if anybody heard the integration
of Vax mips, million instructions per second. It was the first commercial computer that
you could buy for a reasonable amount of money that did a million per second. And it ran
at .00625 speed of the Cray-1. It was pretty seventh. I didn't have 11/780, we had the
cheaper model the 11/750 on, and that's what I developed Erlang on. They came later, somebody
started the first bit terminals, you had to type your program in there. This is before
the day of full screen editors. Just line editors and everything. And then somebody
thought we could make a full screen editor, so we did.
And I'm just going to hop forward a little bit. This guy is 256 times a Cray-1. I gave
a lecture, and I was waving my iPhone and I said do you realize this is more powerful
than a Cray-1. And I hadn't checked my figures. This little fella is 256 times the Cray 1.
This is 256 times as powerful as the most powerful computer in the world in 1975. Okay.
So we can do Pokémon Go and all sorts of things. You know, really useful things.
[Laughter] Right this is lovely. I love this. This is
15 Cray 1s. It's a raspberry pi. I was in Chicago and someone said can you run Erlang
on a weak computer like a raspberry pi, and I said you're joking. You're joking. You're
talking about a supercomputer. Was developed on a machine that is infinitely weaker than
this. This is 15 times the power of a Cray 1. 15 times more powerful than the most powerful
computer in the world. Do I get the impression when I use it's faster than the Cray 1? No,
I don't actually. Because the software is fucked because they put megabytes and gigabytes
of rubbish onto it before it even boots. This is something you have to fix. An operating
system — an old operating system back in 1980 was 1.5 megabytes. Okay? An update of
keynote on my Mac is like 100 megabytes; right? It's 80 times — 70 times the size of an entire
operating system in the mid-'70s and I can't understand why. What the hell is in this 100
megabytes. Even if it's full of images and things. How can it be so big? Could it be
that Apple are putting huge programs on your disk so that you have to buy a more expensive
computer? I wonder, you know? What are they up to? And don't get me on the cloud. Why
— sorry. Blackmail by storing all of your stuff on the cloud.
Right. This is the Nvidia Tesla P100. Which is 66,000 times the power of the Cray 1. This
is scary stuff. This is the sort of thing that you're going to use to beat the world
champion at machine learning algorithms. This is going to be the thing that's going to cause
mass unemployment and vast number of jobs if they program to program it. The only problem
is programming it. If we can program that to do machine learning, it's going to take
over all sorts of jobs and things. It's a really scary machine. Fortunately, there's
an even more — I mean this is 66,000 times more powerful than the Cray 1. But we've got
this fella here. And that's ten to the eight times power of the Cray 1. Runs at 38 petaflops
and at the moment we hold the world record of computing power. So the hardware hasn't
caught up with us yet and has 86 billion neurons in it and gone through a lot of generations.
It's a pretty good computer actually. This is our defense against this thing. We unplug
it. That's later to win. Okay. Timeline. Could somebody tell me what
time I have to finish? Does anybody know? Oh, dear. I think I'm supposed to finish at
10:00. So I have to rush through stuff. Skip through that. Storage is the same story really.
Here's me next to a four megabyte disk in the museum of computing. The photo isn't really
good but as you can see it comes up to here. So the notion of digital photography, every
picture is, like, 4 megabytes and digital music. You know, 4 megabytes per song. Digital
music and digital photography are enabled by massive memories. It's a technology shift.
There's not going to be digital music when you carry that thing around. It weighed — what
does it weigh? It doesn't say what it weighs. I didn't try picking it up. They wouldn't
let me. I didn't try. It probably weighs about 30 kilos I guess. Cost $100,000. And you're
not going to have it in your backpack or anything. So storage is made a massive gain. And that
mobile data. This is the first mobile phone. System A956 weighed 40 kilograms. So, again,
not very useful for mobile computations. But you can see how it has gone on. It's all baked
into an iPhone, and we now have — just to summarize. Now from 1948 to 2016, computers
are insanely fast. They are ridiculously fast. So why are people worried about efficiency?
Because the machine is just so stupid and fast, we don't need to bother.
And how do you make a program speed up? How do you make your program go 1,000 — a million
times faster than the first time I made it. Why is that? Because 20 years has past. If
you wait ten years, your program will go 1,000 times faster. If you wait 20 years, it will
be a million times faster. I don't see that stopping. That's not going to happen. It's
going to carry on like that. We've got massive amounts of memory, terabytes
of memory. The only reason we don't have terabytes of memory in our phones, the only reason we
have gigabytes of memory is the rate at which memory manufacturers releases memory into
devices. Because basically they want to charge you money. They could give you 1,000 times
more memory tomorrow if they wanted to. But then they can't sell you double the memory
every year. So that's the only reason why we don't have massive memories. And we're
going to have massive bandwidth. We're going to go over from wireless to using lasers.
When you put LED lightbulbs in your rooms, you can modulate information on that. So you
can use white light lasers instead of that. So all you have to do is screw out your lightbulbs,
put in Wi-Fi lightbulbs and easily going at 10 gigabits per second. Good to have billions
of small computing devices, some people call it the Internet of useless things and you
don't know what to do with them. I — listening to the radio and this guy is, oh, every household
is going to have 500 devices. We're going to have pillows that tell you when they need
washing. And my wife said that's absolutely just what I need. A pillow that talks to me
and tells me when I need washing. And some of you are going to work on this stuff. Isn't
that wonderful? Yeah. It's great. There are other projects that you could work
on. So what's going to happen in the next 50 years?
Sorry? >> You have until 10:10.
>> Oh, 10:10. Thank you very much. Good. So what's going to happen? Rhetorical question.
Do you think this development's going to stop? I've seen the last 45 years of this. If you're
20 or 25, you're going to be programming for another 20, 30 years, do you think this development
is suddenly going to stop? No, of course it's not going to stop. It's
accelerating if anything. It's very exciting actually. The first 100 years of any science,
from 1600 to 1700, newton and physics exploded in the first 100 years and then slowed down.
We're in this 100-year period where it's exploding. All very fun, and I'm very lucky to be around
at the right time. So hardware is insanely fast so we can do anything with it; is that
right? Yes? No? That's a, no, we can't. Wrong. You can't do anything with it.
So — because I'm a physicist, I get back to numbers. This is numbers 101. So it's good
to have a few numbers in the back of your head. The earth about 10 to the 50 atoms on
it. It's a nice, easy number Torme. So let's try to program. Oh, yeah. Let's make a laptop,
the ultimate laptop weighs one kilogram, we stuff more and more components onto it. It
gets hotter and hotter, denser and denser, it becomes a black hole. So we have a black
hole laptop. It can do ten to the 51 operations per second. 10 to the minus 27 millimeters
small, store 10 to the 15 bits, and it lasts 10 to the minus 21 of a second. And it appears
through quantum entanglement through the universe. There's a problem. We don't actually know
how to get output from this thing. That's the ultimate computer.
And the ultimate printer is — well, let's make the ultimate printer. Take the entire
universe, the biggest thing we can think of, and we divide it by the smallest thing we
can think of, the smallest thing, the smallest pixel to make a 3D printer is ten to the minus
105 meters cubed. Divide one by the other. We made a printer out of the entire device.
Flattening from a huge sheet of paper, and it can print 10 to the 185 pixels. This is
the biggest picture in the world. You can't currently buy this from Hewlett-Packard. 10
to the 185 pixels. And so is this big enough for the output of our programs? The answer
is no of course. Okay. So here's a little program. I in one
double six factorial print I. That's a tiny little program. Wait a moment. What is that
thing? A sticks double factorial. Three characters. Three characters long. How big is six double
factorial? Well, six factorial. You know what factorial is. So 720 times 710 times 709 and
each of those terms. You know, 720 is bigger than 10, 710 is bigger than 10, 709 is bigger
than ten. And that's repeated. So six double factorial is much, much greater than ten to
the power of 711. Okay. So remember I said the biggest printer
in the universe can print 10 to the 185 pixels. So this little program, that little program
cannot be printed on the biggest printer that we can conceive of in the entire universe.
So I was thinking of writing a paper. You know? Consider the class of programs of three
characters in them. This is insanely complicated. So underlying computation is a mathematics.
We can't test this program. We can't run it. We can't do it. We have to use mathematics
to understand how it works. We have to prove things about it. You could prove that that
program terminates. But it would be useless because you could figure out — okay. The
next computer above the laptop is to take the entire universe as a quantum computer.
That will do — if you do that from the time the universe is booted, it's done ten to the
one — ten to the 123 operations since the universe was booted and that's way smaller
than this. So we couldn't actually compute this — well, we could prove it will mathematically
terminate, but it will not terminate within the life of the universe. So you need multiuniverses
to do that. Fun. So let's go on.
My conclusion from that programs are insanely complicated. They're all black holes right
in the middle of your programs. And certain programs you just can't test or do anything
with them. Right. Dangers. Dangers. Right. I just tell you a couple of these.
So this is Rebecca Burkett. And the photo was taken — if you look at the back of the
photo, it was taken in 1892. And my wife is interested in genealogy, and she was looking
through these old photos and said, oh, look, this is Rebecca — and then she said when
we're dead and gone, will our — you know, all of this stuff, all the photos we publish
on Facebook, will these photos just vanish into the cloud? Will our — in 100 years'
time, 200 years' time, will they be able to see these photos? And I thought that's an
interesting question. So I happen to be on a panel debate with some
guy — quite high up in Facebook. So I said, you know, all of these photos we take on Facebook,
are they still going to be around in 200 years' time so that people could look at them? What
about all of our stuff we're doing? And you know what he said? That's a very good question,
he said. Right so problem number one. Is saving our
history. I think — I'm rather worried that I wouldn't — you know, sometimes I start
— I like writing and sometimes I might try to write science fiction — 400 years ahead
and say, unfortunately, all the history from 2000 to 2220 was lost because we put it in
the cloud and encrypted it all and nobody knows how to get it out.
This is a real problem. We are putting more and more stuff into the cloud. We're encrypting
it. And most of the cloud is paid storage. Okay? So you stop paying, it's not stored
anymore. Or is it? What happens to it? Well, nobody knows. And, by the way, which cloud?
Apple's cloud? Google cloudy? Microsoft cloud? So I'm worried we're going to lose history.
So how much data are we talking about? What about history? So who's going to pay for it
all? Who can access the information? How long is it going to be stored for?
Goodness. How is the data named? Well, I don't know. How many documents are there? Well,
there's ten to the nine people on the planet. The sun will become a red giant in five times
ten to the nine years. We might write, say, 1,000 documents a year that we want to store.
So that's ten to the 25 documents and the earth's got ten to the 50 atoms. So maybe
we could do that. What happens after the sun becomes a red giant? Maybe we can beam off
into outer space and hopefully — sorry. Long aside that I haven't got time for.
So let's store everything in a content addressable store. And I've only got five minutes, so
I won't go into that. Content addressable store are wonderful things. We can't talk
about things unless things have got names. So this is a basic philosophical thing. If
something has a name, we can talk about it. So things that don't have names we can't talk
about. And content addressable store is encrypt check sum. So you can use NG5SJ6 to name a
blob of data. So this is more general than a key value store. You've got a key and a
value. This is a value store. Your store blobs, there's awe key. It's implied by the data.
The key is — well, I guess one check of the data. So a content addressable store — and
I want you to build this thing. Okay? Really it needs international collaboration. It needs
standards collaboration. So I would like to go to any website anywhere on the planet and
say get sha1, and it will either say, yeah, here you are. And you've got some data or
sorry, I haven't got it. This is immune to the man in the middle attack.
It doesn't need any security. Because once you've got that data, you can compute its
— in this case sha1 and see if it was the same data as it was. So you can lay the security
on top of it. An underlying mechanism. In fact, you need to make it slightly more complicatedness,
the response to a git request would be — it would say sorry I haven't got this, but here
are some other machines that you would like to lack at because I think they might have
it. And these, appear which is used in the future system, this works fine. People share
movies on it, millions of movies. We could put all of human information into a massive
THT and there by save history. So the API is like this. It's even easier
than a key value store. Just put data. Did it work? Don't know. You have to read it back
to see if you can find it again. That's pretty easy. If you thought key value was useful,
value stores are only even more fun. And there's a few references you can look up. One minute.
Where is he? Wave. Shout. Yeah, he's giving a talk about IPFS and actually building one
of these things. This is great stuff. This is fantastic stuff. Because Juan is going
to save us, he's going to save our history. So thousands of year time, they're going to
say thanks to Juan Bennett and the people who helped him from Barcelona. We've saved
history. Right. And then some other stuff. Vince surf is very keen on this, organized
conferences. He's more worried about the hardware than the formats. I mean okay. So we've got
the data for early computers. But hang on we haven't got the early computers. Can we
emulate the early computers so we can rerun these programs and things like that?
Tim Burner's Lee has cool stuff. And git torrent, bit torrent, it's on a website, huge massive.
Problem two. Computational infrastructure. We're using between about 6% — depends how
you calculate. About 3% of the world's energy to run data centers so we can share pictures
with each other. And we do have climate problems, so we need to do something about that. So
we need to build a computational infrastructure, and I'm not any good at hardware. So I thought
if you can't build something yourself, build a approach time, describe it to some hardware
people that can build it and use it and then I'm going to buy it. So this is what I want.
This is what Alan Kay did. He went around with a cardboard thing like this. This is
a dinobook prototype. And Steve Jobs sort of latched onto this and made the iPad, which
actually — Alan Kay is pissed off about the iPad because it's not the dinobook and basically
Apple made this device, but they haven't let kids program it. It's difficult to program.
It's not a ubiquitous open platform that anybody can program. It's a closed platform which
only Apple will let you program. And that is — so I thought, well, I can make
a model of ubiquitous computer that I want somebody to build. And here it is in operation
on my roof. And it worked fine in Spain. A nice, sunny place. So it's a solar panel.
I thought is solar panels are made of silicon, process of made of silicon. Maybe silicon,
flash memory is made of silicon, so why not just blow them on a solar panel and get 125
watts per square meter if you're lucky, process runs about two or three watts. That could
talk to your local computer with Wi-Fi. And you keep all of your personal data on this.
Is that crazy? Every time we book an airline ticket or hotel, we leak massive amounts of
information to commercial interests. And it's for their benefit. Not for our benefit.
What we should do is suppose you want to book an airline ticket it he moment in the hotel
because you're going on holiday. What you do is you go to booking sites, you go to airline
number one and say how much does it cost to go to Barcelona for the weekend? And you get
a quote. Oh, it's too expensive. Try booking site number two. But they already know you've
been to booking site number one. Oh, he has a MacBook, he can afford it. Or a crappy ol'
Windows. And then you want a hotel and things like
that. So the alternative you keep this data on your only computer at home, you don't leak
anything to anybody. You go to ten travel agents and say can I have your computer program,
please? I want to run it locally. You request these programs, you run them locally
and each of them gives you a quote and the hotels give you a quote. You haven't revealed
to anybody what dates you're moving. You haven't revealed your plans, you haven't told the
NSA or the national security, and then you send out your answers to ones — I'm choosing
you, you, and you. And you haven't incidentally leaked all of this information about yourself
to advertising agencies and security agencies and everybody else. We need to bring back
computing to the people. Okay? So once it's like that, it will talk to the neighbors'
houses, your house, a little battery when the sun goes down, it might not work. I don't
know. And then of course you can stick it on your
car roof. And then when you drive into a parking lot of a big supermarket, you know, there
would be thousands, 500 cars, and it would form a supercomputing cluster. It would say
hello, oh, another computer there. Just build a supercomputer. And that's the sun goes around
the earth, the computations will follow it, the data will follow it, and it will be a
green computer. We can throw away all of these data centers.
Right so, yeah, that's what you could do with it. Stick with it. Yeah, whatever. Stick it
on your roof and your house becomes a supercomputer, keep your own data on your own computer, make
a planet wide global computer with renewable sources. That's what you guys have to do.
I'm kind of not so active program — well, yeah, I am actually. But I'm sort of — it's
like a drug. I'm in withdrawal at the moment because I don't do it as much as I used to.
So finally just, you know, have fun and have a great conference and thank you very much.
[Applause] >> Thank you, Joe. So sadly we don't have
time for questions. We don't have time. Sorry. >> Oh, we don't have time.
>> Sorry. We ran out of time. But if you have questions for Joe, either grab him when you
see him over the next couple of days, or you can tweet him, and maybe he'll respond.

Be First to Comment

Leave a Reply

Your email address will not be published. Required fields are marked *