The discussion centers on "Cloudbot," an AI assistant that integrates deeply with a user's computer and messaging platforms, acting as a highly resourceful and personalized digital companion capable of performing complex tasks and automating workflows.
Mind Map
クリックして展開
クリックしてインタラクティブなマインドマップを確認
It's just like having a new weird friend
that is also really smart and
resourceful that lives on your computer.
I was still in Morocco and someone sent
me a tweet of a bug and I literally just
made a picture of the tweet, posted on
WhatsApp. It read the tweet, it
understood that there was a bug. It
checked out the Git repository, it fixed
it, it did a commit and then it replied
to the person on Twitter that it's fixed
now. This will blend away probably 80%
of the apps that you have on your phone.
Why should I use my fitness pal to track
food when I have an infinitely
resourceful assistant that already knows
I'm making bad decisions and I'm
Kentucky Fried Chicken? Those things are
so resourceful, although in a scary way.
It's like unshackled JGBT. A lot of
people don't realize that if you give an
AI access to your computer, they can
>> All right, welcome everyone. My guest
today is Peter, creator of Claude, an AI
assistant that you can just chat with in
your messaging apps to get stuff done.
And today is Peter is going to show us
how to use cloud. And also Peter has a
lot of really great hot takes about AI
coding that I'm really excited to dig
into. So welcome the other Peter.
>> Peter, thanks for having me.
>> Great to see you. So why don't we start
by talking about cla. So what exactly
does cloud do at a high level and uh why
why is it a lobster? [laughter]
[laughter]
>> Yeah. So, so maybe I have a little bit
of a backstory like when I when I came
back from my retirement, let's say it
like that. I kind of wanted wanted a way
to just check up on my computer from my
phone cuz I I fully jumped on this on
this V boarding trend and then you know
like your agents might run for half an
hour while you while you eat or they
stop after 2 minutes because they have
another question and then and then you
go back and you're like annoyed. But I
kind of I kind of didn't build it
because I assumed all the big labs would
do that anyhow.
it felt like such an obvious thing
>> like like something where like kind of a
new new kind of operating system almost
um but didn't happen and then it was
like November and it still didn't
happen. I'm like okay I'll try something
small and and the small thing was
basically hooking up WhatsApp to cloud
code. So, so, so you send a WhatsApp
message and it would literally open the
binary like with the the prompt and like
return you this thing like very simple
was like built in one hour and it kind
of got a life of its own and now here we
are. It's like I think 300,000 lines of
code. It does every messaging platform
on Earth. Not everyone, but like we're
getting there. And I think it it's kind
of where things are going in the future.
like everybody will have an AI that is
like super powerful and like follows
them through their life. Um, turns out
if if you give an AI access to your
computer, they can basically do anything
that you can do on your computer.
>> Yeah. And it's got to a point where like
you don't have to sit there and babysit
it, right? You can just give it some,
you know, prompts and commands and it
will do it thing for you and you can
check it work and then that that's it.
You know, you have to set a computer.
>> Yeah. So when I when I built it, I I
feel I feel this project is like as much
exploration as it is like technology
because it's it's a little bit of a new category
category
>> and then I was on a birthday trip for
one of my friends in Morocco
>> and I I catch myself using this thing
all the time. It's like, hey, where are
we going? like asking for directions or
like or like tips for for restaurants or
I don't know there was like one morning
where someone sent me a tweet of a bug
and I just literally just made a picture
of the tweet posted on WhatsApp. It it
read the tweet. It understood that there
was a bug in one of my repositories. It
checked out the git repository. It fixed
it. It did a commit and then it replied
to the person on Twitter uh that it's
fixed now. And I'm like really
>> this is nice. And then one day I was I
was walking around and I didn't sync and
I just sended a voice message, you know.
I didn't I didn't I didn't build in
support for voice message and I was like
it showed me a typing indicate. I'm like
oh I wonder what's happening now. And
then it just replied to me as if nothing
would have happened and I'm like wow how
the f did you do that? And it was like
yeah I saw a file but there was no file
ending because I didn't build it. Mhm.
>> So I looked I looked at the at the
header of the file and it was like ous
uh some some audio file format. So I
found ffmpeg on your computer and I
converted it to wave and then I looked
for visper.cpp but you didn't have it
installed but I found this openi key and
then I used curl to send it to openai's
API uh and it got the transcript back
and I replied to you. I'm like >> wow
>> wow
>> that's amazing. Yeah,
>> like those things are so resourceful
although in a scary way. Um, but that
was kind of like the the the moment
where it clicked for me is like, oh
yeah, this is really powerful. This is
much more interesting than using JGBT on
on the web because it's like it's like
unshackled chbt and I think a lot of
people don't realize that that those
things like cloud code, they're not just
good for programming, they are very
resourceful for any kind of problem.
Yeah. You just got to give it access to
like, you know, your computer and like,
you know, be able to find stuff, right?
So, you just have to give it tools.
They'll become very resourceful.
>> Yeah. So, so, so over the last few
months, I I kind of built up my my CLI
army because what are what are agents
good with? Calling CLIs because that's
what they train for. So, I've built like
CLI for accessing all of Google,
including like the Google Places API. I
built one that that that makes it very
easy to look up memes and gifts. So you
can also like reply with some memes. [snorts]
[snorts]
>> I did I did a bunch of experiment. I
even built one that visualizes sound
because I wanted it to like experience
music. Um that that goes a little bit
more into the art direction. I don't
know if that makes any sense, but
anyhow, it's a lot of fun. Like like I
have like a whole list. I built one that
that that hacked into my the food
delivery here. So So it actually tell me
how long it takes until my food's there.
I have one that that that reverse
engineered the the eight sleep uh API so
it actually can control the temperature
of my bed
>> really and real quick like when you
build all this stuff you just you're
just getting AI to build this stuff or
what's going on
>> the funniest thing is I I was in my my
old company um I was very very good at
iOS and and Mac OS like the whole Apple
ecosystem I did it for 20 years I'm like
very much an expert in there
>> but also when I came back I I I built a
project where I'm like I'm kind of sick
of Apple gating everything
>> and it also would make a lot more sense
to build it as a web app because it's
kind of a thing that it should be in a
browser and and should be accessible and
if I do it as a Macup again it's like
we'll have a very limited set of people
that can use it but you notice I see
this with a lot of engineers where
you're really good at one thing
>> and then moving to another technology is
just so painful because then you feel
like you feel like a sorry for the word
an idiot and [snorts] and you have you
look up every little things like what's
a prop or like how do I split an array
cuz because you understand all the
concepts but you don't necessarily like
know the syntax. So that that's kind of
like how I felt when I moved from from
Objective C and Swift to to JavaScript.
Like I know JavaScript a little bit, but
I never really built something big in
Typescript. And then it's just it's not
even that it's hard, it's just painful
because you have to look up all those
things and you're just so slow. And then
and then with AI all that all that melts
away like you can you can still apply
your system level thinking your like how
do I build and structure bigger projects
and your taste may I say or like your
which dependencies do I build on um all
those things all these things is still
valuable and you can like much easier
move that from one domain to the other.
>> Yeah. And and that felt like a
superpower. Suddenly like I I feel like
I could build anything. Languages don't
matter anymore. My my my engineering
thinking matters.
>> Yeah. Because like I was trying to worry
about like whether you have a
parenthesis here and there is is lame,
right? You don't have to worry about
that kind of stuff anymore.
>> This episode is brought to you by
Granola. If you're in backtoback
meetings, you know how much work it is
to take notes [music] live and clean
them up afterwards. That's why I love
Granola, the best AI meeting notes app
in the market. Here's how I use it.
Granola automatically takes [music]
notes during a meeting and I can add my
own notes too. After the meeting ends, I
use a Granola recipe to extract clear
takeaways and next [music] steps in the
exact format that I want. Then I can
just share notes directly in Slack with
my colleagues or even get Granola to
share her notes automatically. Honestly,
of all the AI apps that I use, Granola
is the one that saves me the most time.
Try it now at granola.ai/pater
and use the code Peter to sign up and
get three months free. That's granola.ai/pater.
granola.ai/pater.
Now, back to our episode.
>> But, but dude, let's let's go back to
Claude like like the the thing that you
built. Maybe you can um screen share,
maybe you can show like maybe you can
show like how people can install the
thing first like it like do you have to
be super technical to use cloud or no?
Right. You can just install it and then
get it to work.
>> Yeah. Um yes, yes and no. So
>> fortunately and also unfortunately this
project attracts a lot of uh people that
don't have a lot of clue about
technology because
>> it it lends away all these all these
layers that make it complicated, right? You
You
>> if you use cloud code, you work in a
terminal, you you kind of have to think
about the context space and what folder
you're in and like
>> it feels very techy. like talking to a
thing on on iMessage or WhatsApp or
Telegram. You do it with your friends
and now it's just like having a new
weird friend that is also really smart
and resourceful that lives on your computer.
computer. >> Yeah.
>> Yeah.
>> That makes the whole technology very
approachable. You don't think about, oh,
what model do I pick or what? It just works.
works. >> Mhm.
>> Mhm.
>> And then that's that's that's kind of
the idea. It's also like that good and
bad part because of course with a lot of
power comes a lot of risk which is also
unsolved like this thing is access to
your computer. So yes it could do bad
things on your computer. If you tell it
to like I don't know delete all my files
in my home directory. It would probably
like ask you are you sure? But if you if
you like if you like keep saying yes yes
yes it will probably comply and probably
also delete itself and crash. [laughter]
>> Yeah you got to be careful. Yeah
>> I I'll let me share my screen so you
see. So in it's written in in TypeScript.
TypeScript. >> Mhm.
>> Mhm.
>> So it runs it runs everywhere. Uh even
on Windows you can just go on our
website clogbot. >> Yeah.
>> Yeah.
>> And there's a handy oneliner. Looks very
scary but it's every everything's open
source. You can check everything
including the website. >> Mhm.
>> Mhm.
>> So so this is the easiest way to install
it. It works on Mac OS Linux. It also
works on Windows.
>> It's time to turn terminal right and
then it'll start installing. Yeah. You
can also install the mpm for people who
understand that ecosystem
>> and I think something that that I did
that I haven't seen in a lot of lot of
project is also it has a hackable install
install
>> again a simple way and like the more
manual way where you basically check out
the git repository and then and then
launch it from the git repository which
is to to be fair is like the most fun
way to use it because if your agent can
read its own source code of its harness
it can literally reconfigure and
reprogram itself and then restart and
then either crash or have new powers.
Um, [snorts] >> okay.
>> okay.
>> Like this I think this is one of my my
superpowers where I got a lot of people
participate in the project and like send
me pull requests that never did a pull
request. I mean
>> sometimes that also shows um but I but I
see pull requests more often as a as a
prompt request. Yeah,
>> it's enough to like understand the intent
intent
>> and then and then and then a after we
install it like do you like how do you
hook it up to a messaging app?
>> The nicest way is probably right now
just using this one lineup and then it
will like greet you with some sassy
stuff and and try to configure
everything up.
>> Got it.
>> In install the package and then you and
it just guides you through and you just
you can hook it up to do any of the
common messages.
Okay, that that looks good. It's working.
working.
Yeah. And then you can say plbot.
It will do it automatically if it's a
clean install. But now I have to type in
on board.
>> Got it.
>> And basically then you have like you can
enter a model.
You can Oops.
All providers.
Let's say we go with some tropic.
Probably a new one.
Then you can set up Telegram, Discord
and then it will guide you through the
rest. You can like set up skills hooks
>> and then do you have to give it your
anthropic API key?
>> It works with with any model. >> Yeah.
>> Yeah.
>> Although you know they're in industry
like Anthropic and Open are kind of like leading.
leading. >> Yep.
>> Yep.
>> It works with API keys. It works with subscriptions.
