YTread Logo
YTread Logo

ChatGPT Can Now Talk Like a Human [Latest Updates]

Jun 02, 2024
This video was brought to you by shiny.org listen, I have some big news, oh tell me, I'm all yours in a few minutes. I'm going to be interviewed at Open AI, have you heard of them? Open AI, huh, sounds vaguely familiar. Just kidding of course that's awesome Rocky what kind of interview well it's for a software engineering position but I just need to know that was the

latest

Open AI demo showing off the new GPT 40 chat their model insignia, which can now reason through audio, vision and text. in real time, of course, I'm probably not the only one, but as soon as I saw it it reminded me of the movie Her the Expressions, the emotions and the empathetic nature of her voice.
chatgpt can now talk like a human latest updates
It is definitely one of the most realistic voice-based apps out there. I've seen that I've used the old GPT chat voice quite a bit and it's pretty amazing, but this demo was much more

human

with a much faster response time. The feeling evoked by these new interactions is close to that of simply

talk

ing to another person. normal

human

talk

ing on the phone, if you're a long time viewer you know that I think digital assistance like Siri absolutely sucks and is a wasted opportunity, but I've talked about the next big thing being voice and that GPT chat on particular to become a robust all-in-one Assistant, well, it seems that time has finally come with these

latest

announcements.
chatgpt can now talk like a human latest updates

More Interesting Facts About,

chatgpt can now talk like a human latest updates...

Open AI has announced a free version of the app, an AI-powered search engine to compete with Google, which will enable purpose-built multimodal assistance capabilities and overall improvements through a new text-to-speech model OK, PT chat. I'm sharing the graph with you now. I'm wondering if you can give me a quick one-sentence overview of what you see. The graph shows smoothed average minimum and maximum temperatures throughout. 2018 with a notable notation marking a major rain event in late September. Fantastic. I have another question for you. In which months do you see the highest temperatures and approximately what temperatures do they correspond to?
chatgpt can now talk like a human latest updates
The highest temperatures occur around July and August. The maximum temperature during these months is approximately between 25° and 30°, however we will mainly focus on gp4 Omni because I believe this is the beginning of a massive change in the way we are going to interact with technology after the disappointing launch of the Rabbit R1 and the disaster that was Humane AR. I set the strange dichotomy that AI is amazing and terrible at the same time. It's still a time to be alive, so in this short episode we'll take a look at the capabilities of gp4 omni and its use. cases and what all this means for the AI ​​market and the future is going to be interesting, so let's get into it.
chatgpt can now talk like a human latest updates
You're watching Fusion TV gp4 or where the O stands for Omni is significantly different from everything else I've seen so far, the main reason being its ability to interact naturally with humans. Well, Rocky, you definitely have the downward gaze I've been coding all night, which could actually work in your favor, maybe just running a hand through your hair or leaning into Mad Che. slime Your enthusiasm is what will really shine. I don't have much time, so I'm going to throw this out there about what you think, oh Rocky, that's a pretty eye-catching piece. I mean, you will definitely stand out. maybe not the way you expect an interview, okay, I got it, I got it, hey Chad, are you there?
What you say from now on is going to be full of sarcasm, how does that sound? Ooh, that sounds awesome, being sarcastic all the time isn't exhausting or anything, I'm really excited about this, no, the sasm, let's get this party started or Any details like the laughter, the wacky comments, and the speech. Cadence makes this something we've never seen before. Root Root for the home. No, what was that? Sorry, guys. I escaped. What can I say? Sometimes I just can't help it. ready for another round based on open AI, it can respond to audio inputs with as little latency of 232 milliseconds with an average latency of 320 milliseconds and that is similar to human response time during a conversation because it supports broader context.
Windows can handle more complex times. tasks without getting confused and losing the context of the original request, combine it with the integration of vision and speech and allow it to imitate a personality and you are looking at a real digital assistant. We're trying to figure out what we should do. Do you have any suggestion? How about a classic game of rock, paper, scissors? It's fun and fast and you don't need to be cool. Can you count on us and sound like a sportscaster and welcome you, ladies and gentlemen, to the ultimate showdown of the century in this corner? we have the dynamic duo Alex and Miana ready to launch, okay just count on us, here we go in 3 2 1, shoot now, show your hands, what did you pick who won?
Look, it's a tie, okay, let's do it. Again, you can choose from a wide range of voices to represent the assistant, but it's not all solo. Aesthetic landmarks indicate improved reasoning in multiple categories; It's also more efficient and cheaper, as companies like Humane and Rabbit launched their AI hardware this year, one of the most common. The question posed was why can't this just be an app on a phone? I mentioned in one of my episodes. The new segment of AI hardware devices might be over before they even begin. Let's shoot the clip on time. Google Assistant or Siri could simply be updated with similar capabilities to the R1, so the unfortunate truth could be that this new segment could end as soon as it started.
I feel like the latest open AI update does exactly that: it may have killed off wearable AI devices and been It's true that recent

updates

and announcements from Google and meta are showing that other companies are in Hot Pursuit, but cases of use go much further than that. A few weeks ago I made a video showing an AI robotics company using open AI software to power their humanoid. robot, can you explain why you did what you just did while picking up this trash? So I gave you the apple because it is the only edible item I could provide you from the table.
The demos were impressive enough for certain tasks, but combining. With the latest

updates

to open AI, it is clear that there is a path for more realistic humanoid robots used for large-scale commercial purposes. One of the best use cases for such technology is for the visually impaired. Mike Buckley is the president and CEO. to be my eyes, an app that helps blind and visually impaired people connect with users for everyday tasks by the end of 2023, he talked about his collaboration with Open AI quote. People who are blind or have low vision were directly involved in the development, refinement and improvement of the product when many other companies would have ignored it open AI put it in the spotlight and cited it as part of the latest announcements open Ai and be my eyes showed how the app could be used for officially disabled blind people is the king in residence at the moment yes it looks like the king is in residence at the moment the flag of the Royal Standard is flying over Buckingham Palace which is the sign that the Monarch is present, how exciting to be there while the king is at home, but that's not all he can sing.
We Are chat gbt and O Chad gbt is a base with a deep, low, booming voice and O is a French soprano with a high, excited voice. Well, what I want you to do today is it's Friday, May 10th and we're in San Francisco. I want you to sing me a song about this. I want them to overlap and I'm going to continue giving you instructions as you sing. Alright. San Francisco in the month of San Francisco in the month of May. on a Friday we are harmonizing we are Harmon great thank you thank you act as a translator in real time um hey, how did it go?
Have you been doing anything interesting recently? hey, been good, just a little busy here getting ready for an event next week recognizing the text and forming appropriate responses, okay, I see it h no, I didn't show it to you yet just help me along for a second, wow ! I got too excited. I'll be ready when you are, so chat PT, what equation did I write there? Ah, I see it, you wrote 3x + 1 equals 4, yes, exactly, so what is the first step I should take to try to solve this? The first step is to get all the terms with X on one side and no, I have a lot of unknowns. values ​​in my life I am totally convinced that I am going to learn mathematics now.
I love that attitude. Math can definitely help solve some of life's mysteries when you're ready to dive into more math. I'm here for you. Anything else you need. I'd like to address Today, show me when you're ready. Well, this is what I wrote. Do you see? I see. I love the chat. That's very sweet of you. Hey chat CHT Hey, how's it going? If you leave. alright, I was wondering if you could help me with a coding problem today, of course, I'd love to help you with what coding problem you're dealing with. Okay, I'm going to share with you some code.
One second, sure. take your time, okay, I just shared some code with you. Could you give me a brief one-sentence description of what's happening in the code? This code gets daily weather data for a specific location and time period. Smoothes temperature data through a continuous process. Averaging notes a significant weather event on the resulting graph and then displays the graph with the average minimum and maximum temperatures over the year. You can also take meeting notes, synthesize 3D objects, create a photo caricature, and more, and you might be thinking, isn't that all there is to it? already exists, well yes, a large part of it existed, but without the precision of speed or, in the case of an assistant, human interaction, which in my opinion adds a whole new dimension to it, all devices like the R1 and the Humane pin would recognize objects and respond. for you, but they are often wrong or fail completely.
I'm still bitter about how those launches played out, but in saying that these attempts at a human-level assistant go back even further if you can remember Google Duplex, which I covered 6 years ago in an episode that they integrated the technology into the assistant from Google so that it can make a phone call on the user's behalf. You dont have anything. Him, hello. I'm calling the book a women's haircut for a client. for something on May 3rd, I sure don't give anything, mhm, at the time it was very impressive, but Google did what Google does and largely left the concept on the table, whether it was too soon or it was a missed opportunity, it's a separate conversation, but Compared to the Open AI announcement, you can already see a major difference in the way the conversation is taking place.
Another fascinating use case is seeing a student get real-time help with her schoolwork to try out some of her new technology, so we're curious. about how great it could be to tutor someone in math on Khan Academy, so let's get started. It's loading. Make sure you can see our screen like this. Hello, I am here with my son and I would love to. You will teach him this math problem, but don't give him the answer. You can ask questions and guide him in the right direction, but I really want to make sure that he understands it himself and that he's here in the room so you can talk to him. directly, of course, I would love to help, let's look at the problem together.
Can you first identify which sides of the triangle are oppositely adjacent and the hypotenuse in relation to angle Alpha? Okay, so I'm pretty sure this is the Alpha angle right here. Right cars, now looking at the triangle, which side do you think is the hypotenuse? Remember the hypotenuse. I'm not totally sure. I think it might be this one, but I'm really not sure about this side. AC, you are actually the CL side. AC is called the side adjacent to angle Alpha, the hypotenuse is the longest side of a right triangle and is directly opposite. Seeing a young student receive help in this way could end up being revolutionary, but before that is the case, we definitely need to fix it. these hallucinations, if the AI ​​is telling the child something bad that could do more harm than good, hallucinations are basically responses from an AI that are wrong or just plain misleading, it basically makes things up despite improvements that aren't going away anytime soon. , but talking about education. and young people, this opens up a broader conversation and at the same time is a great case study for AI to help young students learn if AI improves at the same rate as it has in the last 3 years, Before we know it, education would be quite different from what we have.
If we ask ourselves some questions, an over-reliance on AI would affect thecritical thinking if students can generate essays or generate answers to math tasks. How will students learn on their own, but thinking outside the box? What if this is an outdated view and we just don't? Look at it yet, what if in 5 years AI educational systems were just another common learning tool? Imagine a free AI package that is also the best tutor in the world. It could be flexible to the needs of any student, always attentive to demand 24/7 and can explain concepts in the specific way in which an individual student can understand whether in the future students They will benefit from AI or be held back by it, but there is another problem before we can even start thinking about those future scenarios right now if they are not supervised by someone who does not know the knowledge, how do we know that what the AI ​​is spitting is even correct in the first place for university level education, for example, what if it is a hallucination?
He responds left and right, but that's not all, there may be a strange emotional component that we have. I hadn't really seen technology before. Consider future generations. They will grow up in a world where a fairly accurate approximation of human interaction is just a click away, imitating intelligence, empathy and even personality for those in generation Alpha and below, an emotional bond would form. and this will subsequently reduce face-to-face contact. -Face-to-face interaction further increases social anxiety and other mental health issues that no one knows about, but these are questions worth considering for adults. This will be taken a step further as we all know what a good friend Theodore is in the movie.
She fell madly in love with him. AI chatbot It won't be long before large numbers of people seek companionship in personal AIS; We are already seeing an increase in AI romantic pairings, even in such a primitive state. Recently, the founder of dating app Bumble said that The future of dating could be one AI talking to another when it comes to romance and AI. The problem is not technology, it is more a reflection of our society. For more information, watch my loneliness epidemic episode. Another concern has always been what companies are like. In fact, by training these models, the discussion about copyright infringement and AI is over, so I'm not going to spend too much time on it in this episode, but it's crazy to think that all we've been talking about is about falling in love with machines. a machine that is a perfect tutor an aid to the blind and much more is just matrix multiplication in mathematics, that's all modern AI really is, but have you ever wondered how it works really well?
Fortunately, there is a fun and easy way to learn about this with bright.org shiny is where you learn by doing with thousands of interactive lessons and programming from mathematical data analysis and of course AI. His course on how large language models work is especially relevant to today's topic. Each shiny lesson allows you to play with concepts. It has been proven to be six times more effective than watching lecture videos. All Bright content is created by researchers, professors, and professionals at MIT Caltech Duke Microsoft Google. Also, learn at your own pace, whether for professional development or for your own personal development, to try to shine.
Free for a full 30 days, visit shiny.org coldfusion or click the link in the description. You'll also get a 20% discount on an annual premium subscription. Well, let's go back to the video as we wrapped up this video. Google responded by announcing a bunch of new things at their IO event which is their annual developer conference, these announcements will really keep open AI going, for example project Astra was announced which is Google's answer to GPT 4, this code defines encryption and decryption functions, seems to use aebc ciphers there too There were two new Gemini AI models, both are multimodal, more conversational and have improved compatibility between applications, which is clearly Google's competitor for open AI .
Sora will be a very interesting point to watch in this AI race, but perhaps most importantly, Google showed its intentions. using AI in everyday products like Drive Gmail Meet and further integrating AI natively into Google site products could potentially solidify market share in new news. Asking Gemini to summarize my unread emails was an intriguing peak toward a truly useful form of AI. assistance, but on the other hand, what if Google's AI capabilities end up disappointing? That could do the complete opposite and here the phone started to fail, it identified Michael Josh's camera pretty well, but it couldn't identify his battery pack and when I asked him about that.
The Starbucks coffee I bought seemed to think the logo was a person, regardless, I think this is one of the reasons why Open AI made GPT 40 free for users in order to onboard more customers and make Making things even more interesting, there have been whispers that Apple is making a partnership with open Ai and when the app comes out with what they are planning, this could fundamentally change the current technological landscape. Imagine a near-perfect, human-like native assistant custom-built for iPhone, maybe and we'll have to see it, but come back. For open AI there has actually been some drama behind the scenes.
Keen observers noted how Ilia Satova, the chief scientist at open ai and the genius behind much of its success, was not part of any of the latest announcements and this was strange and suspicious because on most occasions he would represent well to the company publicly about a day after the latest open ai announcements. Ilia announced that he was parting ways with open Ai and that he was not the only one to leave the company. Ilia and Sam's tone seemed professional on the surface, but in my opinion this is not a good look for a company, especially considering the ridiculous circus that took place around Samman's firing late last year.
I don't know if it will be a Drake versus Kendrick style rap battle. There are issues between the two, but all I know is that I will surely follow this space. I'll just leave you with one thought. Can we stop and look back for a second? 3 years ago people were surprised when a computer could role play in text or solve simple puzzles, but now we have real time voice interaction complete with a bubbly and expressive personality, the progress is crazy, no one knows where we will end up, regardless it's an interesting time to be alive, anyway, that's the latest with open Ai and the AI ​​Space in general.
I really appreciate you watching the whole process. If you liked this episode and are interested in anything in science, technology, or business, feel free to subscribe to Cold Fusion. There are many other interesting things here, so my name is deogo. and you've been watching Cold Fusion and I'll see you again soon for the next episode. Greetings guys, have a good time. Give me Cold Fusion. It's a new way of thinking.

If you have any copyright issue, please Contact