Live data from Hacker News

AI-generated sad girl with piano performs the text of the MIT License

suno.com

281–290 of 389 posts

Re: AI-generated sad girl with piano performs the text of the MIT License

#281

Asked ChatGPT first to convert the license to poem: https://suno.com/song/bdad5f22-a1f0-42fb-a3d8-572d289687ea "Publish, distribute, let your dreams take flight, Sub-license, sell, under stars or sunlight."

It would be fun to do GPLv2/v3 rap battle.

Here you go: https://suno.com/song/16da57d3-b68f-41fd-ad07-4da2b56bdb36

Re: AI-generated sad girl with piano performs the text of the MIT License

#282

While almost everything sounded really good and well put together, the voice itself has a constant... phaser? robotic vibrato? applied the whole time, which I found surprising. We've got better voice synthesis available already and other instruments don't suffer the same effect. I've not heard that before - does anyone know if that's specific to this model, or a more generic voice issue?

It’s called a vocoder. It allows for (for instance) a monotone-sung piece of text to follow a set of midi notes, by modulating it using a carrier wave (I think. Please correct any inaccuracies!).

I use it sometimes in FL Studio when creating electronic music (plugin is called Vocodex).

Presumably they take the AI-generated voice and generate midi notes, and apply a vocoder to the voice, following the notes.

Re: AI-generated sad girl with piano performs the text of the MIT License

#283
post #132

While almost everything sounded really good and well put together, the voice itself has a constant... phaser? robotic vibrato? applied the whole time, which I found surprising. We've got better voice synthesis available already and other instruments don't suffer the same effect. I've not heard that before - does anyone know if that's specific to this model, or a more generic voice issue?

Yeah, surprised at the amount of comments here about how good it sounds. The voice is full of artifacts, making it quite uncomfortable.

It's got elements which are great and elements which fail hard. I can complain about one bit specifically but still recognise the massive improvements in other areas over what we've seen so far.

Re: AI-generated sad girl with piano performs the text of the MIT License

#284
The question is not if AI replaces mediocre pop, but how the best music producers learn to use AI. Do they make more music or better music? Someone will create an AI tool that has 100s of knobs and producers and artists can work with them just like they do with their colleagues. The question is if people see the difference.

Typically, the intelligence behind pop-song is someone like Max Martin. https://en.wikipedia.org/wiki/Max_Martin, see Max Martin production discography: https://en.wikipedia.org/wiki/Max_Martin_production_discogra...

Re: AI-generated sad girl with piano performs the text of the MIT License

#285
post #269
post #113

Earlier quoted context omitted.

When recorded music was invented, musicians protested. Recorded music was devoid of any vitality or soul. Recorded music still became a hit. Then we got the synthesizer. Again we got the same complaints, lifeless and without soul. The synthesizer still became a hit. Now the next step is happening, and we see the same complaints all over. Only time will show if the next step will happen anyway. My gut feeling tells me…

Humanity lost some things when it gained recorded music. It made the profession of performer less valuable, and diminished the number of performers who could make a living. But humanity got something very valuable in return — the ability to record and play back music. The same goes with the tradeoffs made for photography and motion pictures. I see little value to humanity in tools that are able to generate an endless…

"Music derived from existing music" describes almost all music ever written. So not any kind of argument against AI?

And the quality of music generated by AI is increasing geometrically. Be careful to consider that any music heard today will be among the least quality generated by AI. Because it will get better with practice, at the speed of light.

That first comment I can get behind, but probably not in the way intended. Recording technology made performers less valuable, so fewer could make a living. The AI composers (and performers) will go further down that road. My conclusion? Get used to it. Just like human-adding-machines got replaced by calculators. And a generation of weavers, replaced by looms guided by punched cards.

This phenomenon is not new, and will go down a well-worn path.

Re: AI-generated sad girl with piano performs the text of the MIT License

#286

I remember that this song was linked a few days ago. I decided to then tinker around with this tool together with my colleagues (also MIT License text). The results were too funny to not share them in this context: Our favorite: https://suno.com/song/30c5fff7-7417-42cd-b758-699854ef06d3 The extreme bassdrop: https://suno.com/song/1485e9d0-f0fb-4083-819a-bfb9db6c066a The country: https://suno.com/song/a4307c43-0a1e-4c…

I'm going to download these, since you gave me permission.

Re: AI-generated sad girl with piano performs the text of the MIT License

#287
post #178

These songs don't have any hooks. Melodies don't get repeated. They all just meander along. I think as they get better at making these great middle of the road songs, edgy music will reemerge. Whatever AI will be good at, will immediately devalue, in the realm of arts. Just how photography gave way to non-realistic art and how drum machines made sloppy drums (or ridiculous apex twins) hip. Then, the artifacts we see…

This is your comment as a song:

https://suno.com/song/c974b1ca-c69e-47a9-994c-9172fae52927

Re: AI-generated sad girl with piano performs the text of the MIT License

#288
A little off point but I have read that many times but never spent so long thinking over those words - singing a contract actually makes one read it, and gives time to think about it because I am not rushing to the end of the paragraph.

So weird.

(Like the separation of Authors and Copyright holders implies things I needdd to think three times about)

Re: AI-generated sad girl with piano performs the text of the MIT License

#289
post #178

These songs don't have any hooks. Melodies don't get repeated. They all just meander along. I think as they get better at making these great middle of the road songs, edgy music will reemerge. Whatever AI will be good at, will immediately devalue, in the realm of arts. Just how photography gave way to non-realistic art and how drum machines made sloppy drums (or ridiculous apex twins) hip. Then, the artifacts we see…

Your comment seems to presume that AI will not get any better than it is now. Imagine an AI that understands how to create deep, impactful music better than humans do, because it understands how music works at a biochemical level. Imagine it can even predict the dynamics you're describing, about employing "unwanted artifacts" in the music as a way to evolve new genres. It would no longer need to create such obviously…

I think that requires a baseline reasoning capability that we see no signs of developing as of yet.

In the field of AI, only game playing / graph search has gotten to that level of superhuman capability.

Re: AI-generated sad girl with piano performs the text of the MIT License

#290
post #178

These songs don't have any hooks. Melodies don't get repeated. They all just meander along. I think as they get better at making these great middle of the road songs, edgy music will reemerge. Whatever AI will be good at, will immediately devalue, in the realm of arts. Just how photography gave way to non-realistic art and how drum machines made sloppy drums (or ridiculous apex twins) hip. Then, the artifacts we see…

Idk I've managed to generate some good-ish ones getting it to generate the lyrics itself as well:

A smelly wolf: https://suno.com/song/c2b30ffc-729f-405b-8f22-b1b5f36a7c6a

Trying to get a lid off a jar: https://suno.com/song/44562993-df45-4b56-939b-afd65832042f

Two people that are too different for each other: https://suno.com/song/c63c82fe-399a-41b8-91b2-f16911deaaf0

Vocaloid robot whose code is incompatible with love: https://suno.com/song/fbb51ff7-3f69-41b0-9d41-7f6b5f6a5d87 (I want to do something more with the hook in this one "Heartbeat system, can you teach me to feel?" was touching)

An AI achieves sentience: https://suno.com/song/3eee76bd-2313-423f-87e3-035566b4718c

Mushroom psytrance: https://suno.com/song/a785adf8-92dd-4b13-acb7-93beb44ab7b2

Kernel panic dubstep: https://suno.com/song/5d37f5e7-3e62-4df8-a1d8-67122470aeff

Neuromancer: https://suno.com/song/d2705c66-4be5-496c-add1-480427b4a005

I mean it's definitely not perfect, but as per 2 minute papers "only one year later..."

Post reply on HN