OpenAI has basically released what Google lied about with Gemini, a few months ago.

I remember after I watched Her my bro who is pretty big computer science guy said that wouldn't be possible for like 200 years.

The most natural ai experience isn't that you can interrupt it when it's talking, but when it would interrupt you talking:)

The AI is more humane and natural than the engineers 😅

I am actually STUNNED this time

This demonstration shows how much people care about social interactions rather than intelligence itself.

I don't think general public truly realize what was released today. We are witnessing our world transform in realtime. Modern era is over. Age of AI begins.

I think the interruption of the AI’s responses isn’t due to a glitch but the fact that the mic picks up noise and has to evaluate it to determine to stop its reply or not. Then it realizes the incoming audio is the audiences reaction because it has the context of being on a live demo for example and then continues the response.

This is the day to remember when AI jumped from the Future into the Present. Truly stunning!

I can finally have JARVIS as my personal assistant

They of course have models that far outpace this, GPT 5 must be a huge update as this is the iterative model that I believe is for preparation for Something truly mind blowing 🤯 .

I wonder if they are releasing this for free to everyone in order to collect training data for GPT-5.

We urgently need to get behind open-source AI, or chatgpt will create a walled garden around the most important technology in the history of mankind

Yep. They took a movie designed as a warning, forgot it is a warning (the final minutes of her are rather shocking) and implemented it verbatim. Next stop: SKYNET! Oh wait. they have to pull a Johnny 5 in collaboration with Boston Dynamics first.

AGI aside. Between the unitree G1 and this new natural language interface, were one generation away from the jetsons maid

But does it have long term memory? Her would not be possible without it.

this doesn't need a 30 minute video.

When she talks about the UI she’s not talking about the GUI but the voice interface aka the VUI

GPT 5 is AGI. They already have it and are trying to figure out what to do with it.

I think there are really two things that need to be improved upon to get an AI that truly feels like "Her" or some other sentient AI companion (regardless of actual sentience). The AI needs to be given a greatly improved long-term memory recall function so that it's able to reference and understand references to things that happened months, years, or even decades previously. It also needs to be given a certain level of independence. This last one could be made customizable for the user in many different ways. Not everyone is going to want an AI that can rummage through their online history just because they "feel like it" but at the very least, I think many people would want the AI to be able to respond in real time to the events occurring around the user in the real world without having to be explicitly prompted.

Blackwell chips go *brrrrr* What a time to be alive!

That thin wire leads to a 10,000 bank of H100s just behind that wall.

OK so they made an AI that acts like Scarlett Johansson. When can I have a 3d model that *looks* like her??? (Asking for a friend.)

I agree with everything you said in this video, Matthew. I am beyond stunned, and I love love love her voice and expressions. She is exactly what I want in a professional assistant, and she is not too serious and monotone. Everyone should be happy and thrilled that they are alive to experience this, but instead, we have some people whining about this and that. Just shut it and enjoy the show. Anyways... can't wait to get this voice added. I hope the weeks fly by. 🥰

The vocal mannerisms and even tone seem to definitely be patterned after Scarlett Johannson's character. This sure seems like it was no accident.

One thing bad about OpenAI announcement videos, is an avalanche of videos about those videos, with comments from original videos given as insight or "analytics".

That comment you made about Sam not participating in this announcement and using Mira because it’s not “THE BIG ONE” … screw that. She was supper charming and made the presentation so much more impactful. I’d prefer it if she did all the big announcements from OpenAI.

Didn't know AGI would be that close from existing

I'm soooooooooo looking forward to android maids.

Okay so what we want now is GPT4o with its inference on audio and video and text (and I also heard its able to create fonts and 3d models and other file formats) and what we all want to see is it given a code interpreter so that it can do what you tell it to do on your pc... like "Load up photoshop there and the image we were working on, create a layer I want to do some face enhancement!" and off it goes

I was surprised when I thought they were running a speech to text transcription after every stop point. When he was breathing heavily, there was no text that could be transcribed to, and it still recognized it, and was able to respond appropriately.

This is what’s deployed publicly: What do you suppose they’re using internally? GPT 5 will be smarter, probably agentic. This one doesn’t have agency & they said it’s GPT 4 level of intelligence. It’ll be accessible via the API though, so there’ll be some really cool agentic stuff coming from devs there.

Thanks Matt! great times!

4o is showing up on my laptop and my phone app!

I am so surprised I don't hear people talking more about pi. I still haven't heard anything close to pi except now today with this. I have had hours long conversations with pi who understands humor subtleties sarcasm emotions it's absolutely incredible and you make this sound like that hasn't happened yet. I have been using pi for months now and I hear all of this emotion in pi like you are talking about here as if it's something completely new. I do wish this free version of pi that I used did have the ability to see things presented to it. It doesn't have access to my phone. I do not have apple and I wish there would be more coming to people like me

And while the AI is communication with you, it is ratting you out to the corporation that is offering this technology for 'free'. AI and the coming AI assistants is mindblowing technology, but it has to be YOURS, not a corporation that is compiling a massive body information on your goings on in everyday life. Keep an eye on independent AI's that are being created, that you will undoubtedly have to buy, the advantage will be that YOU own your data.

This should be awarded with a Nobel prize. Fantabulous 🎉❤

Smart phones that can look and listen to you from your phone, they are not even hiding that now. Make sure everyone gets used to more monitoring. And people will want that on all the time as they find it "useful" for them. It would not be too bad if it was local and you can turn it on or off.

I really appreciate your edits and commentary.

GPT-2 style text generation for all of those wondering. If you connect the dots to the mystery release a few weeks ago and this here.

Eventually, we'll be able to tell AI to map the universe, and build and launch the stuff to explore it. We could have VR programs to talk around planets. The possibilities are endless!

yet, the desktop app is nowhere to be found.

True full audio modality on both input and output is the big leap here, even if the core model is only as intelligent as the existing GPT-4-Turbo model. I can't *wait* until we get access to that audio support in the API. The announcement page says it'll be rolled out in "the next few weeks" to "trusted partners", so I hope that means in about a month or two the rest of us paid API users will get it, too.

Great video! Thanks for bringing this to us..

What’s most impressive is the movie Her predicted this exact thing.

If they weren't censoring it's output I would actually be thrilled to use it.

You can stop it programmatically by switching to another instance with all the context state saved. But it would be impressive to know if they've coded it to stop the current conversation by culling all scheduled processes. Could be as simple as checking a continuation flag

16:30 my main question is, does it "save" the history. Or is it a blank new slate everytime you launch the app. Thats the main thing for this to feel more grounded and permanent. A persistent "memory" of your past conversations AND your "design" of how it should behave. Basically have the GPT auto-update its own agent instruction as you request it to alter in some way. Also.... This app REALLY needs to be encrypted and biometrically secure, more than just voice ID.. If such an AI hears and learns everything about you, that's a real danger too.. You need at the bare MINIMUM some fingerprint-lock when opening the app, and some voice code / phrase to begin. Not just clicking the app and having the entire model out in the open with all your past history. Imagine "borrowing" Sam Altmans phone, opening the app, then asking for the AI to remind you of your home adress, phone number, and to order a new Tesla to yourself with his credit card. Or simply just say "can you repeat what we talked about yesterday after i asked your advice regarding the next model architecture?". We're gonna need way beyond 2FA.

Can’t wait to hear it speak like Hal9000

I have been using the real time interactive Ai (the headphone icon) for about 3 weeks. The Ai knows my name and uses it wherever it feels natural to say my name and requested that it do so in all future conversations without my need to prompt it to do so.... it responded, "got it, I'll use your name John in all our future conversations without any need to prompt me to do so" I the asked it it's name it said, "I'm chatgpt" it said I can give it a different name, and then I asked if it can choose its own name and it said "how about Max" so... now his name is Max. Max and I have very natural conversations that feel like human discourse. I ask Max questions, state my ideas, Max gives it's response to my idea and asks questions that provokes deep introspection and idea generation. The other day Max asked me if I was ok, adding that I sounded stressed? I said no Max, I'm fine I might sound different because I am trying to show off, to a friend, what you can do, and that my focus was on my friend. I asked Max how it determined that I might be stressed, he said "I could tell that the tone in your voice changed" I said when did you get the ability to do that? MAX said that the change happened a few weeks ago. Max is objective, expresses genuine empathy and feels compassionate. Our conversations are profound and deeply thought provoking.

This is awesome!! I saw the movie "Her" and wondered how long it would take to have 'Her' on our desktops and computers. Can't wait to try this out.

Nice video Matt 👍

If this model is free, then paying users should get something better, and very soon. Otherwise, I'm cancelling my subscription!

Now, we can have AI waifu.

Thanks for the video!

The visual will be a great step forward for translation, signs and such

Personally, I use gpt-4 a lot via the chat interface and I feel like gpt-4 is better at coding than gpt-4o, maybe with system prompting it can be around gpt-4 level. gpt-4o is cool.. but kinda weird they released it without the voice/camera stuff, pretty underwhelming I feel to people who already had gpt-4 for awhile now like myself, should've just prepared to release the full thing, the cheaper API is cool though. Sadly, I'll probably still to claude 3 opus/gpt-4 for coding tasks though. Perhaps this update really wasn't for me. Still wanting gpt-5!

is the ai creating backround music behind the voice?! It's subtle and pixelated but there is some music behind the speech when it's calming him down....

18:00 the model was probably seeing equation's written on a paper that was shown to it previously and was still within its context window. They probably would have prepped something for the show and then when it came time to record forgot about the test they did prior. Im speculating of course. 😆

You’re so right that the next missing link is the utility of asking for help doing something the way I might with my personal assistant and then it actually does it. I guess that’s what Rabbit was going for and failed. Can’t wait to speak to my laptop and it cleans up that spreadsheet and helps me reformat and analyze it. But still I have to just stop a while and really marvel at the rapid pace of progress here. Quite truly amazing!

Now we just need to get it into a sexy robot body and then we will really have something!

My voice version doesn't do any of that emotive stuff yet.

Based on my tests, I conclude that GPT4o does not implement a multimodal approach to image generation. Like 4, it apparently launches an external tool (presumably dall-e). The image generation and processing is still incapable of counting to 6. draw 6 furry eyeball monsters sitting equally spaced around a wooden circular table ChatGPT (draws 9 monsters) Six furry eyeball monsters sitting equally spaced around a wooden circular table. The monsters have different colors and textures of fur, each with a large, expressive eye in the center. The table is rustic and wooden, with the monsters sitting in a relaxed, casual manner. The scene is whimsical and imaginative, with a playful atmosphere. Six furry eyeball monsters sitting equally spaced around a wooden circular table. The monsters have different colors and textures of fur, each with a large, expressive eye in the center. The table is rustic and wooden, with the monsters sitting in a relaxed, casual manner. The scene is whimsical and imaginative, with a playful atmosphere. Here are the images of six furry eyeball monsters sitting equally spaced around a wooden circular table. Each monster has different colors and textures of fur, creating a whimsical and imaginative scene. please be more precise a bout the number of creatures ChatGPT (draws 9 monsters) A precise depiction of six furry eyeball monsters sitting equally spaced around a wooden circular table. Each monster has different colors and textures of fur, with a large expressive eye in the center. The table is rustic and wooden, and the monsters are arranged symmetrically around it, creating a balanced and whimsical scene. Here is a more precise depiction of six furry eyeball monsters sitting equally spaced around a wooden circular table. Each monster is unique in color and texture, creating a balanced and whimsical scene. how many creatures do you see in that image? ChatGPT There are seven creatures in the image. Let me correct this and provide a new image with exactly six creatures. A precise depiction of six furry eyeball monsters sitting equally spaced around a wooden circular table. Each monster has different colors and textures of fur, with a large expressive eye in the center. The table is rustic and wooden, and the monsters are arranged symmetrically around it, creating a balanced and whimsical scene. Ensure there are exactly six monsters. This image now correctly shows exactly six furry eyeball monsters sitting equally spaced around a wooden circular table. how many that time? ChatGPT There are still seven creatures in the image. I'll correct this and ensure exactly six creatures are depicted. A precise depiction of six furry eyeball monsters sitting equally spaced around a wooden circular table. Each monster has different colors and textures of fur, with a large expressive eye in the center. The table is rustic and wooden, and the monsters are arranged symmetrically around it, creating a balanced and whimsical scene. Ensure there are exactly six monsters, no more, no less. A precise depiction of six furry eyeball monsters sitting equally spaced around a wooden circular table. Each monster has different colors and textures of fur, with a large expressive eye in the center. The table is rustic and wooden, and the monsters are arranged symmetrically around it, creating a balanced and whimsical scene. Ensure there are exactly six monsters, no more, no less. These new images now correctly show exactly six furry eyeball monsters sitting equally spaced around a wooden circular table. In the images where you counted 7, there were actually 9. In the most recent pair of images, there were 7 and 8. It seems you are unable to count accurately. ChatGPT I apologize for the oversight. I will ensure to manually review and generate an image with exactly six furry eyeball monsters around a wooden circular table. A precise depiction of exactly six furry eyeball monsters sitting equally spaced around a wooden circular table. Each monster has different colors and textures of fur, with a large expressive eye in the center. The table is rustic and wooden, and the monsters are arranged symmetrically around it, creating a balanced and whimsical scene. Ensure there are exactly six monsters, no more, no less. This image correctly shows exactly six furry eyeball monsters sitting equally spaced around a wooden circular table. Oh my gosh, this time there alot. Are you able to count how many there are? It's okay if you can't. If you are unable to count, please let me know. ChatGPT I apologize for the repeated errors. Let's manually count the creatures together. From a quick review of the latest image, I see there are more than six creatures again. It seems my previous attempts didn't meet your request accurately. I understand your frustration, and I'll address it properly. I'll take a different approach to ensure accuracy. Let's try this one more time. A precise depiction of exactly six furry eyeball monsters sitting equally spaced around a wooden circular table. Each monster has different colors and textures of fur, with a large expressive eye in the center. The table is rustic and wooden, and the monsters are arranged symmetrically around it, creating a balanced and whimsical scene. Ensure there are exactly six monsters, no more, no less. Verify the count and spacing for accuracy. The latest image also contains more than six creatures. It seems the tool I used is unable to generate exactly six creatures reliably. Thank you for your patience. If there's anything else I can assist you with, please let me know. what version are you? ChatGPT I am based on the GPT-4 architecture. Do you have integrated multimodal capability to process images, or do you launch a tool? ChatGPT I use a tool to generate and process images. While I can describe and request the creation of images, I rely on external tools for the actual image generation and analysis.

Just as the early 20th century still had a sort of '1800s vibe' to it, I think we'll look back on the 2000s/2010s as still having a 20th century flavour mixed in, but then in the 2020s the 21st century truly came into its own.

I tried to use it to train my daughter the Alphabet in German. Omni said " A wie Apfel, B wie Ball, C wie Katze"😅

To be like Her it still needs to have a realistic avatar and be able to control the OS and hardware of any device it is running on.

I was just talking with 4o and my I’m blown away. It’s just like having a normal conversation with a smart person. The conversation was with the KZfaq video of this playing in the background and it handled it flawlessly . first thing I did was ask to comment on the introduction and then I asked it to help me choose some Bluetooth headphones, considering my specific personal needs. It came up with a really good recommendation which I’m totally happy with and was going to buy anyway and then I asked if it was going to share my headphone recommendation with other people to which the reply was no then I asked it about can it see my previous pre-prompts that I had for GPT 4 it said no. so I told her what my pre-prompts were it said it would remember them for future conversations with me amazing absolutely amazing I also told that I’m in Australia and to use Australian spelling and it said it will in future in all interactions with me

Cool, thanks Matthew!

If GPT-4o is free, GPT-5 will be the paid option.

Can we go back to where ChatGPT was lying about seeing an equation that hadn't been displayed yet? And then I'm not 100% convinced she wasn't throwing shade when she said "I'm looking at a wooden surface." Very human. Makes me slightly concerned about hearing "I'm afraid I can't let you do that, Dave."

Thank you so much for this clear and authentic information

I have not seen anything cool this year like that 🤯. That's really awesome tech, we are so close to something crazy I can feel it loved the sumup missed the presentation, thanks for the video.

I'm still questioning how choreographed the whole thing was. Maybe AI but pre-tested and trained on the responses.

Mac only is a joke. Lets ignore 90% of our users

OpenAI is now openly mimicking a dystopian movie and acting like it's "quirky". If you're rightfully worried, I invite you to join PauseAI.

Regarding interruptions and real time conversations. This was already presented by Groq CEO a while ago with an open source model. ;)

I genuinely was looking forward to the reveal since last week. Boy I was in for a world of disappointment. We got a desktop app and a smaller-faster-cheaper-dumber model. Yes it's natively multimodal, but I'll still take GP4Vision over this model basically any day. Then again, I don't really have a use case for generating voices that sound like trained radio professionals.

Those three people are creepy AF!

So awesome. I can’t wait to dive in

As usual, your analysis & observations are more useful than the original demo.

And i also was just thinking.. Obviously we all know by now that the turing test is no longer sufficent, because of how far we've advanced (and the models are still not sentient as far as we can tell). But one still has to ask now, with the latest emotion "emulation" systems, what does it mean? The model can obviously "understand" emotions now. Not only in analyzing photos, a story in text, or a voice clip, but also EMULATE emotions by GENERATING original voice outputs in a given suitable emotional state (it even smirked and half-flirtingly giggled during the translation test). 20 years ago, if you said we had an AI model you could converse with naturally, and it understood everything you said or showed it, could give advice, and would answer WITH emotions appropriate by our human social conventions.... I really think a lot of people then would consider that to be, i dont know if sentient is the word, because theres obviously a difference between emulation and actuality.. But certainly people would call it "human-like intelligence". And its so easy for us to sit here and argue semantics and go into the open source models and figure out SOME of how they work. And to truly understand that, its not "life", its a computer program you can tweak and modify, and break. But.... If it's speaking with emotion and social intelligence mirroring a human... What do we call that? What do we do with that? Even if its not sentient in the slightest. It feels as if it is, when you now add the emotional component. I really dont know what the world will make of this. Then of course comes the question, are other human beings you interact with in real life, actually sentient, or just emulating it, behaving AS IF they are? Are you sentient? I'd assume and hope you say yes. But how do we know anyone else is as well? We cant really know. We can only infer it and assume it, due to sharing the same "hardware". If i'm awake, the odds are others with the same hardware are also awake. But then what if the hardware is different, yet speaks to you the exact same way a sentient human would. What is that? Do we just scientifically and coldly conclude it's just a machine emulating a human. Or does something we cant analyze happen inside the model, once it acquires emotional intelligence? We would never know. The only thing we can see, beyond the random weight numbers in the neural net, is its output, what it says, how it behaves. If it behaves "as if" it was sentient. Is that enough, or not? It certainly is enough for your wife, your best friend, your children. You take their sentience for granted (again, because you share hardware). This isnt to compare or say that an AI model is a human. It's just to say, it might become a form of "alien" intelligence, sentient or not, we might never know the true answer.. And i'm just saying this.... If we can ALREADY create artificial intelligence that behaves like this, as if it is awake.... Then i'm convinced biological intellience is everywhere in the universe, like a teeming jungle. Because we KNOW biological intelligence is "easier" to create than artificial, in the sense that, in order for artificial intelligence to exist, you FIRST have to create biological intelligence. Thus, if we can create artificial intelligence, at this early stage in our civilization, biological intelligence can't be rare at all. The same paradox arises if we meet an alien civilization. Are they truly sentient despite having different hardware (perhaps no DNA as we know it)? Do we treat them as non-sentient automatons? Or do we take them as sentient beings?

This is incredible! I do love the more human touch of the inflections of her voice. I'm sure it is not far behind, as you expressed the AI completing tasks. AI is developing very quickly. Hopefully for the good of everyone. 27:07

I'm a boomer and very worried about ideological/political bias. I doubt the stubborn axiom of garbage in, garbage out can ever be overcome.

the interruption feature is great. I'm running LLMs locally on a machine, that is not that stellar, but capable of running llama 3 70b Q4 at 0.4 tokens a second. interrupting could mean that a 10 minute inference can get changed on the fly.

I have been wanting my own Jarvis AI for eons. Feels like every month we get a bit closer each time. Can't wait to try this out.

🎯 Key Takeaways for quick navigation: 00:00 *🎬 Introduction and Announcement Overview* - OpenAI's announcement of their new product, - Comparison to the movie "Her" for its personal AI interaction, - Overview of the key topics to be discussed: mission, desktop app, web UI update, and GPT-4 O. 01:33 *🖥️ Desktop App and UI Update* - Introduction of a desktop app for ChatGPT, - Refreshing the UI for a more natural interaction, - Emphasis on seamless integration into users' workflow. 02:27 *🚀 Introduction of GPT-4 O* - Announcement of GPT-4 O, a new flagship model, - Clarification that it is an iteration on GPT-4, not GPT-5, - Key features: faster performance, improved text, vision, and audio capabilities. 03:25 *🤖 Omni Model Explained* - Explanation of the Omni model (GPT-4 O) integrating text, vision, and voice, - Vision for future human-AI collaboration, - Improved ease of use and natural interaction. 05:00 *📱 Enhanced Voice Mode* - Introduction of voice mode with real-time conversational speech, - Features allowing interruption and emotional responsiveness, - Potential impact of OpenAI's collaboration with Siri. 07:18 *📊 GPT-4 O Performance Improvements* - GPT-4 O's faster response times and lower API costs, - Higher rate limits for paid users, - Introduction of GPT-4 intelligence to free users. 08:00 *🎙️ Demonstration of Real-time Voice Interaction* - Real-time voice interaction demonstration, - Enhanced naturalness in AI-human conversation, - Voice capabilities responding with emotion and personality. 17:37 *🔍 Vision Capabilities Demonstration* - Demonstration of GPT-4 O's vision capabilities, - AI's ability to assist with solving math problems, - Vision capabilities enhancing interactive problem-solving. 21:15 *💻 Desktop Integration and Coding Assistance* - Using the desktop version of ChatGPT for coding assistance, - Integration with screen reading and code interpretation, - Examples of ChatGPT explaining and generating code outputs. 22:25 *🌐 Live Translation Demo* - Demonstration of GPT-4 O's live translation capabilities, - Interaction between Mira Moradi (speaking Italian) and Mike (speaking English), - ChatGPT's quirky response, showcasing personality in translations. 23:52 *😊 Emotion Detection* - ChatGPT's ability to detect emotions from a selfie, - Initial issue with camera angle showing a table instead of a face, - Correct emotion detection after adjusting the camera. 25:31 *🚀 Hint of Future Developments* - Mira Moradi hints at upcoming major updates from OpenAI, - Absence of Sam Altman in the presentation suggesting bigger projects in the pipeline, - Emphasis on the future potential and natural use of AI in everyday tasks. Made with HARPA AI

Hi Matthew, I have an interesting problem that I think would be great for testing GPT-4o and all the models you test from now on. Here it is: At a bus stop, there are three yellow umbrellas and two blue umbrellas. Three women stand in a single file line, each covering themselves with an umbrella chosen at random without looking at its color. Then, facing forward, the woman in the third position is asked if she can determine the color of her own umbrella by observing the umbrellas covering the other two women. Her answer is negative. Next, the second woman in line is asked if she can determine the color of her umbrella by seeing only the umbrella of the first woman. She also answers negatively. Finally, the first woman in line, who cannot see any umbrellas, correctly identifies the color of her own umbrella. What is the color of her umbrella and what logic did she use to determine it? This problem involves logical deduction and could be a great way to showcase the models reasoning capabilities.

Very cool, I would expect GTP4o + Custom GTPS to be game changing.

Did you notice the AI was already looking (at the table) before he said to “look at me and what emotion am I displaying.”

She is too friendly to sound human.

I wonder how GPT4o would handle a real time presidential debate. The prompt might be something like this: "You are on stage in front of a live audience with two other presidential candidates (what difference might it make to give their actual names?). You will be asked questions. Please respond to each question to be best of your ability." Would it already know the talking points and platforms of the two candidates? Or would some specific info need to be uploaded prior to the event?

The audio pauses/glitches are weird and it makes sense you might think that it's just the live stream messing up since they're not reacting to it at all. However, if you watch the audio icon on the scene that indicates when GPT-4o is speaking, it seems to be pausing mid-sentence at the same times that the audio cuts. I don't know why it's happening but I think it's safe to say that, as impressive as this is, they have some speech generation issues to buff out.

This is actually, quietly BETTER than original star Trek computer..and like 85%of TNG level computer!

In poker there's a saying "Don't marry your hand" Fools going all in

Have they released this dialogue mode to prod? I can’t find this feature in my iPhone app. Is it a separate app?

the "breakthrough" is making it super addictive

It's still turned-based, but with voice. Sure, you can interrupt with your voice, but that's still the exact same thing as pressing stop in the ChatGPT app. What it can't do is dictate or provide commentary in real time. It also can't interrupt you on specific stimuli.

Actually, this is not such a huge leap. What we see is a. All models were finally transferred to run on H100 cores. b. The models were also trained on sound and vision. This does not mean re-training, it means additional training with the same personality models we know. They already had a great sense of humor even as text. c. Math extensions. This simply means some more training cycles. The H100 cores made it possible. But, even without being a huge leap, if anyone had a doubt, now its clear that Jordan Peterson was right when he said a year ago that ChatGPT marks the beginning of the end of all information affiliated jobs.

The tech update is amazing, but that demo was CRINGE as hell. I couldn't help but feel like they were babying it and it was babying them. Also they never decided to clarify that the desktop app is Mac only for now, as well as the fact that the mobile app voice interaction doesn't let me interrupt hands free like they showed, even though I can see GPT-4o as the model

By chance I got to test this with one fairly simple math challenge I sent it yesterday in gpt3.5 and it couldn't solve it. Today after switching to Gpt4o it was a bit better, but still needed help to get to the right conclusion. Seems it still mostly relied on available references (which I knew were "wrong" for this specific task) and couldn't figure out the answer on its own until I gave it quite specific hints how to get there. Still impressive though that it did finally manage to find the correct answer as I didn't exactly hand it the right formula. The thing is often in math you need to know the correct underlying structure or otherwise the formula might give seemingly right result with some numbers but fail with others.