No sense of humour…DM vs Internet

I was very intrigued now what is still possible with udio now after all that...
And of course i was very curious about other aspects of this, so i tried something...

The name of the artist was nowhere mentioned in the process, but it seems if you point it hard enough into a certain direction it still comes up with an exact copy of Artists that fit on that


I guess it cannot get closer than this, and i think this is a flaw in the software.
I did not provide udio with anything else than a prompt.

Edit: or, after thinking about it, it is missing training data. depending what data they use, the further back in time you go ( and especially if you point to an exact year there ) the less data you have in total.
So pointing udio with your prompt to a special year, you get very close to the provided training material.
I have to try this now.
 
Zuletzt bearbeitet:
But they invite all users to report such content:
  • a statement that the information above is accurate, and under penalty of perjury, that you are the copyright owner or the authorized person to act on behalf of the copyright owner; and
  • the physical or electronic signature of a person authorized to act on behalf of the owner of the copyright or of an exclusive right that is allegedly infringed.
But from the last two phrases, I get the clear impression that it's not "all users" that are invited to report, but the copyright owner themselves or their authorized representative? In this case DM or their staff.

Just a question, can you still hear this somewhere? ☺️
Has anyone downloaded this, can someone send it to me or upload it to a cloud? Thx!
Please PM
So I got an answer from the company that hosts my website and they strongly recommended not uploading the videos there, but instead using services meant for such things. So I will follow their advice and won't be uploading them. And probably a good idea not to share the files in general. Sorry.
 
I was very intrigued now what is still possible with udio now after all that...
And of course i was very curious about other aspects of this, so i tried something...
I'm not very civilized with older music. Jimi Hendrix?

With the first DM song, I wrote Depeche Mode as the prompt.

HOWEVER!!! The only prompt I used for all the following "DM" songs was the one that Udio originally replaced Depeche Mode with, which was:

Male vocalist, Electronic, Synthpop, Rock, Alternative rock, Dark, Rhythmic, Melodic, Atmospheric, Nocturnal, Alternative dance, Mechanical, Passionate, Cold, Longing, Sombre

People in the comments said they were getting DM songs with that same prompt as well (as I did share it in the description).
 
what AI could/can do astonishingly well is very minimal (instruments) vocal based music, no matter folk, singer songwriter etc..
with high expression level.

the prompt words: thanks for that!
my guess here is - the system tagged things and has not so many training material that had this kind of signature. let's assume they had the chance of training "all music" might have thrown in more and even more tags.

so if you check that with simpler systems like "people who bought this might love that" seem to be in a similar frame of tags or tag clouds.
really interesting what kind of "intelligence" might be behind genres and tags in general.
 
I'm not very civilized with older music. Jimi Hendrix?

With the first DM song, I wrote Depeche Mode as the prompt.

HOWEVER!!! The only prompt I used for all the following "DM" songs was the one that Udio originally replaced Depeche Mode with, which was:

Male vocalist, Electronic, Synthpop, Rock, Alternative rock, Dark, Rhythmic, Melodic, Atmospheric, Nocturnal, Alternative dance, Mechanical, Passionate, Cold, Longing, Sombre

People in the comments said they were getting DM songs with that same prompt as well (as I did share it in the description).
You shouldn't expect too much from the current version of this type of AI. There is no trace of intelligence and no great variety of results. I wouldn't be surprised if several people with the same or even similar prompts were given completely identical results.
 
my guess here is - the system tagged things and has not so many training material that had this kind of signature.

It really looks like that. to get anything else than Genesis out of it if you point it to 1975 british Prog Rock is very hard.

I am trying different things now since a few hours and it clearly points to a lack of training material. Like they only took one or two of the most well known and successful snippets from every style and year.
And if you point especially to a certain year and style, you only get that.

when you ask for british progressive rock 1970s you get either genesis ( 8 out of 10 ) or early Pink floyd, and it is very hard to get something else out of it. Everything sounds like Peter Gabriel or Syd Barrett.
Only if you especially point to 1978 and later it changes slowly.
 
Zuletzt bearbeitet:
Ich glaube da passiert gerade was ich vor Monaten schon mal in einem ähnlichen Thread prophezeiht habe...
DAS ENDE IST NAH

nein, quatsch.

Text- und Bildmaterial gibt es im Internet genug, und die zu verarbeitende Datenmenge ist mit Sicherheit um einen signifikanten Faktor kleiner als bei Musik oder gar Videos.
Ich dachte eigentlich deshalb wird es noch ein weilchen dauern bis brauchbare Modelle auf dem Markt sind...
Aber wie es aussieht haben die einfach auf eine sehr begenzte Datenmenge trainiert, und es ist ziemlich klar was das Trainingsmaterial war.

Sind Udio jetzt vielleicht mit einem unfertigen Modell vorgeprescht weil Suno mit einem nutzbaren Modell rauskam und die den Hype mitnehmen wollten? Das sind ja offensichtlich keine Big Player wie Meta, Microsoft oder Google.
 
They are obviously not big players like Meta, Microsoft or Google.

They're not a group of geeks in a basement either though. According to this Rolling Stone article:

Udio’s product came together remarkably quickly after its founding last December by four former employees of Google’s AI-research wing, DeepMind — David Ding, Conor Durkan, Charlie Nash, Yaroslav Ganin, and Andrew Sanchez — along with Andrew Sanchez. They’re backed by a range of tech heavyweights, including a16z (a.k.a. Andreesen Horowitz) and Instagram co-founder and CTO Mike Krieger. “We were very well supported from the day we took investment,” says Sanchez. “So the technical co-founders were sort of able to hit the ground running because we could get that all going pretty quickly.”

There are some notable music names on Udio’s list of early investors as well, including Common, producer Tay Keith, industry vet Steve Stoute’s United Masters, and Will.i.am. In a press release, Will.i.am, who’s long been an evangelist for AI’s musical possibilities, was effusive about the company’s product: “This is a brand-new Renaissance, and Udio is the tool for this era’s creativity,” said the artist, who was consulted during the development of the product. “With Udio you are able to pull songs into existence via AI and your imagination.”
 
that's for sure - but they knew how to do it. let others die for you. and when I rush, I rush for you ;-)

well - what I thought is, they only got the Tags rolled out on the more known bands rather than anything underground. that's why synthpop etc triggers davedancing and I'd assume the same for other genres. Editors, Depeche Mode and maybe Hurts are in - others may be there as well - since the new try sounded more like those WGT-synthpop-dark-bands that never got even the idea of what is and was so cool with DM or NEP or …

So - the AI model is about to be hard to prime right.
but in our case it was cool - since I'd really like to check that AI how a generic DM song sounds like - you did.
so - it is sort of our solution for 2024 humanity.

but we must wait.



btw - I tried something "likely" by writing an article about a music style that does not exist and recombined it in a special way.
so now if you ask GPT it throws something at me that I sort of vaccined it with.
enough tags from other pages might re-combine the tags and that might chance how the result could be like?

normally you do not have the chance, here you need to create a band and tags and genre overnight and inject that stuff to the training material and into their engine.
it also shows, that the results are sort of ... hmm - mainstreamed.
that's what I'd like to point out - means - it is sort of not fair - but grabbing stuff is sort of not fair as well since they take the way we post. if Sequencer.de was the source it will and would have responded differently, same here with music.

yes that is the geek inside of me - I bought my first computer because I wanted to unterstand it..
 
edit: Chuck Norris hat den Song jetzt leider gelöscht. Und den Account.

Zweimal.

Das ist schon krass.


das ist nicht krass, sondern ganz normal.

wer nachgemachte stimmen veröffentlicht und mit namen von anderen personen wirbt um damit geld zu verdienen, der weiß was er da tut, und dass das mindestens persönlichkeitsrechte und markenrechte verletzt.


Erst später kommt dann die kreative Neuschöpfung - und die passiert auch beim Menschen nicht aus dem "Nichts", sondern aus seinem Erfahrungshorizont.

sie kommt garnicht.

Kurz gesagt: lass die KI mal in ein paar Jahren "erwachsen" werden. Dann kann man nochmal über Schöpfungshöhe und Kreativität diskutieren.

diskutieren kann man alles. ist halt oft sinnlos. :)


Und rein theoretisch könnte es ja auch eine reale Band geben, die Musik in der Art von Depeche Mode macht und die einen Sänger gefunden hat, dessen Stimme der von Dave Gahan gleicht. Darf der dann auch nicht mehr singen?

"ja, herr richter, aber rein hypothetisch hätte ich ja auch von rechts kommen können und dann hätte ich doch vorfahrt gehabt, oder nicht?"
 
Zuletzt bearbeitet:
So guys... I decided to reupload all the songs on a new channel. But to play things safe, this time I have made NO mention of you-know-what and also replaced you-know-who's face with just random dark pictures like my other videos had.

So if you're someone who missed out on the songs that were linked in this thread, you can see them here. As for how long this channel will be up? Who knows.
https://www.youtube.com/@andrea_fryer
 
Did YouTube give you any details why they closed your channels? Was it related to DM?
Nope, I tried to ask them directly as well but they refused to give specific info. They just kept repeating the initial reason (spam, scam etc policies). I'm still waiting for news on the internal appeal that the support lady made. It's been silence from them for about a week now.

Originally I was just going to patiently wait for the results and push all of this out of my mind until I hear more from YouTube... but then this happened:



After seeing this, I couldn't contain myself any longer.
 
Vaughn ist one of theee DM Commenters - and I must say - I am not so far from his "verdict" - would have bin a lot cooler to listen to this as a leaked song - I just thought one thing - is has sort of not exactly the structure of a classic (even DM) song, but the details are so real / authentic - it is ... good.

and second - he speaks about creating it and how it was sort of parameterised / prompted - and what other potential songs would have been created alongside of this?
this is more related to the KI, what it actually means to big data a well known group with a long back catalogue - I'd suggest a lot of other band tries might sound as good as this.
as long as the band has a long enough history.

so what did you think about him when reacting since he sort weighs the KI and it's "controls" and in this case you as the initiator of this song etc.?
how does it feel - is it different after what has happened to you and your channel and - sort of this is an interesting double meta reflection…
 
Vaughn ist one of theee DM Commenters - and I must say - I am not so far from his "verdict" - would have bin a lot cooler to listen to this as a leaked song - I just thought one thing - is has sort of not exactly the structure of a classic (even DM) song, but the details are so real / authentic - it is ... good.

and second - he speaks about creating it and how it was sort of parameterised / prompted - and what other potential songs would have been created alongside of this?
this is more related to the KI, what it actually means to big data a well known group with a long back catalogue - I'd suggest a lot of other band tries might sound as good as this.
as long as the band has a long enough history.

so what did you think about him when reacting since he sort weighs the KI and it's "controls" and in this case you as the initiator of this song etc.?
how does it feel - is it different after what has happened to you and your channel and - sort of this is an interesting double meta reflection…

Yeah the structure of this song (and the others) is clumsy for sure. For two reasons:
1) I'm someone who doesn't have any musical talent whatsoever and also completely clueless about music theory or how to structure a song (so part of the fault is in the creator)
2) It is very challenging to get proper song structure in Udio. It has a hard time repeating sections that were earlier in the song (for instance a chorus) instead it likes to keep reinventing the song as you add new chunks. (so part of the fault is in Udio itself)

Other potential songs:
So whenever you generate a clip in Udio, it will produce two samples. When I made this first song, the "twin" was actually this clip:


It sounds super promising, but it also had some issues that I didn't like. That's why I went with the other twin, which ended up being that first song.

As far as prompting, to be honest, ever since the first song, I have been constantly reusing the original prompts that Udio replaced "Depeche Mode" with. I should experiment more though. It would be interesting trying to get Martin Gore's voice for instance. Or try different things like 80's or 90's.

So what did I think about his reaction?

1) Surprise: Well first off, I honestly thought everyone had already moved on and forgotten about this song. So I was shocked and surprised to see a reaction video now at this late stage, after a couple of weeks had passed. I guess Vaughn had other videos scheduled before he got to this one. Dunno!

2) Emotions resurfaced: Since this whole event of losing my YouTube account has been super traumatic to me, I have been pushing it all out of my mind. I haven't touched Udio. I haven't touched YouTube. I've just been moping around ignoring the world and playing Valheim to get my mind off it all. Just waiting waiting waiting for a result of the 2nd YouTube appeal.

So when I saw his reaction video, all the emotions resurfaced and overwhelmed me. To actually see the video that had been crushed, bludgeoned, erased... now there - in his video. It felt surreal to see it there knowing that the original does not even exist anymore. Surreal also in the sense that the video was there in someone else's world, with their comments. And I felt like I was behind a glass window watching from afar. Almost like a mother watching through a glass window when her baby is being handed to a foster parent and she has no control or access to her baby anymore. Sorry for being dramatic, but it was this kind of feeling. Silly, I know!

3) Delight and bittersweet feelings: Of course, assuming my video was dead and forgotten, it was a feeling of delight to see that people still care about it (in either good or bad). I couldn't believe people still want to talk about it! So this made me think: "Why should I be excluded from this experience?" "Why should I be behind the glass window watching from afar?" So this emotion prompted me to open a new channel and reupload the videos. (most people will never find them of course, since there is no mention of DM anywhere, but that's fine)

4) But of course, I understand that the above rambling is not what you meant when you asked "What did I feel about his reaction". You probably wanted to know what I thought of his actual reaction. Well first off, I was quite surprised that he reacted as positively as he did. I recently watched his video where he listed his 10 top least favorite DM songs and he was BRUTAL in that video. I was expecting him to be much more brutal in his reaction to my video! I could see his inner struggle with the "wanting to hate, but I kind of like it". And I understand this emotion, as I still have conflicting feelings myself.

Some points he made:
a) About the lack of the human touch and when he was comparing it to how easy synthesizers made producing music. Yes, although Udio does most of the work, it's not like the song was just from one press of a button. For the first song, it took 10 hours of generating samples and adding parts and listening and comparing and generating more to get that end result. So there was some human element in the process.
b) He also talks about how worrisome it is that people get lazy with making music. And for sure this is a valid point when we are talking about actual proper musicians. But then there are people like me: Who have zero musical talent. Software like this (regardless of whether it produces famous voices or not) gives people like me the opportunity to create something they could have never created before. And for us, this is a wonderful beautiful opportunity and experience! I'm a visual artist, so for me it's easy to make nice artwork. But what about people who have zero artistic talent, yet have these visual dreams in their brain that they wished they could express in an image. Equally for people like that, AI generated art is a wonderful opportunity.

But overall, the whole reaction video was a delight (even if he would have been brutal). And it kind of woke me up from my depressed and sad state. After opening the new channel last night, I feel so much better. I don't feel silenced, shackled or chained. We'll see how long that lasts though. I am emotionally prepared for it to be taken down again.
 
Zuletzt bearbeitet:
Glad to hear that you managed to handle the situation for yourself somehow.
Did you talk to Vaughn yet or did he try to contract you?
I'm not an expert at all, but I would imagine that he should have asked you for permission to use your video on his channel, from a legal and moral point of view.
 
Glad to hear that you managed to handle the situation for yourself somehow.
Did you talk to Vaughn yet or did he try to contract you?
I'm not an expert at all, but I would imagine that he should have asked you for permission to use your video on his channel, from a legal and moral point of view.

Yeah no, he never asked for permission - but I actually don't mind. I'm guessing that most "reaction videos" never ask. And like he says in the video, he didn't even know who had made it, although I guess he could have asked the people telling him about it.

In the video he invites the creator to reach out, so I did send him an email explaining who I am, how I made the stuff in Udio etc.

He invited me to do a zoom call with him for an video interview. But I told him that right now that doesn't seem like a good idea because:
- I feel like I would blunder my words when talking about ethical stuff and make the haters even angrier. When writing text out it's so much easier to think carefully about what I will say, but in a real life speech situation I can be super shy and clumsy
- I feel like I might say something that messes up the legal side and makes me more vulnerable
- Until we get results with the appeal, it feels risky to talk about losing the channel. (if we were at a point where all hope had been lost, I might feel differently)
 
He said in his video that he is ok with contacting to "the maker" and he is more into the "solution" and just talks about that, so he may see you as the messenger who brings something he sort of "was afraid" of - what I read between his lines and sort of "unknown" what prompt led to exactly that solution - I don't even think it is "against you" it's just like someone did it with KI and the KI is what is now to be examined.
what I would think: since it is not easy to reach him via yt - you can only comment there or check for his email and maybe he likes that you did it and it tool some time for you to create or let create this - we electronic musicians know this "press a button" kind of argument, so it is sort of next level but same thing - technology again.
but since you had connection -

I like that you could do a face to face reaction since you would be the voice for what you did - you may not be the voice pro or for AI itself but you could if you liked.
so - lets see this as you as a reporter and him as some sort of "the musician" who is into DM as well is a very good thing for you, your channel, his channel and the topic and idea behind it - I'd watch it!

maybe in some weeks to get the balance right - and then talk - maybe it is even cooler so both of you have had some time to think about it more than twice.
I'd think this could be a very good and deep talk about KI vs Music vs DM - since I am a DM lover as well it is all good.

aaaand - if you have that video inside the talk and not just the music it is a commented thing which is even more "legal" - I had a record talk section in our sequencerTalk show with a good guy (and different ideas and likes) and we just tried without playing the music since that would kill the channel by claiming ..
but - I hear some did it and it seemed ok - since it is metatalk about it.
just a nice double plus thought about winning the moral game and talking about it - which is actually you wish / job anyway? isn't it?

So - maybe see and hear you both on that topic.
 
b) He also talks about how worrisome it is that people get lazy with making music. And for sure this is a valid point when we are talking about actual proper musicians. But then there are people like me: Who have zero musical talent. Software like this (regardless of whether it produces famous voices or not) gives people like me the opportunity to create something they could have never created before. And for us, this is a wonderful beautiful opportunity and experience! I'm a visual artist, so for me it's easy to make nice artwork. But what about people who have zero artistic talent, yet have these visual dreams in their brain that they wished they could express in an image. Equally for people like that, AI generated art is a wonderful opportunity.
It is a great tool for those who need music for their projects, but I'm afraid that it will be (or already is) uploaded en masse to spotify, to earn money with it, no matter how good or bad it is. Because people are people.
 
Zuletzt bearbeitet:
I'm not an expert at all, but I would imagine that he should have asked you for permission to use your video on his channel, from a legal and moral point of view.
For reaction videos you don't need a permission. You can even take a video from pay TV for example, as long as you use it like that guy did. Let's say like some kind of "reportage".
 
I like that you could do a face to face reaction since you would be the voice for what you did - you may not be the voice pro or for AI itself but you could if you liked.
so - lets see this as you as a reporter and him as some sort of "the musician" who is into DM as well is a very good thing for you, your channel, his channel and the topic and idea behind it - I'd watch it!

maybe in some weeks to get the balance right - and then talk - maybe it is even cooler so both of you have had some time to think about it more than twice.
I'd think this could be a very good and deep talk about KI vs Music vs DM - since I am a DM lover as well it is all good.

aaaand - if you have that video inside the talk and not just the music it is a commented thing which is even more "legal" - I had a record talk section in our sequencerTalk show with a good guy (and different ideas and likes) and we just tried without playing the music since that would kill the channel by claiming ..
but - I hear some did it and it seemed ok - since it is metatalk about it.
just a nice double plus thought about winning the moral game and talking about it - which is actually you wish / job anyway? isn't it?

So - maybe see and hear you both on that topic.

Yeah, you have some good points about going ahead with the interview. It's also a good point that maybe it would be a good thing to do it later to let things sink in first and to figure out one's thoughts.

As for winning the moral game, I don't think I'll ever be able to win that as the moral reasons people have are very valid. And just because I had purely innocent intentions doesn't remove those moral concerns.

I'll have to see.

It is a great tool for those who need music for their projects, but I'm afraid that it will be (or already is) uploaded en masse to spotify, to earn money with it, no matter how good or bad it is. Because people are people.
Yep, understandable that if people see an easy to make money, they will try it.
 
Yep, understandable that if people see an easy to make money, they will try it.

all these people must be pretty naive if they think they can become rich and famous by using a ki for
generate imitation art. if something is too good to be true, then at least it isn't

I've been making electronic music as a hobby for over 20 years and if I wrote hits, nobody would be interested because people here don't like me and other broken things.

I wouldn't spend any money on a ki service that let it look like me I can do anything with it, but the rights to the work lie at the maker of the ki.

i think you've learned an important lesson. if you want to create something in the field of art, don't do anything with copies. Be a original.
 
Zuletzt bearbeitet:
i think you've learned an important lesson. if you want to create something in the field of art, don't do anything with copies. Only originals are the measure of all things.

Just to be clear, I am not one of those people "trying to get rich quick" on creating AI songs. In fact it's the opposite: I refuse to monetize or sell these AI DM songs because to me it would feel utterly wrong and weird to do. I've had so many people asking me to put them on Spotify, but since Spotify is a monetizing platform, I don't want to do that.

As for your last sentence. I get and agree with your point in a broader sense, but then begs the question: "What is an original". Every piece of music, every piece of art has had influences, references, inspirations. No art is "pure" in that sense. Many pieces of art that we consider masterpieces of history, have heavily borrowed or copied from other people's work. Each generation of music has been influenced by bands from former decades. Every movie has borrowed from movies before it. So where do you draw the line on what's "original"?
 


News

Zurück
Oben