joining us today.
Please welcome to the stage Sam
Altman.
[music]
[cheers and applause]
>> Good morning.
Welcome to our first ever
OpenAI DevDay.
We're thrilled that you're here
and this energy is awesome.
[cheers and applause]
And welcome to San Francisco.
San Francisco has been our home
since day one, the city is
important to us and to the tech
industry in general.
We're looking forward to
continuing to grow here.
So we've got some great stuff to
announce today, but first, I'd
like to take a minute to talk
about some of the stuff that
we've done over the past year.
About a year ago, November 30th
, we shipped ChatGPT as a
low-key research preview, and
that went pretty well.
[laughter]
In March we followed that up
with the launch of GPT-4,
still the most capable model out
in the world.
[applause]
And in the last few months, we
launched voice and vision
capabilities so that ChatGPT
can now see, hear, and speak.
[applause]
There's a lot, you don't have to
clap each time.
[laughter]
More recently we launched DALL·E
3, the world's most advanced
image model.
You can use it, of course,
inside of ChatGPT.
For our enterprise customers, we
launched ChatGPT Enterprise,
which offers enterprise grade
security and privacy, higher
speed GPT-4 access, longer
context windows, a lot more.
Today, we've got about 2 million
developers building on our API
for a wide variety of use cases,
doing amazing stuff.
Over 92% of Fortune 500
companies building on our
products, and we have about 100
million weekly active users now
on ChatGPT.
[applause]
And what's incredible on that
is, we got there entirely
through word of mouth.
People just find it useful and
tell their friends.
OpenAI is the most advanced and
the most widely used AI platform
in the world now.
But numbers never tell the whole
picture on something like this.
What's really important is how
people use the products, how
people are using AI.
So I'd like to show you a quick
video.
>> I actually wanted to write
something to my dad in Tagalog.
I want a nonromantic way to tell
my parent that I love him and I
also want to tell him that he
can rely on me, but in a way
that still has the respect of,
like, a child-to-parent
relationship that you should
have in fill I teen zero culture
and in taking a long.
I love you very deeply and I
will be with you no matter where
the path he leads.
>> I see so many possibilities,
I'm like, who he, sometimes I'm
not sure about some stuff, and I
feel like the actual
ChatGPT -- just thinking about
giving it more confidence.
>> The first thing that blew my
mind was that it levels with
you.
That's something that a lot of
people struggle to do.
It opened my mind to just what
every creative could do if they
just had a person helping them
out who listens.
>> So this is to represent
circulating hemoglobin --
>> And you built that with
ChatGPT.
>> ChatGPT built it with me.
>> I started using it for daily
activities like, hey, here's a
picture of my fridge, can you
tell me what I'm missing because
I'm going grocery shopping and I
really need to do recipes that
are following my Vegan diet.
>> As soon as we got access to
Code Interpreter, I was like,
wow, this thing is awesome.
It can build spreadsheets.
It can do anything.
>> I discovered about -- on my h
 birth date.
Very friendly, very patient,
very knowledgeable, and very
quick.
It's been a wonderful thing.
>> I'm a 4.0 student but I also
have four children.
When I started using ChatGPT,
I realized I could ask ChatGPT
that question, and not only does
it give me an answer, but it
gives me an explanation.
Didn't need computer go as
much.
It gave me a life back.
I gave me time for my family and
time for me.
>> I have a chronic nerve pain
on my whole left half of my
body, nerve damage.
I had like a spine -- brain
surgery.
I have limited use of my left
hand.
Now you can just have the
integration of voice input, and
the newest one where you can
have the back-and-forth
dialogue, that's just like
maximum best interface for me.
It's here!
[music]
[applause]
So we love hearing the stories
of how people are using the
technology.
It's really why we do all of
this.
Okay, so now on to the new
stuff, and we have got a lot.
[cheers and applause]
First, we're going to talk about
a bunch of improvements we've
made, and then we'll talk about
where we're headed Next.
Over the last year, we spent a
lot of time talking to
developers around the world.
We've heard a lot of your
feedback.
It's really informed what we
have to show you today.
Today, we are launching a new
model.
GPT-4 Turbo.
[cheers and applause]
GPT-4 Turbo will address many
of the things that you all have
asked for.
So let's go through what's new.
We've got six major things to
talk about for this part.
Number one, context length.
A lot of people have tasks that
require a much longer context
length.
GPT-4 supported up to 8k and
in some cases up to 32k
context length but we know that
isn't enough for many of you and
what you want to do.
GPT-4 Turbo supports up to
128,000 tokens of context.
[cheers and applause]
That's 300 pages of a standard
book, 16 times longer than our
8k context.
And in addition to longer
context length, you'll notice
that the model is much more
accurate over a long context.
Number two, more control.
We've heard loud and clear that
developers need more control
over the model's responses and
outputs, so we've addressed that
in a number of ways.
We have a new feature called
JSON load which ensures that the
model will respond with valid
JSON.
This has been a huge developer
request, it will make calling
APIs much easier.
The model is also much better at
function calling.
You can now call many functions
at once.
It will do better at following
instructions in general.
We're also introducing a new
feature called reproducible
outputs.
You can pass the seed parameter
and it will make the model
return consistent outputs, which
gives you a higher degree of
control over model behavior.
This rolls out in beta today.
[cheers and applause]
And in the coming weeks, we'll
roll out a feature to let you
view log probs in the API.
[cheers and applause]
Number three, better world
knowledge.
You want these models to the
access better knowledge about
the world, so do we.
We're launching retrieval in the
platform.
You can bring knowledge from
outside documents or databases
into whatever you're building.
We're also updating the
knowledge cutoff.
We are just as annoyed of all of
you, probably more than, that
GPT's knowledge of the world
ended in 2021.
We will try to never let it get
that out of date again.
GPT Turbo has knowledge of the
world up to April 2023 and we
will improve that over time.
Number four, new modalities.
Surprising no one, DALL·E 3,
GPT-4 Turbo with Vision, and
the new text-to-speech model are
all going to into the API
today.
[cheers and applause]
We have a handful of customers
that have just started using
DALL·E 3 to programmatically
generate images and designs.
Today, Coke is launching a
campaign that lets its customers
generate Diwali cards using
DALL·E 3, and our safety systems
help developers protect their
applications against misuse.
Those tools are available in the
API.
GPT-4 Turbo can now accept
images as inputs via the API,
can generate captions,
classifications, and analysis.
For example, Be My Eyes uses
this technology to help people
who are blind or have low vision
with their daily tasks like
identifying products in front of
them.
And with our new text-to-speech
model, you'll be able to
generate incredibly natural
sounding audio from text in the
API with six preset voices to
choose from.
I'll play an example.
>> Did you know that Alexander
Graham bell, the eminent
inventor, was enchanted by the
world of sounds?
His ingenious mind led to the
creation of the graphophone,
which etched sounds onto wax,
making voices Whisper through
time.
>> This is more natural than
anything else we've heard out
there.
Voice can make apps more natural
to interact with.
It unlocks a lot of use cases,
like language learning and voice
assistance.
Speaking of new modalities,
we're also releasing the next
verse of our open source speech
recognition model, Whisper V3,
today, and it will be coming
soon to the API.
It features improved performance
across many languages and we
think you're really gonna like
it.
Okay.
Number five, customization.
Fine-tuning has been working
really well for GPT-3.5 since we
launched it a few months ago.
Starting today, we're going to
expand that to the 16k version
of the model.
Also starting today, we're
inviting active fine-tuning
users to apply for the GPT-4
fine-tuning, experimental access
program.
To fine fine an API is great for
adapting our models to achieve
better performance in a wide
variety of applications with a
relatively small amount of data,
but you may want to model to
learn a completely new knowledge
domain or to use a lot of
proprietary data.
So today we're launching a new
program called Custom Models.
With Custom Models, our
researchers will work closely
with a company to help them make
a great custom model, especially
for them, and their use case,
using our tools.
This includes modifying every
step of the model training
process, doing additional
domain-specific pre-training, a
post-training process tailored
to a specific domain.
We won't be able to do this with
many companies to start, it will
take a lot of work and in the
interest of expectations, at
least initially it won't be
cheap, but if you're excited to
push things as far as they can
currently go, please get in
touch with us and we think we
can do something pretty great.
Okay.
And then number six.
Higher rate limits.
We're doubling the tokens per
minute for all of our
established GPT-4 customers,
so that it's easier to do more.
And you'll be able to request
changes to further rate limits
and quotas directly in your API
account settings.
In addition to these rate
limits, it's important to do
everything we can do to make
it -- you successful building on
our platform.
We're introducing Copyright
Shield.
Copyright Shield means that we
will step in and defend our
customers and pay the costs
incurred if you face legal
claims around copyright
infringement, and this place to
both ChatGPT Enterprise and
the API.
And let me be clear.
This is a good time to remind
people, we do not train on data
from the API or ChatGPT
Enterprise ever.
All right.
There's actually one more
developer request that's been
even bigger than all of these.
So I'd like to talk about that
now.
And that's pricing.
[laughter]
GPT-4 Turbo is the industry
leading model.
It delivers a lot of
improvements that we just
covered, and it's a smarter
model than GPT-4.
We've heard from developers that
there are a lot of things that
they want to build, but GPT-4
just costs too much.
They've told us that if we could
decrease the cost by 20, 25%,
that would be great, a huge leap
forward.
I'm super excited to announce
that we worked really hard on
this, and GPT-4 Turbo, a
better model, is considerably
cheaper than GPT-4 by a factor
of 3X for prompt tokens --
[applause]
And 2X for completion tokens,
starting today.
[cheers and applause]
So the new pricing is 1 cent per
thousand prompt tokens and $0.03
per thousand completion tokens.
For most customers that leads to
a blended more than 3.75%
cheaper to use.
We worked super hard to make
this happen.
We hope you're as excited about
it  as we are.
[cheers and applause]
So we've decided to prioritize
price first because we had to
choose one or the other but
we're going to work on speed
next.
We know speed is important,
too.
Soon you will notice GPT-4
Turbo becoming a lot faster.
We're also decreasing the cost
of GPT-3.5 Turbo 16k, also input
tokens for 3X less, and output
tokens are two, less.
Which means 16k is now cheaper
than the previous model.
Running a fine-tune GPT-3.5 16k
version is also cheaper than the
old version.
We just covered a lot about the
model itself.
We hope these changes address
your feedback  , we're really
excited to bring all of these
improvements to everybody now.
In all of this, we're lucky to
have a partner who's
instrumental in making it
happen.
So I'd like to bring out a
special guest, Satya Nadella,
the CEO of Microsoft.
Music.
[cheers and applause]
>> Welcome.
>> Thank you so much.
>> Thank you.
Satya, thanks so much for coming
here.
>> It's fantastic to be here,
and, Sam, congrats.
I'm really looking forward to
Turbo and everything else that
you have coming is, it's been
just fantastic partnering with
you guys.
>> Awesome.
Two questions, I won't take too
much of your time.
How is Microsoft thinking about
the partnership currently?
>> First --
[laughter]
We love you guys.
Look, it's been fantastic for
us.
In fact, I remember the first
time I think you reached out and
said, hey, do you have some
Azure credits, we've come a long
way from there.
>> Thank you for those.
That was great.
>> You guys have built something
magical.
There are two things for us when
it comes to the partnership.
The first is, these workloads
and even when I was listening
backstage to how you're
describing what's coming even,
it's just so different and nut.
I've been in the infrastructure
business for three decades --
>> No one has seen
infrastructure like this.
>> The workload, the pattern of
the workload, the training jobs
are so synchronous and large and
data parallel.
The first thing we've been doing
is building in partnership with
you the system all the way from
thinking from power to the DC to
the rack, to the accelerators,
to the network, and just really
the shape of Azure is
drastically changed.
And it's changing rapidly in
support of these models that
you're building.
And so our job number one is to
build the best system so that
you can build the best models,
and then make that all available
to developers.
The other thing is, we ourselves
are developers, building
products.
My own conviction of this entire
generation of foundation models
has completely changed.
The first time I saw GitHub
Copilot on GPT.
And so we want to build our
Copilot, GitHub Copilot, all
as developers on top of OpenAI
APIs so we're very, very
committed to that.
What does that mean to
developers?
I always think of Microsoft as a
platform company, a developer
company, and a partner company,
and so we want to make -- for
example, we want to make
GitHub available --
GitHub Copilot available,
the enterprise he diddation to
all the attendees here so they
can try it out.
>> That's awesome.
>> We're very excited about
that.
[applause]
And you can count on us to build
the best infrastructure in Azure
with your API support, and bring
it to all of you, and then even
things like the Azure
marketplace, building out
products here to get to market
rapidly.
That's sort of really our intent
here.
>> Great.
How do you think about the
future?
Future of the partnership or
future of AI or whatever.
[laughter]
Anything you want.
>> You know, like, there are a
couple of things for me that I
think are gonna be very, very
key for us.
One is, I just described how the
systems that are exceeded as you
aggressively push forward on
your roadmap, requires us to be
on the top of our game, and we
intend fully to commit ourselves
deeply to making sure you all,
as builders of these foundation
models, have not only the best
systems for training but the
most compute so you can keep
pushing forward.
>> We appreciate that.
>> On the frontiers because I
think that's the way we're going
to make progress.
The second thing I think we both
care about, in fact, quite
frankly, the thing that excited
both shades to come together is
your mission and ours.
Our mix is to empower every
person and organization on the
planet to achieve more, and
ultimately AI is only going to
be useful if it does empower.
I saw the video you played
earlier.
That was fantastic to see
those -- hear those voices
describe what AI meant for them
and what they were able to
achieve.
So ultimately it's about being
able to get the benefits of AI
broadly disseminated to
everyone, I think is going to be
the goal for us.
The last thing is we're very
grounded in the fact that safety
matters and safety is not
something that you care about
later but it's something we do
shift left on and we're very,
very focused on that with you
all.
>> Great.
I think we have the best
partnership in tech, I'm excited
to be working together.
Thank you for coming.
>> Thank you.
[applause]
>> Okay.
So  we have shared a lot of
great updates for developers
already, and we've got a lot
more to come, but even though
this is a developer conference,
we can't resist making some
improvements to ChatGPT.
So, a small one, ChatGPT now
uses GPT-4 Turbo with all the
latest improvements including
the latest knowledge cutoff,
which we'll continue to update,
that's all live today.
It can now browse the web when
it needs to, write and run code,
analyze data, take and generate
images and much more, and we
heard your feedback that model
picker was extremely annoying,
that's gone starting today.
You will not have to click
around the dropdown menu.
All of this will just work
together.
[cheers and applause]
ChatGPT will just know what to
use and when you need it.
But that's not the main thing.
And neither was price, actually
the main developer request.
There was one that was even
bigger than that.
And I want to talk about where
we're headed and the main thing
we're here to talk about today.
So we believe that if you give
people better tools, they will
do amazing things.
We know that people want AI that
is smarter, more personal, more
customizable, can do more on
your behalf.
Eventually you'll just ask a
computer for what you need and
it will do all of these tasks
for you.
These capabilities are often
talked in the AI field about as
agents.
The upsides of this are going to
be tremendous.
At OpenAI we really believe that
gradual iterative deployment is
the best way to address the
safety challenges with AI.
We think it's especially
important to move carefully
towards this future of agents,
it's going to require a lot of
technical work, and a lot of
thoughtful consideration by
society.
So today we're taking our first
small step that moves us towards
this future.
We're thrilled to introduce
GPTs.
GPTs are tailored versions of
ChatGPT for a specific
purpose.
You can build a GPT, a
customized version of ChatGPT,
for almost anything, with
instructions, expanded
knowledge, and actions, and then
you can publish it for others to
use.
And because they combine
instructions, expanded
knowledge, and actions, they can
be more helpful to you.
They can work better in any
context and they can give you
better control.
They'll make it easier for you
to accomplish all sorts of tasks
or just have more fun and you'll
be able to use them right
within ChatGPT.
You can in effect program a GPT
with language just by talking to
it.
It's easy to customize the
behaviors so that it fits what
you want.
This makes building them very
accessible and it gives agency
to everyone.
So, we're going to show you what
GPTs are, how to use them, how
to build them, and then we're
going to talk about how they'll
be distributed and discovered.
And then after that, for
developers, we're going to show
you how to build these
agent-like experiences into your
own apps.
First, let's look at a few
examples.
Our partners at Code.org are
working hard to expand computer
science in schools.
They've got a curriculum that is
used by tens of millions of
students worldwide.
Code.org crafted Lesson Planner
GPT to help teachers provide a
more engaging experience for
middle schoolers.
If a teacher asks it to explain
four loops in a creative way, it
does just that.
In this case, it will do it in
terms of a video game character,
repeatedly picking up coins,
super easy to understand for an
eighth grader.
As you can see, this GPT brings
together Code.org's extensive
curriculum and expertise and
lets teachers adapt it to their
needs quickly and easily.
Next, Canva has built a GPT that
lets you start designing by
describing what you want in
natural language.
If you say, make a poster for a
DevDay reception this afternoon,
this evening, and you give it
some details, it will generate a
few options to start with by
hitting Canva's APIs.
This concept may be familiar to
some of you.
We've evolved our plug-ins to be
custom actions for GPTs.
You can keep chatting with this
to see different iterations, and
when you see one you like, you
can click through to Canva for
the full design experience.
So now, we'd like to show you a
GPT live.
Zapier has built a GPT that lets
you perform actions across 6,000
applications to unlock all kinds
of integration possibilities.
I'd like to introduce Jessica,
one of our solutions architects,
who is going to drive this
demo.
Welcome, Jessica.
[cheers and applause]
>> Thank you, Sam.
Hello, everyone.
Thank you all.
Thank you all for being here.
My name is Jessica Shay, I work
with partners and customers to
bring their product to life.
Today I can't wait to show you
how hard we've been working on
this, so let's get started.
To start, where your GPT will
live is on this upper left
corner.
I'm going to start with clicking
on the Zapier AI actions.
And on the right-hand side, you
can see that's my calendar for
today.
So it's quite a day.
I've used this before so it's
connected to my calendar.
To start, I can ask what's on my
schedule for today.
We built GPTs with security in
mind, so before it performs any
action or shares data, it will
ask for your permission, so
right here I'm going to say
allowed, so GPT is designed to
take in your instructions, make
a decision on which capability
to call to perform that action,
and then execute that for you.
So you can see right here, it's
already connected to my
calendar, it pulls in my
information, and then I've also
prompted it to identify
conflicts on my calendar.
You can see right here it
actually was able to identify
that.
So it looks like I have
something coming up.
So what if I want to let Sam
know that I have to leave
early?
Right here I say, let Sam know I
gotta go, chasing GPUs.
[laughter]
With that, I'm going to swap to
my conversation with Sam, and
then I'm going to say, yes,
please run that.
Sam?
Did you get that?
>> I did.
[applause]
>> Awesome.
So, this is only a glimpse of
what is possible, and I cannot
wait to see what you all will
build.
Thank you and back to you, Sam.
[cheers and applause]
Thank you, Jessica.
So those are three great
examples, in addition to these,
there are many more kinds of
GPTs that people are creating
and many, many more that will be
created soon.
We know that many people who
want to build a GPT don't know
how to code.
We've made it so that you can
program the GPT just by having a
conversation.
We believe that natural language
is going to be a big part of how
people use computers in the
future, and we think this is an
interesting early example.
So I'd like to show you how to
build one.
All right.
So I'm going to create a GPT
that helps give founders and
developers advice when starting
new projects.
I'm going to go to create a GPT
here.
And this drops me into the GPT
builder.
I worked with founders for years
at YC and still, whenever I meet
developers, the questions are
always about how do I think
about a business idea, can you
give me some advice.
I'm going to see if I can build
a GPT to help with that.
So to start, GPT builder asks me
what I want to make, and I'm
going to say I want to help
start-up founders think through
their business ideas and get
advice.
After the founder has gotten
some advice, grill them --
[laughter]
On why they are not growing
faster.
[laughter]
All right.
So to start off, I just tell the
GPT a little bit about what I
want here, and it's going to go
off and start thinking about
that, and it's going to write
some detailed instructions for
the GPT.
It's also going to ask me about
a name.
How do I feel about start-up
mentor?
That's fine.
That's good.
So if I didn't like the name, of
course I could call it something
else but it's going to try to
have this conversation with me
and start there.
And you can see here on the
right, in the preview mode, that
it's already starting to fill
out the GPT, where it says what
it does, it has some ideas of
additional questions that I
could ask.
It just generated a candidate.
Of course I could regenerate
that or change it but I sort of
like that, so I will say, that's
great.
And you see now that the GPT is
being built out a little bit
more as we go.
Now, what I want this to do, how
it can interact with users, I
can talk about style here but
what I'm going to say is, I am
going to upload transcripts of
some lectures about start-ups I
have given.
Please give advice based off of
those.
All right.
So, now it's going to go figure
out how to do that, and I would
like to show you the configure
tab so you can see some of the
things that were built out here
as we were going by the builder
itself and you can see there's
capabilities here that I can
enable.
I could add custom actions.
These are all feign to leave.
I'm going to upload a file.
Here's a lecture that I gave
with some start-up advice, and
I'm going to add that here.
In terms of these questions,
this is a dumb one.
The rest of those are
reasonable.
And very much things founders
often ask.
I'm going to add one more thing
to the instructions here, which
is be concise and constructive
with feedback.
All right.
So, again, if I had more time,
I'd show you a bunch of other
things but this is like a decent
start, and now we can try it out
over on this preview tab.
So I will say -- what's a common
question?
What are three things to look --
what are three things to look
for when hiring employees at an
early stage start-up?
Now, it's going to look at that
document I uploaded.
It will also have all of the
background knowledge of
GPT-4.
That's pretty good.
Those are three things that I
definitely have said many
times.
Now, we could go on and it would
start following the other
instructions and grill me on why
I'm not growing faster, but in
the interest of time, I'm going
to skip that.
I am going to publish this only
to me for now.
I can work on it later, I can
add more content, I can add a
few actions that I think will be
useful, and then I can share it
publicly.
So that's what it looks like to
create a GPT.
[applause]
Thank you.
By the way, I always wanted to
do that, after all of the YC
office hours, I thought, some
day I'll make a bot that can do
this and that will be awesome.
[laughter]
With GPTs we're letting people
easily share and discover all
the fun ways that they use
ChatGPT with the world.
You can make private GPTs like
I just did.
Or you can share your creations
publicly with a link for anyone
to use.
Or if you're on ChatGPT
Enterprise, you can make GPTs
just for your company.
And later this month, we're
going to launch the GPT Store.
You can list a --
[applause]
>> Thank you, I appreciate
that.
[applause]
You can list a GPT there, and
we'll be able to feature the
best and the most popular
GPTs.
Of course, we'll make sure that
GPTs in the store follow our
policies before they're
accessible.
Revenue sharing is important to
us.
We're going to pay people who
build the most useful and the
most used GPTs a portion of
our revenue.
We're excited to foster a
vibrant ecosystem with the GPT
Store just from what we've been
building ourselves over the
weekend, we're confident there's
going to be a lot of great
stuff, we're excited to share
more information soon.
Those are GPTs, and we can't
wait to see what you'll build.
But this his a developer
conference and the coolest thing
about this is we're bringing the
same concept to the API.
[applause]
Many of you have already been
building agent-like experiences
on the API.
For example, Shopify Sidekick,
which lets you take actions on
the platform, Discord's Clyde,
lets Discord moderators create
custom personalities for, and
Snap's My AI, a custom island
chatbot that can be added to
group chats and make
recommendations.
These experiences are great but
they have been hard to build,
sometimes taking months, teams
of dozens of engineers, there's
a lot to handle to make this
custom assistant experience.
So today we're making it a lot
easier with our new Assistants
API.
[cheers and applause]
The Assistants API includes
persist tents threads so they
don't have to figure out how to
deal with long conversation
history, built-in retrieval,
Code Interpreter, a working
Python interpreter in a sandbox
environment, and of course the
improved function calling that
we talked about earlier.
So we'd like to show you a demo
of how this works and here is
Romain, our head of developer
experience.
Welcome.
[music]
[applause]
>> Thank you, Sam.
Good morning.
Wow.
It's fantastic to see you all
here.
It's been so inspiring to see so
many of you infusing AI into
your apps.
Today, we're launching new
modalities in the API, but we
are also very excited to improve
the developer experience for you
all to build assistive agents.
So let's dive right in.
Imagine I'm building Wanderlust,
a travel app for global
explorers and this is the
landing page.
I've actually used GPT-4 to
come up with these destination
ideas, and for those of you with
a keen eye, these illustrations
are generated programmatically
using the new DALL·E 3 API
available to all of you today.
So it's pretty remarkable.
But let's add a very simple
assistant to it.
This is the screen, we'll come
back to it in a second.
I'm going to switch over to the
assistants playground.
Creating an assistant is easy,
you give it a name, some initial
instructions, the model, GPT-4
Turbo, and I'll go ahead and
select tools.
I'll turn on Code Interpreter
and retrieval and save.
And that's it.
Our assistant is ready to go.
Next I can integrate with two
new primitives of this
Assistants API, threads and
messages.
Let's take a quick look at the
code.
The process here is very
simple.
For each new user, I will create
a new thread, and as the users
engage with their assistant, I
will add their messages to the
threads, very simple.
And then I can simply run the
assistant at any time to stream
the responses back to the app.
So we can return to the app and
try that in action.
If I say, hey, let's go to
Paris, all right.
That's it.
With just a few lines of code,
users can now have a very
specialized assistant right
inside the app.
And I'd like to highlight one of
my favorite features here,
function calling.
If you have not used it yet,
function calling is really
powerful.
As Sam mentioned, we're taking
it a step further today.
It now guarantees the JSON
output with no added latency and
you can invoke multiple
functions at once.
If I say, what are the top 10
things to do, I'm going to have
the assistant respond to that
again.
And here what's interesting that
the assistant knows about
functions, including those to
annotate the map that you see on
the right, and now all of these
pins are dropping in real-time
hire.
[cheers and applause]
It's pretty cool.
And that integration allows our
natural language interface to
interact fluidly with components
and features of our app, and it
truly showcases now the harmony
you can build between AI and UI
when the assistant is actually
taking action.
But let's talk about retrieval.
And retrieval is about giving
our assistant more knowledge
beyond these immediate user
messages.
I got inspired and already
booked my tickets to Paris so
I'm going to drag and drop this
PDF.
While it's uploading I can sneak
peek at it, typical united
flight ticket, and behind the
scene here, what's happening is
that retrieval is reading these
files and, boom, the information
about this PDF appeared on the
screen.
[cheers and applause]
And this is of course a very
tiny PDF but assistants can
parse from documents, from
extensive texts to intricate
product specs depending on what
you're building.
I booked an AirBNB so I'm going
to drag that over to the
conversation as well.
We've heard from so many of you
developers how hard that is to
build yourself.
You typically need to compute
your on biddings, set up
chunking algorithm, now all of
that is taking care of.
There's more than retrieval.
With every API call, you usually
need to resend the entire
conversation history, which
means, you know, setting up a
key value store, that means
handling the context windows,
serializing messages and so
forth.
That complex it now completely
goes away with this new stateful
API.
Just because OpenAI managing
this API does not mean it's a
black box.
In fact, you can see the steps
that the tools are taking right
inside your developer
dashboard.
So here if I go ahead and click
on threads, this is the thread I
believe we're currently working
on, and these are all the steps,
including the functions Building
Coded with the right parameters
and the PDFs I've just
uploaded.
Let's move on to a new
capability that many of you have
been requesting for a while.
Code Interpreter is now
available today in the API as
well.
That gives the AI the ability to
write and execute code on the
fly but even generate files.
So let's see that in action.
If I say here, hey, we'll be
four friends staying at this
AirBNB.
What's my share of it plus my
flights?
All right.
Now here what's happening is
that Code Interpreter noticed
that it should write some code
to answer this query so now it's
computing, you know, the number
of days in Paris, number of
friends, it's doing some
exchange rate calculations
behind the scenes to get this
answer for us.
Not the most complex math but
you get the picture.
Imagine you're building a very
complex finance app that's
crunching countless numbers,
plotting charts, so, really, any
task that you'd normally tackle
with code, Code Interpreter will
work great for you.
I think my trip to Paris is
sorted.
To recap here, we've seen how
you can quickly create an
assistant that manages states
for your user conversations,
leverages external tools like
knowledge and retrieval and Code
Interpreter and I know vocation
your own functions to make
things happen.
But there's one more thing I
wanted to show you to really
open up the possibilities using
function calling defined with
our new modalities that we're
launching today.
While working a DevDay, I've
built a small custom assistant
that knows everything about this
event.
But instead of having the chat
interface while running around
all day today, I thought, why
not use voice instead.
So let's bring my phone up on
screen hear so y so
you can see it.
On the right you see a simple
swift app that takes microphone
input.
I'm going to bring up my
terminal log so you can see
what's happening behind the
scenes.
Let's give it a shot.
Hey there, I'm on the keynote
Stage Right now, can you greet
our attendees here at DevDay?
>> Hey, everyone, welcome to
DevDay, it's awesome to have you
all here.
Let's make it an incredible
day.
[cheers and applause]
Isn't that impressive?
You have six unique voices to
choose from in the API, each
speaking multiple languages so
you can find the perfect fit for
your app.
On my laptop, you can see what's
happened behind the scene.
I'm using whisper to converts
the voice input into text, and
the new SSI to make it speak.
Function calling, things get
even more interesting when the
assistant can connect to the
internet and take real actions
for users.
So let's  do something A even
more exciting here.
How about this?
Assistant, can you  randomly
select five DevDay attendees
here and give them $500 in
OpenAI credits.
>> Yes.
Checking the list of attendees.
[laughter]
Done.
I picked five DevDay attendees
and added $500 of API credits to
their account.
Congrats to: (Reading name).
>> If you recognized yourself,
awesome, congrats.
That's it, a quick overview
today of the new Assistants API
combined with new tools and
modalities we launched, all
starting with the simplicity of
a rich text or voice
conversation for you end users.
We really can't wait to see what
you build and congrats to our
lucky winners.
Actually, you know what?
You're all part of this amazing
OpenAI community here so I'm
going to talk to my assistant
one more time before I step off
the stage.
Hey, assistant, can you actually
give everyone here in the
audience $500 in OpenAI
credits?
[cheers and applause]
>> Sounds great.
Let me go through everyone.
[cheers and applause]
>> All right.
That function will keep running,
but I've run out of time so
thank you so much, everyone,
have a great day.
Back to you, Sam.
[cheers and applause]
>> Pretty cool, huh?
[cheers and applause]
So that Assistant API goes into
beta today and we're super
excited to see what you all do
with it.
Anybody can enable it.
Over time, GPTs and assistants
are precursors to agents, are
going to be able to do much,
much more.
They'll gradually be able to
plan and to perform more complex
actions on your behalf.
As I mentioned before, we really
believe in the importance of
gradual iterative deployment.
We believe it's important for
people to start building with
and using these agents now to
get a feel for what the world is
going to be like as they become
more capable.
And as we've always done, we'll
continue to update our systems
based off of your feedback.
So, we're super excited that we
got to share all of this with
you today.
We introduced GPTs, custom
versions of ChatGPT that
combine instructions, extended
knowledge and actions.
We launched the Assistants API
to make it easier to build
assistive experiences with your
own apps.
These are our first steps
towards AI agents and we'll be
increasing their capabilities
over time.
We introduced a new GPT-4
Turbo model that delivers
improved function calling,
knowledge, lowered pricing, new
modalities and more.
And we're deepening our
partnership with Microsoft.
In closing, I wanted to take a
minute to thank the team that
creates all of this.
OpenAI has got remarkable talent
density but it takes a huge
amount of hard work and
coordination to make this
happen.
I truly believe I've got the
best colleagues in the world.
I feel incredibly grateful to
get to work with them.
We do this because we believe AI
is going to be a technological
and societal revolution, will
change the world in many wakes,
and we're happy to get to work
on something that will empower
all of you to build so much for
all of us.
We talked about earlier how if
you give people better tools,
they can change the world.
We believe that AI will be about
individual empowerment and
agency at a scale that we've
never seen before, and that will
elevate humanity to a scale that
we've never seen before,
either.
We'll be able to do more, to
create more and to have more.
As intelligence gets integrated
everywhere, we will all have
superpowers on demand.
We're excited to see what you
all will do with this
technology, and to discover the
new future that we're all going
to architect together.
We hope that you'll come back
next year.
What we launch today is going to
lack very quaint to what we're
creating for you now.
Thank you for all that you do.
Thank you for coming here
today.
[cheers and applause]