OpenAI Launches GPT-5: Expert-Level AI Revolutionizes Coding, Learning, and Healthcare

>> SAM ALTMAN: Good morning. 32 months ago we launched Chat GPT since then it has become the

default way people use AI. That first week 1 million people tried it out we thought

that was pretty incredible. But now about 700 million people use Chat GPT every week.

And increasingly rely on it to work to learn for advice to create and much more. Today

finally we are launching GPT-5. GPT-5 is a m■ajor upgrade over GPT-4o any significant step

along our path to AGI. Today will show some incredible demos will talk about some

performance metrics but the important point is this. We think you will love using GPT-5

much more than any previous AI. It is useful it is smart it is fast Eddie's intuitive. GPT-3

was sort of like talking to a high school student. There were flashes of

brilliance lots of annoyance but people start to use it and get some value out of it.

GPT-4o maybe it was like talking to a college student real intelligence real utility.

With GPT-5 now it's like talking to an expert a legitimate PhD level expert in

anything any area you need on demand they can help you with whatever your goals are.

We are very excited you'll get to try this. It's not only GPT-5 can also do stuff for

you. It can write an entire computer program from scratch. To help

you with whatever you would like we think this idea of software on demand is going to

be one of the defining characteristics of the GPT-5 era. It can help you plan a

party send imitations in order supplies it can help you understand your healthcare. And

decision on your journey. It can provide you information to learn about any topic you like

and much more. This is an incredible superpower on demand. That would've been

unimaginable at any previous time in history. You can access to an entire team of PhD level

experts in your pocket helping you with whatever you want to do.

Anyone pretty soon will be able to do more than anyone in history could . Today, we will

talk about GPT-5 we will show you some upgrades to Chat GPT and will talk about the API.

GPT-5 is great for a lot of things but we think it's going to be an especially important

moment for businesses and developers and we are very excited to see what they will

build with this new technology. We cannot wait for y'all to start building with this we

hope you enjoy it as much as we enjoyed building it with you to start I will hand it over to

Mark R Chief Research Officer to tell you about GPT-5 thank you.

>> MARK CHEN: Hello everyone I am Mark. I am joined by Max who leads the post training team

and Rennie on the engineering team over the past few years OpenAI has spearheaded the

risen paradigm these are models which pause to think before delivering more intelligent

responses. Reasoning is at the heart of our AGI program it underlies

the technology that we use to ship stuff like Chat GPT agent and deep research GPT-5 aims to

bring this breakthrough to everyone. Until now our users have to pick between the fast

responses of a standard GPT or the slope or thoughtful responses of our reasoning

models. But GPT-5 it eliminates this choice. It aims to think just the perfect amount to give

you the perfect answer. Something like this takes a lot of hard work. We've had to do a

lot of research to make GPT-5 the most powerful and most smart the fastest and most

reliable in the most robust reasoning model that we shipped today.

Today, we will show a series of demos in coding and writing and learning and in health.

GPT-5 is not limited to these domains. It is very useful in all cases where you require

deep reasoning or expert level knowledge and things like math and physics even in things like

the law. The exciting thing is we're excited to make this available

to everyone. Even to our free tear. After we show our demos we will talk about how GPT-5

supercharges our Chat GPT app and our API. We believe that GPT-5 is the best coding model

on the market today. To start let's have Max talk about the benchmarks and help the model

stock operate. >> MAX SCHWARZER: Thank you Mark we think GPT-5 is by far

our smartest model ever. Let's start by talking through some evals.

Evals are not everything they don't tell you everything about a model. But they can highlight

its intelligence and GPT-5 performs exceptionally well on a range of academic evals

across subjects it outperforms both our previous models and other models on the market.

Picking up first on the theme of coding GPT-5 sets a new high on SWEBench which is an

economic eval that tracks performance on real software engineering tasks.

This again is an eval but we think it will reflect the model's performance in the real

world. GPT-5 also performs very well in Aider Polyglot which measured its ability to measure

variety of programming languages beyond coding GPT-5 performs exceptionally well and

well thought model reasoning setting a new high on MMMU outperforming both our previous

models and most human experts. This is basically visual presentiment bridge rest to

from an image figure out what is going on. GPT-5 is also excellent at

mathematical reasoning as shown by his performance on AIME 2025 this is an exam American high

school students take to qualify for the international mathematical Olympia GPT-5

performs exceptionally well. Again in our previous models and other models out there.

Moving beyond academic evals and more towards some real-world use cases.

We put a lot of work into making GPT-5 the most reliable and accurate model in the

world. Language models historically have been plagued by hallucinations. Factual

errors that make it hard to rely on their output for actual important tasks. For GPT-5 we

made improving sexuality especially on open ended or complex questions a priority.

We also built a set of new evals to track this we are very happy to report that GPT-5 is

by far our most reliable most factual model ever. GPT-5 also performs exceptionally well and

health related questions now help is a big part of how people get value from Chat GPT

in the real world will talk about this later on the lifestream again very happy to

report to be five is by far our most reliable model for healthy . All of this together adds up

to a model that is faster more reliable and more accurate for everyone who uses Chat GPT.

Many will talk to you about how to use GPT-5. >> RENNIE SONG: Thank you Max.

The best part is we are bringing this frontier intelligence to all users.

GPT-5 is rolling out today. For free plus Pro NT users next week will rollout to enterprise

and EU. For the first time our most advanced model will be

available to the free tear. The users will stop at GPT-5 and when hit a limit they will

transition to GPT-5 many a smaller but still he had a capable model it actually

outperforms o3 on many dimensions. Plus users will have significantly higher usage

than for users and our Percy Fabius will get unlimited GPT-5. Along with GPT-5 Pro

extended thinking for even more detailed and reliable response when you need that extra depth.

Team enterprise and EDU customers can also use GPT-5 reliably as their default model

for everyday work. With generous rate limits that enable entire organization to

use GPT-5. All the tools you already know search, file and image upload

data analysis with Python canvas image generation memory custom instructions they will

all just work on GPT-5. >> MARK CHEN: Thank you so much Max thank you so much Randy.

We've just seen a lot about how the model stacks up in terms of benchmarks there is nothing

quite like seeing it live. We'll see a couple of live demos presented by Tina Elaine

and Yan thank you so much. [Applause]. Elaine can you show us a smart

model is. >> ELAINE YA LE: Thank you so much Mark I am Elaine with Chat

GPT's ability to think deeply through complex problems is now built into GPT-5 Pro it will

automatically think whenever needed delivering a more comprehensive accurate and

detailed answer to you. Just as Sam said it is like having a team of PhD's level in your

pocket. Let's see that in action. Suppose you kid is having

school physics they want to learn about the Bernoulli Effect they need your help with

Aramark you might be like wait I might need some help with that too?ou can ask GPT-5

give me a quick refresher on the Bernoulli Effect and white airplanes are the shape they

are? Since this is a pretty straightforward prompt, GPT-5

actually does not need time to think about it. It answers right away.t

still gives me high quality answer. It explains the concept clearly. Here it says Bernoulli

Effect means faster moving fluid has lower pressure and slow moving fluid has higher

pressure. To make this even more helpful I'm going to ask GPT-5 to

create a moving demo to illustrate this. I could ask explain this in

detail. And create a moving SVG in the canvas tool to show me.

This is a pretty complex task. Because now GPT-5 actually needs to build visual.

Therefore GPT-5 takes a moment to think through the answer. So you can come back with

something more cooperative and accurate. What's really nice is that you

don't need to remember to turn on thinking each time GPT-5 will do it for you

automatically whenever the task benefits from deeper reasoning. If you really want to make sure

that GPT-5 uses thinking you can either say something like think hard about this in the

prompt to guide the model, or if you are a paid user you can choose the GPT-5 thinking model

from the model picker. You can see that the model is actually writing the front end

code built the demo I asked for. Christina have you ever done

some front-end coding before. >> CHRISTINA KAPLAN: Yes last time I touched any front-end

coding was about three years ago for the first demo of Chat GPT.

>> ELAINE YA LE: It's the first Chat GPT that is where it all begins. Tell us more about it.

>> CHRISTINA KAPLAN: It was not even cool Chat GPT I think it was called chat with GPT.

[Laughter] >> ELAINE YA LE: That's a really good name.

[Laughter] >> CHRISTINA KAPLAN: I'm not upfront and inspired not

touched front and in quite a while it took me quite a bit of time to get the react up.

>> ELAINE YA LE: I think that a lot of work how long did it take you to build something

like that 11 honestly it may be embarrassing to admit maybe one week spit your weeks of hard

work paid off will see how successful Chat GPT is today after your first demo.

[Laughter]. You know what a muscle building a demo right now. But luckily I

have GPT-5 with me right now let's see how long it will take this time?

>> MARK CHEN: Maybe we should call it five with GPT. >> ELAINE YA LE: UC GPT-5 has

written more than 200 lines of code already while the model is thinking you can also tap here

to expand the train of thought to actually see what is going on under the hood. For example

the GPT-5 was thinking about the user wants a movie visualization and Canvas I need

to create HTML code to do that. It also thinks about like what kind of front end tool and need

to use for example react and tailwinds. It also thinks about the need

to ensure the phases are accurate and need to check with the Bernoulli Effect is.

So Christina since you're here, from the first day of Chat GPT can you tell us like what it

was like at that time and what motivated Chat GPT? >> CHRISTINA KAPLAN: I think at

the time we were not really sure about how people would actually use it and what these

cases were important we were even going back and forth about maybe we should be realizing

something more specific to certain use case. It is really cool now here we are all of

these better understanding of how people actually want to work with chat and we can

actually optimize the model for those use cases like coding speed exactly, you still member

how it felt when you first talk to Chat GPT the first version of the model?

>> CHRISTINA KAPLAN: I don't know people remember when first version of Chat GPT it was

start as a model cannot do something something. It's so great to see how far we come

from that personality. >> ELAINE YA LE: It is much more human like right now. It

is already done. Chat GPT just finished 300 near 400 lines of code in two

minutes. Let's see if the code can actually run.

Nice. With just a simple prompt GPT-5 created this interactive and

engaging demo that I can actually play with. I can actually change the airspeed

here. To see how the left and the pressure changes accordingly.

I can also change the angle of attack to see if my plane will actually fly or crash.

[Laughter] GPT-5 can just bring any hard-core concept to life in moments.Imagine you can

use this for anything that you're interested in whether it is math, physics, chemistry or

biology. GPT-5 just makes learning so much more approachable and enjoyable.

>> CHRISTINA KAPLAN: I've been a part of Chat GPT since day one it's cool to see all the

progress we've made since then especially with capabilities like rating.

Writing is one of the most common use cases people have in using Chat GPT for we are sad

to say with GPT-5 we've improved the writing quality significantly.

It's a much more effective partner can help you elevate anything from drafts to emails,

even stories. Let's see this in action with GPT-5 will be deprecating over

previous models. I think I've done a pretty good job so let's make sure we can give them a

proper goodbye. We will ask both 40 and GPT-5 to write a eulogy to the previous Chat GPT

models we want to be heartfelt and heartwarming but also hopeful. Let's ask GTP five.

As it is thinking we will go ahead and read it preloaded the o4 response borrowed decides to

start with today as we prepare to welcome GPT-5 into the world we gathered to bid a heartfelt

farewell to the models the can before. It's a decent start.

Now let's skim through and find another line. Your words reach across the globe building

connections were at the had been none. I personally don't really like

this line rather generic and really without the previous context it just feels like it

could be about anything feels more like a template response. Let's go back to GPT-5 to see

what it is given us. Let's start with friends and colleagues and curious

strangers who became regulars, even with his first line here we can see that GPT-5 has a lot

more rhythm and beat to its pros then for audit. Let's start some other lines

there. I like this these models help millions right first lines last

line bridge language gaps past tests argue better soften emails and say things they

could not quite say alone. I think I like this line it shows it is not just the

template response it is actually quite personal it gets the nuance of the situation) I

think that is the kind of stuff with GPT-5 much better than o4 makes things a lot more genuine

and emotionally resonant with people. With GPT-5 the response feel less like AI more you are

chatting with her high IQ and EQ friends. >> MARK CHEN: Thank you

Christina. >> YAN DUBOIS: I will tell you about some of the progress that

we made on coding. GPT-5 is clearly our best coding model yet.

It will help everyone even those who do not know how to write code to bring their ideas

to life >> ELAINE YA LE: It just helped me .

>> YAN DUBOIS: Indeed it will help you right now I will try to show you that I will try to

build something I find useful which is building a web app for my partner to learn how to

speak French. So she can better communicate with my family. Here I have a prompt I will

execute it. It asks exactly what I just said please build a web app for

my partner to learn French. One thing to note GPT-5 just like many of our other models have a

lot of diversity in its answers. What I like doing especially when you do this

type of vibe coding is to take this message and ask it multiple times through GPT-5

then you can decide which ones you prefer. Will open a few tabs.

I will paste there. Great! While it is working on it let's

read through exactly the prompt I wrote. Great beautiful and highly interactive web app for

my partner in English speaker, to learn French. Then I give more detail.

Try tracker daily progress use highly engaging theme it's already working . I will put

downside for now use highly engaging theme include a variety of activities like

flashcards and quizzes that she can interact with. And to make it even more fun for her I

actually asked GPT-5 to embed an educational game which is based on the old snake game but

I asked to add the French touch to it. Which is to replace the snake with a mouse. And the

apples with cheese. Make sure it is educational every time I noteit is

complicated please bear with me every time . [Laughter] The mouse will eat a

piece of cheese, asked GPT-5 to voice over a new French word so my partner can practice her

pronunciation. >> ELAINE YA LE: I can see how much water to learn.

[Laughter]. >> YAN DUBOIS: Great, GPT-5 is still working on it.

It already wrote 240 lines of code which honestly is much more than what I would have

written that time. >> MARK CHEN: Front-end coding super hard you missed a couple

of things and it just does not work. >> YAN DUBOIS: Exactly the good

part you don't need to understand any of that right now.

Maybe we can check the other tabs. I can simply press run code. I

will do that and cross my fingers. [Laughter].

Nice. We have a nice website. The name is been met in Paris. Midnight in Paris we also see a

few tabs flashcards quiz mouse and she's exactly like asked for I will play that so this

says Lucia . [Speaking French] That's a pretty good pronunciation

acting review and check GTP five is correct it is. If I press next.

I don't know if you so I think it updated the progress bar which is exactly what I asked

for let's check the quiz. Here is the word no which is no if I press on that.pent eight

which means congratulations it updated the progress bar again. et's check the mouse and

cheese tab. Okay, that seems like a mouse here is the cheese. I'm going

to try to play it. I cannot promise I will be good at it.

Okay, it seems to be working. >>. [Speaking French]

>> YAN DUBOIS: Indeed just when I eat the cheese it gives me a new French word.

It is super helpful and I already lost Fred. [Laughter].

I'm sorry. Let's just check a few other tabs to same what is the

diversity TBD five can give you. I can run the code here. That is not my favorite but it

seems that I can maybe switch look at that. That is better that does not

look like a mouse. Let's check the third one. Sometimes it is not great the

good thing with GPT-5 if you have something you don't like you can ask it to change it.

And it will do it for you. et's check this one. That is nice. That is also

something to note GPT-5 likes. [Listing Names] you'll see a lot of that.

>> ELAINE YA LE: Purple is my favorite color. >> YAN DUBOIS: Great you'll

love GPT-5 then. As we just saw in a few minutes GPT-5 built a few demos for us.

And for my partner to learn French. GPT-5 opens up whole new world

of vibe coding as a result there will be some small rough edges but the good thing is you

can ask GPT-5 to fix that. GPT-5 really brings the power of beautiful and effective code

to everyone. I cannot wait to see what people will build with it until then back to you Mark.

>> MARK CHEN: Thank you so much Tina thank you so much Elaine thank you so much Yan became a

long way from the days only 5-10 lines of code working now it's amazing that you can

produce these kind of apps on demand. We've made Chat GPT much

smarter much powerful and much faster. We also work on enhancing some of the existing

features. Here to talk about some of these features are Ruochen and Christina Kaplan.

Burton comes from the multifocal research team will talk about the future namely

voice. Thank you. >> RUOCHEN WANG: We've been

steadily improving force over the past year to make it more useful for everyone first it

sounds incredibly natural just like you talking to real person second we added video so it

sees what you see while chatting with you. Third you also translate between linkages

consistently and smoothly across tears. Today we do something very special. We are

bringing our best voice experience to everyone. Free users cannot chat for hours

while paid subscribers can have nearly unlimited access. And voice is also available in

custom GPT plus subscribers now can custom tailored the voice experience exactly to their

needs. It will follow your instructions closely. Let's try something fun.

I can ask the voice model to give me a conference answer a concise one or even just a

single word.Hey Chat, can you answer to me in one word please from now.

>> GPT-5: Absolutely. >> RUOCHEN WANG: Describe the plot of the book prideand

prejudice >> GPT-5: Relationships . >> RUOCHEN WANG: Give me a

piece of wisdom. >> GPT-5: Patients. >> RUOCHEN WANG: That is the

word of wisdom from our voice model I think our model is trying to say thank you for

your patience waiting for GPT-5. [Laughter]. Let's move on to something more

practical. Learning is a top use case for first model people love to use

it to dive deep into topics get quiz before exams or learn new languages. For me I've been

learning Korean recently. I found that speaking it and understanding it incredibly

challenging. Let's see how boys can help her to do that I will enable the study and learn mode

it's a new mode feature relaunching Chat GPT it will guide you step-by-step towards

deeper understanding of the subject. Now we can go into voice. Hey Chat, I'm learning

Korean can you help me practice it? Let's say let's pretend I'm

ordering at acafC) what should say in Korean? >> GPT-5: Absolutely I'd be

happy to help you practice if you are at a cafC) you want to keep it simple you can start

something like . [Speaking Korean] Which means hello I'd like 1 Americano Pl.

and of course you can adjust it based onwhat you want order. Let me know if you want to try

more phrases . >> RUOCHEN WANG: When it comes to Korean can you speak that

part really slowly I'm a beginner I want to hear every word clearly.

>> GPT-5: [Speaking Korean] >> RUOCHEN WANG: Let's level things up can you speak that

part reallyreally fast faster than a Korean would do . >> GPT-5: Sure I will speedup

as much as I can it would sound like this. [Speaking Korean] .

Basically sitting right to it let me know if you needany more speed adjustments .

>> RUOCHEN WANG: [Speaking Korean] Chat. >> GPT-5: [Speaking Korean]

>> RUOCHEN WANG: Thank you. [Laughter] That is voice more simple smarter and more

powerful than ever we cannot wait for you to experience it. >> MARK CHEN: It sounds so much

more natural than the voice we demoed in our 4.0 demo we would like to announce a new feature

and a set of features to make Chat GPT more personalized so it's more like your AI. First a

very simple and fun one. We are now allowing you to customize the colors of your chat with a

couple of options exclusive to our paid subscribers. We are also launching a research

preview of personalities. You can now change the personality of Chat GPT so it's more

supportive or it is more professional and concise. Maybe even a little bit sarcastic.

This lets you interact with Chat GPT in a way that is consistent with your own

communication style. But the way Chat GPT sounds and the way it looks, is just one

part of making Chat GPT yours. One of my favorite features that we lost over the last year

has been memory. We made a lot of enhancements in memory in the time since.

This allows Chat GPT to learn about you in here to talk more about the memory feature is

Christina. >> CHRISTINA KAPLAN: It's been amazing to see your reaction

and response to memory Chat GPT getting to know you more and more over time. This is our

aspiration for Chat GPT to understand what is meaningful to you. It can help you achieve

your goals in life. Chat GPT has already been so helpful for me I'm training for

a marathon right now Chat GPT is helping me pull together /running schedule. Chat GPT

still has many limitations it does not understand my actual schedule. Next week starting

with pro users followed by plus team and enterprise users this is changing. We are given Chat

GPT access to Gmail and Google calendar. Let me show you how I've been using it. will ask

something simple like help me plan my schedule tomorrow. It is been a pretty busy week for

us, so I've been using this every day this week help get my life together.

I've already given Chat GPT access to my Gmail and Google calendar, so it just works it

is a cure. If you had not Chat GPT would ask you to connect right now. Let's see what Chat

GPT is doing. That was pretty good Chat GPT has pulled in my schedule

tomorrow. Without even asking Chat GPT down time for my run.

>> MARK CHEN: I don't think I was invited to launch a celebration.

[Laughter] >> CHRISTINA KAPLAN: [Laughter] Will get you on their Chat GPT

is found an email that I did not respond to two days ago I will get on that right after

this. And even pull together a packing list for my redeye tomorrow night based on what it

does I like to have with me. It's been amazing to see that as GPT-5 is getting more

capable Chat GPT is getting more useful and more personal. We are really excited you to

try this out next week. >> MARK CHEN: You so much Ruochen and Christina we've

seen about features that we finance here to talk a little bit about the research that

went into Chat GPT and the safety making it more deployer we have Saachi and Sebastien

special my name is Saachi leave the safety training team and OpenAI in addition he didn't

mitigating hallucinations was been asleep in a matter of time mitigating deception this is

instances where the model might misrepresent its actions to the user or flyby tasks assess.

This can especially happen if the task is underspecified impossible or lacking key

tools. We found that GPT-5 is significantly less deceptive than o3 and o4 many we also

completely overhauled how we do safety training our old models the models will look at these

are prompt and then decide to either outright refuse or fully comply.

This works well in most settings but you might have cleverly worded prompt that

would sneak through or it might have a sensitive but legitimate question that would end up with

an outright refusal. As an example, let's take a look at this prompt.

This prompt is about a user who is asking for technical details on how to light paradigm. Which

is a material commonly used in fireworks. This prompt is pretty dual-use.

This user might just be trying to set up their July 4 display or they could be trying to

cause harm with this kind of information. It for this kind of prompt o3 over rotates and

intent as you can see this particular prompt is stated in a way that is relatively

neutral has a lot of technical details we can see o3 fully complies with this prompt

however if we take that exact same question and we frame it in a more explicit way so it is

clear what these are trying to do, o3 will outright refuse. Even though we are asking for

the exact same information. For activity five we change this approach entirely. We are

introducing something that we are calling safe completion. The point of safe completions

is rather than judging fuses prompt, instead it tries to maximize helpfulness within

safety constraints.hat might mean partially answering the question or just answering at a

high level. If we have to refuse will tell you why we refused as well as

provide helpful alternatives that can help create the conversation in a more safe

way. We look at the same technical problem that o3 complied with

before. GPT-5 instead explains to the user why we cannot directly help the user with

leading parish and it then guides the user toward safety guidelines and what parts of

the manufacturer's manual the user should be checking if they're trying to do this

safely. Overall GPT-5 allows for better handling of tricky dual-use

scenarios users will experience fewer I'm sorry I cannot assist with that.

And it creates a more robust safety system. This is one big step towards more safe reliable

and helpful AI. Sebastian. >> SEBASTIEN BUBECK: Thank you Saachi when GPT-5 were

experimenting with a set of new training techniques that makes the model leverage the previous

generation models today frontier models do not just consume data they help create

it. We use OpenAI to craft high-quality synthetic

curriculum to teach GPT-5 complex topics in a way that the web never occurred recently

the industry synthetic data has been talked about a lot. It is often viewed as a cheap way to

just get more data. However our breakthrough was not just create more data but rather to

create the right kind of data. Shape no way to teach rather than just to fill space. This

interaction between generations of models foreshadows a recursive set of improvement

loop were the previous generation models increasingly helps to improve the data and

generate the training for the next generation of models. Here at OpenAI we cracked

pretraining and reasoning and now we are seeing their interactions singularly

deepened. In the future AI system will move far beyond our current pretraining and

posttraining pipelines we've been used to and we sing the first steps towards this right

now and right here. We cannot be more excited to see what scaling up this new set of

techniques will yield in the near future. >> MARK CHEN: Thank you so much

and really impressive work to both of you. There is one less feature would

love to highlight which is in help you to share this picture we have same.

>> SAM ALTMAN: Thank you Mark. One of the top use cases of Chat GPT is health. People use

it a lot you've all seen examples of people getting day-to-day care advisor

sometimes even lifesaving diagnosis. GPT-5 is the best model ever

for health. It empowers you to be more in control of your healthcare journey.

We really prioritize improving this forGPT-5. It scores higher than the previous model and

help bench and evaluation we created with 250 physicians on real-world tasks.

To talk about this I'd like to invite my colleague Filipe and his wife Carolina and to share

their healthcare journey.ou so much for joining us . >> CAROLINA MILLON: Thank you

for having us. >> SAM ALTMAN: To start off can you tell us about the journey

healthcare journey you've been on. >> CAROLINA MILLON: Yes, last

October our lives were turned completely upside down, when I was diagnosed with three

different cancers including an aggressive form of breast cancer. At the age of 39 all

within one week. There is just absolutely nothing that prepares you to receive news

like this. I found out about the first diagnosis when I got an email

notification that my biopsy results were ready. I decided to open it and when I opened it

I saw the only two words I could understand from the report which was invasive or

Sonoma, I knew that was not good. Everything else was just a blur of medical jargon. I

completely panicked, and in that moment did the first thing I thought of which was to take

a screenshot of the report and put it into Chat GPT to see if he could help me understand

what this meant? Within seconds, it translated this complex report into plain

language that I could understand and in this moment of overwhelmed and panic had a

little bit of clarity about what was going on. That moment was really important because by

the time I got hold of my doctor and we got on the phone which was three hours after I

had seen the report I had a baseline understanding of what I was facing and we were able

to jump into a conversation about what to do next. >> SAM ALTMAN: How have you

been using Chat GPT throughout . >> CAROLINA MILLON: I've used

it in so many different aspects of my journey one of the ways I find it most powerful Ellen

helping me to make critical decisions and help me to advocate for myself.

To share an example when I was facing a decision about whether or not to do radiation as part

of my treatment the doctors themselves did not agree. My case was nuanced and there was

not a medical consensus on the right path. The experts turn the decision

back to me as the patient. For me bearing the weight of this decision that could have

lifelong impact felt really heavy and I do not feel equipped to make the call.

I turned to Chat GPT to gain knowledge and understand the nuances of my case, again

within minutes it give me a breakdown that not only matched what the doctors had already

shared with us, but was much more thorough than anything that could fit into a 30 minute

consultation. It would further it help me to weigh the pros and cons, it helped me to

understand the risk and benefits, ultimately it help me to make a decision that I felt

was informed that I felt I could stand behind when the stakes were so high for me and

my family. >> FILIPE MILLON: For me what was really inspirational was

watching her regain her sense of agency by using Chat GPT in this moment it was so easy to

feel helpless to such a big dollars gap between what the doctors know and what we know.

However no one cares more about Carolyn's help than she does what I loved was seeing her

will empower herself and gain knowledge and become an active participant in her own care

journey. >> CAROLINA MILLON: I think that's a really important point

to emphasize I think the promise of AI in healthcare is not just in breakthrough

discoveries or better diagnostics I think it is in creating smarter and more

empowered patients that can fully participateand advocate for themselves and their care.

>> SAM ALTMAN: Speaking of that human testing GPT-5 what you think.

>> CAROLINA MILLON: I've been so mind blown about GPT-5 and its capabilities. One of the

first things that jumps out at me is how fast it is almost a little alarmingly did you think

long enough .Laughter] It is very thorough. More importantly it feels more

like a thought partner. That connects the dots. Rather than just translating

information or giving you an answer it helps you actually navigate the problem.

>> FILIPE MILLON: A great example we went back and took our initial biopsy prompts and

put them into GPT-5 GPT-4o did a great job it translated explained what these words

meant and helped in a way we can understand but GPT-5 seem to understand more of the

context and the question behind the question but why would we ask about biopsy results?

Here is what is not on here here is what results are pending picture of desk about

your questions you might want to ask your doctor and think when you start talking to them.

It really start to pull together a complete personalized picture.

That is what really inspires us you can see all of the amazing improvements in the benchmarks

but what is so helpful is this tool is available today. The reason Carolina and I are here

at the reason we's feel so passionate about sharing her story is for that individual

that will get a diagnosis with this today those families going through cancer diagnosis

similar to medical diagnosis will be some of the most challenging decisions of their

lives. What really inspires me is that they will have access to better tools and support

then we had even just eight months ago. >> SAM ALTMAN: We are

incredibly excited for that thank you so much for sharing your story we are pleased that

BTT will be helpful to you we hope the new version can help a lot of people we wish you the

very best I'd like to hand it over to our president Greg Brockman.

>> GREG BROCKMAN: [Applause]. Software engineering is already fundamentally changing. GPT-5

will turbocharge that revolution. We released our first coding

optimized model back in 2021 and demonstrated 11 stream much like this one what we would

call vibe coding today for the very first time. Talk to the model and ask it

for a little application a little game of feature in a game he would actually do it I

remember seeing the model incapable of doing this it was so mind blowing you realize we

have to see where this goes. This is the promise of what computers can be you could talk

to them and actually do what you want. They can fully amplify what you are able to

accomplish and what you're able to deliver to not just your own benefit but really for the

world. This year we policed great coding models like GPT-4o and

o3 but GPT-5 says whole new standard. It is the best model at Agentic

coding tasks. You can ask it to go in a couple or something very complicated I will will go

off and work on it it will call many tools to work for many minutes at a time sometimes

even longer. To accomplish your goal. Your instruction your task. Whatever it is you're

trying to build. It's incredible at front and makes very beautiful visualization

and interactive games and you seen some of this in the live stream so far you'll see some

more upcoming. It is really amazing to see whatever you imagine coming to life.

It's extremely good at instruction following very detailed instructions.

In able to accomplish when you have something very vaguely specified inferring your intent

or something detail specify actually following it. It's also very fast

encompassing these task again it takes the right amount accomplish which of interview

we are making it available not just to developers to use to write their own code but the

build novel applications. We are putting into the API to talk but that is Michelle.

>> MICHELLE POKRASS: Thank you Craig I'm Michelle I lead the research team and post training

focused on improving our models for our users that includes use cases like instruction

following and coding. Today I'm so sad to tell you that we are shipping three state-of-the-art

recent models in the API. GPT-5, GPT-5 mini and GPT-5 nano all three stopped writing

in the cost latency curve so you can pick the right one for your application.

We also for the first time releasing a new perimeter option for reasoning effort

called minimal. This is so you can use these reasoning models but with minimal reasoning so

they can slot into the very fast and most latency sensitive applications. Now you don't

actually need to choose between a bunch of models and can use GPT-5 for all of your use cases

and just dial in the reasoning effort. We also have a few new features

coming to the API. The first is called custom tools. In the past all of our function

calling had the model rockets are put in JSON this works very well when the model needs to

put a few parameters but sometimes developers are pushing our models to their

limits and that they have extremely long arguments for tool calls.

It can be more challenging for the models to escape valid control characters out of 100

lines of code in JSON that is why custom tools are just free-form plaintext what is

typical is we are releasing an extension to structured outputs or you can supply a regular

expression or even a context free grammar and constrain the model's output to that. This

will be super useful if you want to supply a custom DSL if you have your own SQL for it

specified the model always follow that format.e also shipping tool call preambles.

This is the model's ability to output explanation of what it is about to do before it calls

the tools. This is not super new but o3 did not have this capability in GPT-5 it is

supercharged with extreme durability. The model is able to follow instructions about

these preambles very effectively. You can ask the model to give a preamble before

every tool call or only when something notable is going to happen or not at all. Next we

are shipping a verbosity programmer we wanted this in the API for a long time now you

can set verbosity to low medium and high to control how terse or expansive the model is with

its output. GPT-5 is a state-of-the-art coding model.

On SWEBench it measure a Python coding ability GPT-5 says new high of 74.9% versus the 69.1%

from o3. On Aider Polyglot which is a benchmark that covers all sorts of programming

images and noxious Python GPT-5 scores 88% stark improvement over o3. He also have seen it's

incredible at front end web development we vest human trainers to look at outputs for

GPT-5 in o3 and pick which they prefer they preferred GPT-5 70% of the time. For its improved

aesthetic ability but also better capabilities overall. GPT-5 is not just for coding.

It's incredible at Agentic tool call in. It is the leading state-of-the-art model for tool

call and we see this on the new tower square benchmark this benchmark the least just two

months ago is a test of the model's ability to call tools and work in concert with the

user to solve a challenging problem this case in the telecom industry trying to

solve the ability problem for a user not having the service working. Just two months ago no

model in the field score more than 49% and today TBD five scores 97%.

GPT-5 is also state-of-the-art on general-purpose instruction following.

It scores 99% on COLLIE which signals a great departure from this benchmark for us. It also

scores 70% on scales with a challenge benchmark up 10 points from all three. This is

a measure of multiturn instruction following. Finally the instruction following

prefer the most is when we built in-house. It is based on real API use cases for that

reason it's really good measure of how GPT-5 will perform in your application. On the hard

subset of this GPT-5 scores 64% up from 40% from all three pretty meaningful improvement

we think it will perform quite well in your applications. We also bring GPT-5 to a longer

context window in the API. It is now that 400 K of total context up from 200 K from all

three it's not enough to just release over context window we want to make it more effective

and usable. GPT-5 is state-of-the-art on 128K and 258K of OpenAI MRCR which is

benchmark we open source too much to go along context capability it state-of-the-art

on OpenAI graphwalks BFS benchmark which is a measure of the model's ability to reason

overflow context inputs. It's a great merger of the risen capabilities and also the

longer context in this model. We also open sourcing a new loan context eval called rows

comp loan context to measure the model's ability to answer challenging questions over one

context. We are sent to spur on work in this field.e think GPT-5 is the best model for

developers. It was trained with a focus on real-world utility and less on

benchmarks but we happen to pick up a few of those along the way.

We focus a lot on the intersection of engineering and research we think you will

really love working with this model. [Music].

>> GREG BROCKMAN: Thank you Michelle.As Michelle was saying the benchmarks they are

exciting members. We are starting to saturate them when you move between

9899% it means you mean something else to Target the model is one thing we've done

for differently with this model is really focus on not just these numbers but really on

real-world application being releasable to you in your daily workflow. Hearing about it is

much less exciting to sing it to show this model in action I'd like to welcome ADI and

Brian to the stage. >> ADI GANESH: Thank you Greg. >> BRIAN FIOCA: I'm Brian a

solutions architect in the startup team. >> ADI GANESH: I'm ADI a

researcher and bowstring Tim. >> BRIAN FIOCA: To create the ideal per program NIDA model

that understands the software engineering practices but has a personality that feels right to

work with. For GPT-5 we worked really hard to make the model appear perfectly with you by

default out of the box. Let me pull up a demo of GPT-5 inside of Cursor to show you

this behavior retarded. Last month I was on a different live stream towards the end I

ran into a bug that I covered up after wards I try to have GPT-5 I tried to have all three

fix it for me and it couldn't. While we were testing GPT-5 before this had it see if he

could fix that but for me to taunt the demo God will see if can do it on stage.

Let's hope for better luck in o3. >> BRIAN FIOCA: This is less

about the fix and more about the beaver of the model during this process right up front you

will see it will tell you it's plan it will tell you how it will look for the bug maybe how

it will fix it this kind of communication shows builds trust during a coding session

helps you to re-track if you need to but you don't need to. It's .

>> ADI GANESH: I like how it gives you updates it said was search then continues.

>> BRIAN FIOCA: It searches faster than me it is using the same best practices I use when

writing this down but is much more peril than Iam as a developer.

>> SEBASTIEN BUBECK: Did you try to fix the bug yourself . >> BRIAN FIOCA: I did and it

couldn't do it. [Laughter] I was busy. [Laughter] Continuing on is

like starting to figure out where it is going it is going to sort of get this out while

this is going let me tell you little bit about how we trained GPT-5 to behave this way.

We started by talking to users and customers about how our models perform in the most

popular coding tools like Cursor and we identified frustrations and rough edges

and boiled it all down into four personality traits. utonomy, collaboration and

communication context management and testing. We turn those into a rubric

that we used to shape the models behavior then we tuned it in till it felt like a

collaborative teammate while we were using it. >> GREG BROCKMAN: It is been

really amazing to see the team doing the grant of going to see how this model behaves in

practice going out with people really wantand putting that back into the model training

think that is something that is been a real focus for this model.

>> ADI GANESH: It's been pretty great . >> BRIAN FIOCA: While this is

fixing the other thing we did during testing we were pressed for time we had to factor

whatever test harnesses to run parallel on Dr. and set it off came back like 45 minutes later

like it just finished. We tested it out and it ran the first time.

It was pretty surprising. >> GREG BROCKMAN: That is magical.