how long have i been waiting for you, i love you so much, holding my breath, with you i’m flying to the ends of the earth, i love you so much, breathless! but i’m flying with you to the ends of the earth, i love you so much, you are my soul, you are the ocean of my people, i love you so much, breath of my behind, i’m flying with you to the ends of the earth. i

love you so much, i love you, now my soul, you are the ocean of my love, this is the blue light of an ultraviolet lamp for gel manicure, what we should know about nails, what we should know about such unusual gloves, the whole truth about nails and not only. a lot of different, interesting things important for your health, live healthy in the program, tomorrow on the first. arkhist for tourists, as a rule, starts from here, mountains, rivers, views, lambs, guys from the concrete jungle usually come to us, they never have any mountains or small forests on the horizon, they are simply shocked, at the same time a record for the arkhist resort for today day... 11,800 people per day,

per day, movements are light, feminine, like a swan, and as sharp and clear as an eagle. my mother sent me to dance as a child, but i always wanted to fight, i need to motivate rooms to make the reception easier. it seems to me that this is how boys and girls in the seventh grade dance at discos. let's go, the premiere is on saturday, on the first. valerie is with you. syutkin, radion gazmanov, today we are hosting together the podcast melodies of my life, which is dedicated to those artists who shone their voices in the project, and it is with great pleasure that i invite you to admire our charming guest, raisa dmitrenko, you generally enjoyed taking part in all this, not too much , it’s nerve-wracking, i wouldn’t like it, to be honest, to be honest, i took a long time was going to. i didn’t want to, but i had one

crazy friend who kept pushing me, saying: you should be there, you should be there, they tried to persuade me for 2 years, i went, i thought, okay, i’ll remind you of myself, otherwise don’t be afraid, they forgot , but i had great pleasure, because all your numbers, in addition to the brilliant vocals, were also very artistically solved, beautiful, you as an actress were simply beyond competition, after your ... not as often as we would like, but basically, well, i managed to go somewhere with concerts, say, tagan-rock, yes, tell me, how else did your voice influence your life? they began to recognize you on the streets, neighbors came up for autographs, i don’t know, these kinds of things happened, oh, neighbors and housemates all recognized them, yes, yes, we found out at the store.

that ones of my heart so well okay so take all of me!

bravo, after all, what an amazing thing this is and an expressive human voice, this is fantastic, thank you very much, let's go. which turned us all like a hurricane just right from the first note, it’s some kind of unimaginable mix, elo fitzgerald and faina ranevskaya, you see, there was so much self-irony there, i felt it with my back, it’s a great feeling, today i want to ask you

to sing something for us, yes, it will probably be a romance based on gumilyov’s poems, i just can’t cope with the composer , i know him by nickname, with great pleasure in today’s podcast of the melody of my life, which we dedicated to the project, the voice for you is sung by raisa dmitrenko. my monotonous days flash by with the same will and only the roses fall and die. solovin,

but she is sad too, who ordered love to me, and under her satin skin, and under her satin. through the skin, corrected blood flows, poisoned blood flows.

it was amazing, rais, tell me what song, you said, this will be raisa dmitrenko’s signature song, which one would you choose from the entire world heritage, so to speak, or even in english, i dreamed of singing one piece from gin’s repertoire vanelli, wow, yes, yes, it's called fly into this night, it's. i’ll spark you directly, because i want to tell you, in the mid-seventies of the last century, here are two names, benson and vaneli, all the musicians were raving and so to speak, there was a different arrangement,

funkier, jazz-funk, another, another performer did this thing, i fell in love with it, and there i had the opportunity to demonstrate everything in all four octaves. we’ll take our russian-language repertoire, here ’s the russian-language repertoire, you know, at one time i was in love with anatoly dneprov, by the way, the bravo group was also one of my favorites, i sang your repertoire in my youth, this is the most favorite song of the bravo group, well orange tie, raisa dmitrenko is a person with good taste, to be sure. thank you for taking the time, please sing, you are wonderful at this activity. thank you, thank you, very much. this year zhanna frisky would have turned 50. she was called the standard of female beauty. both those

older and those younger fell in love with her. the star achieved everything she wanted and could cope with any problem. she could not overcome one thing: an illness that turned out to be incurable. and i never left her side... how did i even sleep next to her? how is she did you perceive changes in appearance? very painful, we covered the mirrors, hid only in the darkness, she hated the light, she hoped, fought, but... exclusive with dmitry borisov premiere. on saturday on the first. the podcast melodies

of my life is on air. today i, valery syutkin, am hosting it together with radion gazmanov. well, experience and skill, remember, they used to say that, give way to youth, for a fool, i even said, to beauty. yes, today our guests are two charming girls, they started their journey in the voice project. children, and then secured success in the project the voice is no longer children, it’s our beauties, ragda khanieva, hello, and elizaveta kochurak, hello, i was relieved by the thought that we now have a generation of performers who can potentially take part in all seasons, in all different versions project voice, no, 60 plus is too early there, no, not yet, now of course yes, 60 plus, and then maybe someone else will become a mentor? i think it’s very difficult, especially at the stage

of fights, when you have to make a choice. let us remember together how it was in in your case, let’s relive these minutes again. yes, pay attention to the screen. even though it's hard to leave. there is depth above you, a bright light ahead, suddenly you hear voices, be patient a little longer. the path, we will show you,

yes, pilagea was more worried, she was just, yes, very, very worried. where is the incomparable day love in the day i was afraid in the nasty beautiful country any lisa ragda that's why these songs? which i performed in the final voice for the children, it was a joint choice with my mentor, pilagea at that time, and

since the song is very deep, she quite significant for me, because i was immediately imbued with it, the lyrics, the melody, the energy of this song all came together, everything responded to me, they sparkled now, i remembered that moment of the finale, i will never forget these emotions, they are probably the brightest. for lis, tell me how it felt for you? but emotionally - it was just magical, i guess, when the children in that younger age heard their voices, they, they are no longer children, uh, in some ways it was even simpler, right? well, to some extent, yes, it’s simpler, because you don’t misunderstand some points a little, it’s like the second parachute jump is scarier, that’s exactly what i wanted to say. it’s always scary, yes, the second time everything was conscious, and it was my decision, right

from beginning to end, that well, i want to try this again, the first time my parents said, let’s go, no, no, no , this has always been , well, we always discuss all the moments connected with everything there, i also consulted the children out loud with their parents, they helped me and always help, but out loud... they are no longer children, they kind of asked me like this oh you do you want, do you want to experience again this this this this, yes, this, i don’t even know how you need this, how how this? to call in one word the spectrum of some emotions, sensations very different and joyful and sad, well, we will continue the profession, i hope the profession continues successfully, of course, the girls sing all the time, i’m happy to constantly see in different projects we go out on stage alone, i present it to the stage with pride because in addition i also know the voices

from a bunch of projects where we also sang together , so it’s incredibly pleasant for me the question is the same. an exciting moment in the project, remember your ragda, tell me, this is where it’s just, this is where it was scary, but i can’t, where is the spectrum of all emotions, this is most likely the finale, the finale, yes, i was very worried about the finale for the children, and for i was very worried about the song’s path, because i was 12 years old at that time, the song was serious, the song was quite deep, and i had to complete a number of whole tasks not with... the voices of no longer children, since i already have quite a lot of experience in participating found, many are familiar with mine creativity, with the way i sing, and i had to prove again whether i deserved to stand on this stage or not, and it was

very stressful, a very season, success raises the bar, this is important, yes, your moment of fear, tell me, but i had them. the children are a little loud, this is probably the finale, because i sang my mother’s song, it was called a prayer, sung by lyudmila gurchenko, and i was 13 years old when they gave me this song, well , for several days i just cried, because i didn’t know, how can i convey this, how how i can do this... it will work out, but i really love soviet cinema, to some extent it helped me, because i somehow let each film pass through me, and i take something from each hero for myself, before performing after praying, i finally collected this

image, collected all these feelings, sensations, and i think it worked. a little different, i had a different look, but it still worked out, the second point, yes, i agree with ragda, these are blind auditions, but not children anymore, you were all stressed there, everyone was stressed, because it’s not clear, we we went through the same procedure, that is , casting, blind auditions, then everything is as it was in the projects before, and how to turn to us, not to turn back, i still don’t want to somehow. lose face, i remember this moment, when we had this waiting room, our fourth season, i dug up this bubble tape somewhere, a large skein, no one thought about it then, i’m right there such a roll, so i go out and i just handed out these things to everyone who participated with me, they say it’s anti-stress, and in the end they come in the editor invites someone and starts laughing, because we all sit and click this

thing, it was very funny, this is the song that made you fall in love with this... with my grandmother i loved to sing cossack songs in two voices, he and i sang there and started and somehow from this i think that i got a small piece of what this is, let’s do it, my beloved, i always sang it with my grandmother, the kingdom of heaven, she sang the second voice and i was the first in the garden to pick

roses. alladzelin a real cossack song, and but good taste, i never tire of repeating this, this is a reflection of the traditions of our native culture, in the end. of our podcast today, i, as the host, will be pleased to invite you to perform a song that we wish everyone who participates will participate in

the project voice 7.0 happy moments every day, let them be exciting, well , music is the language of feelings, so it’s great that we we experienced it, it’s great that future participants and mentors have ahead... there will be so many exciting moments, let them be a lot, dear friends, today in the podcast melodies of my life, together with radion gazmanov, raisa dmitrenko, sergei volchkov, elizaveta ragda and anastasia spiredonova, which is also important, we lived together, i’m not afraid of this word, again moments of excitement, inspiration of happiness, when we... the voice project united us all together, let this voice last as long as our dear tv viewers want, that is, forever, so today

we wish 7.0 happy moments together with this work, above the ground, goldurbin snatches of sleep. outside the window lies in white clouds landscape at night, the moon flies above it, secret movement, endlessly in the sky, i see the reflection of your face, you are far from me, the delay of another day, but even time cannot stop me, the flight. the ocean, and having dispersed the winged fog, the danger of the night skies, rather than you!

dear friends, this is the podcast melodies of my life, we hosted it today together with radion gazmanov, but i am happy to leave you alone with elizaveta and ragda, with our...

i am not there, where your footprints have not been traced in the sand, where white bird in a bag, where is the bird white in anguish, destroying... don’t stop, but you, i’m only there, where the sound trembles, the desired pier, and where your guardian eyes, and where your guardian eyes, glide over not intently.

i am not there where you are. the white day will not cloud the white day, where the pines are from amber tears, where the pines from amber tears are wiped away by caring olya, i am only where you sometimes look at the door with hope, and like a child with children and like a child with children, you sculpt snowy woman, i’m not there. where the night steamboat

boomed abruptly, where the sky understands the vault, where the sky understands that without you astirote, i am only there where i am not, around you, invisible. you know, not a day without you, you know, not a day without you, it’s impossible to live, don’t you see,

dear friends, the creative industry podcast is on the air, there are still living, real copies of the presenters with you, this is still elena kiper, producer and video director , but i won’t touch it yet, we need to make sure, roman karmanov, general director of the presidential fund for cultural initiatives, is our guest, denis dimitroev, our guest today, managing director by research.

let's figure out what kind of thing this is, in fact, artificial intelligence, there is absolutely no need to be afraid of it, since we started with this, it is a tool that helps us do different things, that is, it automates some part of our intellectual work, in basically the routine part, artificial intelligence - this actually usually means some kind of neural network, what is a neural network, a neural network is some kind of you know, you can imagine it as a black box that takes something as input and something gives to... the output is exactly how we imagine it, that inside the black box, this is some kind of mathematical function, a function that now, for example, lies behind, for example, generating a picture from text, has, well, there are billions of parameters, so they are like this complex ones, which a simple person who is now sitting in front of our digital, still digital tv, must pass, about artificial intelligence, within the framework of such an everyday understanding of artificial intelligence, it is artificial.

intelligence is such a black box, you can so imagine that everyone just imagined now a black box, what to do with it, which learns to make some decisions, these decisions can be a huge number of problems, in fact, which it solves, that is, you take a certain amount of data, well, let’s say , a certain amount of knowledge, well, relatively speaking, you take all the volumes of leo tolstoy, load them into this black box, and it can give you, well, relatively speaking, another volume of leo tolstoy, for example, well, in a sense... yes, that is, this function here, it learns in this way, that is, the parameters are configured in this way, these billions, based on, as it were, so that it is configured, what does this mean, this means that this is it, that is, a learning process occurs, if we are talking about language models, such as, for example, well, everyone the well-known chat gpt, gigachat, for example, this is a function that takes a set of words as input

, tries to predict the next one, and so... the network, i mean, of course it can do various very, very cool things in my opinion, that is, it can process and, for example, make some objects in the style some artist, here you can argue whether this is creativity or not, yes, these debates are already going on, quite fierce, but it’s like the very fact that it can be done beautifully, especially lately, this is an indisputable fact in my opinion, but in fact, i can say this: indeed, the field of artificial

intelligence is now being democratized. such a term, maybe it’s a little complicated, but i’ll try to explain what this means, that people can now study artificial intelligence starting from school, say, from the ninth grade. when someone from the seventh there, in general, they study at a good level, which was impossible to imagine there even 10 years ago, that is , the level of mathematics is really there, the level of interest of schoolchildren, sometimes even the quality of training programs, which are actually done on artificial intelligence, they they allow you to get into this science, and this is really science, it is difficult, this is mathematics, this is the intersection of mathematics and the actual calculations of machine learning, you can enter it already in the seventh grade. and we spend there a huge number of competitions, hocothons, and we see that children in general cope with complex tasks no worse than people who graduated from college, and what they do, that’s what they do, well, actually the task, the task of a person who

deals with artificial intelligence, let’s say neural networks , although in fact there are a huge variety of algorithms and types of algorithms, these are not only neural networks, they are simply very flexible and therefore they allow you to solve a huge number of problems, including even creative ones, that is, the task a person who wants to create an artificial intelligence model or artificial intelligence in how to select an algorithm that suits the task, although recently there are universal algorithms that solve a huge number of problems, and how to train it, what is most important, i you know what is amazing i discovered for myself that a creative person, if he has some images in his head, has ideas, fantasies, and so on, he needs to... now it turns out that with the help of artificial intelligence you refute this or or confirm this, that is, you can transfer these images from your head,

so to speak, into the world network, yeah, it will create a picture for you that will generally transfer the picture from your head, in general, to the computer, this is true, like would be possible. of course, yes, and the universe that draws pictures, for example, can accept text as input, that is, you can write something in text, but the text must be artistic, it must include all the images, you need to understand actually in detail, what do you want, this, this makes the work of the neural network much easier, because it’s easier for it when you described in detail what you want, it’s easier for it to draw it, when you wrote i just want a fish in space, for example,

i came up with it myself, and we, we sort of thought about how to animate it , or something, let’s say, to make her more recognizable, and we decided, at that moment 3 years ago, she was creating abstract objects, and we kind of thought, what kind of

russian artists are there who painted in the style of abstract art, the first, the first model was called mali, the smallest, of course, then we made large versions of the models, like this...

architecture, we even have a set of articles where we talked about this architecture, in general this model is known, well, in fact, all over the world, in, say, the scientific community, in community. people who use it, we are in some sense limited in that, but the model, this is the first reason, to move progress, the second reason is that if we just use other people’s neural networks, what kind of content, how can we influence the creation of content, actually what we are in the model we put into the model, if it is not ours, what we could put in if it were ours, roughly speaking, well, you know, yes, that the model learns from data, and we can, for example, make a model which is better. generate russian objects, russian entities. it is clear that western networks,

neural networks, they certainly saw, there is the kremlin, and some iconic russian objects, and a character, it is still unknown what kind of kremlin, well, that is, what kind of kremlin will be there exactly, yes, that is, they they don’t specifically set the task to make it generate a model, their task is simply to generate everything in general, but we can set the task to and, as it were, show the models a lot of our data of such a domestic cultural code, and this is not only the domestic cultural code...

he essentially said that the next president will be trump, and he influenced the speaker, that is, this is interference in internal affairs, he is convinced that putin wants part of the north of kazakhstan, you told them that putin wants to seize their state, which means they are scared, yes. humanly sets up both trump and the minister of foreign affairs of kazakhstan, this will not be forgiven him, from now on cameron can be considered a political dwarf. premiere, show of vavan and lexus. on wednesday, on the first. we continue the creative industry podcast. our guest today is denis dimitrov, and the man who created the kandinsky neural network. and with you. still elena kiper and roman karmanov, and what successes are recognized for

kandinsky is already this, what he does better than his analogues, let’s say, the analogues are wrong according to his word, well, it looks like it means on neural networks that solve the same problem, generating images from text, for example, what we are cooler in, although kandinsky videos are generated now, yeah, now, well, that is, it’s already, as it were, we’ve just recently presented a model that generates video, called kandinsky video. although we probably should have called it something torkovsky, well, they called kandinsky video, we will continue this line, but what does it better, knows the domestic cultural code better, of course, this is what we actually set before the model, which task, and we will certainly develop this further, what is the problem with russian data , knowledge of the russian domain, is that russian data, of course there is less of it, what the model learns from, learns from data from the internet, that is, from open pairs of image descriptions ,

it seems to capture the data at the time of the request, no, naturally, there is a team that deals with the data, and that is, the data is already contained in it, it is not searching on the internet at this moment, no, no, in no case, it is creates, in this way unique they are stored, this voluminous quantity is a huge amount of data, kandinsky the third studied on one and a half billion pairs picture text and you can imagine how much storage is needed there, well , there is a supercomputer, it’s like learning all this on a supercomputer and storing it nearby in special storage facilities, they are called s3, but these are these big, big data warehouses that really, say , for the dataset model to be able to see, they need to be put there, and not just put, you need to remove everything low-quality pairs, that is, filter out. well, if you go to the internet, then in general

half of the data there will probably not be of very good quality, all the rubbish there, just like that, the picture does not correspond to the description that is written there below, or it may be that the picture contains a watermark, uh-huh, it’s probably also bad to use such data, because the neural network will reproduce this voturka, it would now say that the artists are already fighting, that is, they spoil their image, so that it won’t be too, that’s it that's also true, yeah. this also needs to be dealt with, that is, there are a huge number of filters that need to be written before giving the data to the model, because of course you can’t give everything in a row, it’s like you know, showing a child: everything in a row, it’s not clear what he will learn in the end, the data development team is, of course, responsible for this, and this is a super important activity and the team itself, because not only half, but more than half of all success depends on it, and after the data is stored,

here they are in the atom s3 storage, you can actually train the model, yeah, training the model is just such an iterative review.

why is this useful, because it is clear that creating pictures using text and editing pictures is much, much easier than actually drawing yourself, something that people always did before took a huge amount of time, now it’s enough just to write in text, the picture will be generated, you some area you don’t like, you covered it up, painted what you wanted, really simplifies the work of designers, and very much so, that is, the ability to not only generate an image, but also edit it. with the same text, yeah, and moreover, draw not just one picture, but a whole one, a whole collage of these pictures or a whole panel, that is, you have created a gift for designers, is it necessary, is it necessary now, some designers are afraid of this, that we as if automated work, in fact , is not so at all, because artificial intelligence

is a tool that allows you to simply optimize work, it can be used by anyone the design profession is no exception in general; there is a routine part of this work. it needs to be automated as quickly as possible in my opinion, as high-quality as possible, this will only save people’s time, in fact it will also improve the quality of the content, animation, for example, how many routines are there, animation is not about creating videos at all - they actually make films there how many, well, over the years, i mean , now this can happen faster and faster, that is, since, well, until the creation of full-length films, the technology has not yet matured to be honest, but the progress is such that... if you have been saying for 3 years that we have been working on neural networks for 3 years, yes, i mean creating a neural network that generates pictures from text, so if you look at how neural networks, the best neural network created an image 3 years ago, then you will see that it’s very, very bad, let’s watch the video, let’s watch the video, and then i’ll ask my questions, yeah, what

can you tell denis, i’ll comment, that’s all- it's an animation, it's not a full-fledged video, was it made by kontinsky? yes it kandinsky did it, how he does it, he draws the first frame based on the text, and then you choose, that is, how animation differs from video, in that animation is a camera flying around a static object, or something like that camera movement, and video is a full-fledged movement of everything, here it is still animation, because there is a first frame, and then we select the camera movement, that is, the monotonous movement of the camera, this is what we choose. we draw the first picture using zum and we can without creating a new model on based only on a model that generates an image from text, generate animations like this, let's tell you where to look, yes, yes, there is actually a telegram bot within which you can create animations like this, that is.