> Unfortunately it turns out that classical music and waxing poetic are easily generative in an enjoyable way
On the contrary, I would say that generating convincing and original classical is an incredibly hard (if not impossible) task. All the current music AI projects give results which may sound “good“ to a casual listener, but they sound horribly wrong to any educated listener. The reason is that AI can only imitate the surface, but completely misses to recognize/synthesize larger structures. This might be ok for some background noodling in a TV drama, but not for the concert stage.
Finally, we rarely perceive art works in isolation. We know and appreciate the fact that a certain work has been created by a certain person in a certain time.
It may be instructive to look at David Cope's [1] work (what he calls "recombinant music" [2]). Cope's been writing algorithms to compose in the styles of the masters (Mozart/Chopin/et al) for about 3 decades now, well before the recent surge in "AI". His techniques are much less sexy for the "deep learning" enthusiasts, and yet he managed to outrage an audience of connoisseurs who assembled to listen to a "lost Chopin piece" only to be told, after they shared their applause, that it was composed by a computer taught to mimic Chopin's style (the composition was performed by a musician). The response, in my opinion, also points to music as a social constructed experience and not purely attributable to the sound signal itself. i.e. if I give you a romantic background story for a lost composition of a master, you may be inclined to experience the piece in a more favorable light than if I told you it was generated by an algorithm (or the converse).
You're absolutely right that the musical output of the current crop of "AI" projects (especially the ones using deep learning / neural networks) are crappy to even a modestly trained listener .. or even a lay untrained listener for that matter. However, more involved modeling (such as Cope's) has produced some very compelling results decades ago, so it would be a mistake to assume that the current crop won't get close enough [3]. The fact that DL systems don't need to be instructed in the way Cope has had to encode his musical understanding is also something to be considered in the evaluation as well as in scoping their capabilities going forward.
[1]: https://en.wikipedia.org/wiki/David_Cope [2]: https://www.recombinantinc.com [3]: https://deepmind.com/blog/article/wavenet-generative-model-r... (see "Making Music" section and examples there)
However, we have to make a clear distinction between creative and recreative methods. David Cope's work is impressive, but it focusses on the recreation of existing musical styles. This is interesting from a musicologist perspective, but not very interesting artistically.
I would certainly say that deep learning generates lots of interesting “material“ (like many other methods of algorithmic composition), but we still need a human being to curate, edit and assemble the material into a meaningful piece of art.
Finally, I think the current AI debate can be very fruitful for the arts. In a way, it raises similar questions as the concept of the “readymade“ and the pop art movement did in the 20th century.
Btw, I'm currently working on an opera which uses AI generated lyrics :-)
BTW - I'm curious, what do you think about birds songs? Are their songs interesting artistically? How do you think they were composed?
On the other hand, you have composers like John Cage (or more recently: Peter Ablinger) who claim that the act of listening itself can be/create art, blurring the borders between nature and art. There are conceptual pieces which only consist of listening instructions.
Finally, bird "songs" have been used as the source material for musical composition for centuries. You can find it in Beethoven, Mahler, Debussy, Stravinsky, etc. Olivier Messiaen even was a hobby ornithologist; he faithfully transcribed hundreds of bird songs and used them in his music (see for example his piano cycle "Catalogue d’oiseaux").
As for the question of who composed the actual bird songs, the answer probably depends on the theological background of the person you ask ;-)
I think this topic will keep reverting to the point you raise - "meaningful art". As long as the "meaning" is a construct in a human brain that we're looking for, we have little to say about AI and it's capabilities (like Joshua Bell's hardly-noticed playing of Bach classics at New York's subway station as opposed to when he's performing at a concert hall).
.. (edit) and I do think that active listening is itself a creative act.
I think you're right, in that AI won't be able to create deeper themes and patterns, but I disagree with the above point: AI will take over the music industry because the vast, vast majority of people aren't educated listeners. The popularity of 6six9ine is a fantastic example.
To put it another way, I don't need another Terry Riley, Clint Mansell, or Meredith Monk, I just need something good enough to occupy some brainspace while I drive home after work; a move soundtrack just needs something sad, or exciting, or tension building. The AI can and will get there soon enough.
Lack of "larger structures" is the key here. That's where GPT-1 was. Each sentence, in isolation, seemed to make sense, but after a few lines, it was clear the text wasn't going anywhere. By GPT-2, paragraphs seemed semi-reasonable, but multiple paragraphs didn't hold together. GPT-3 is able to keep it together for a few paragraphs, but probably not for a book chapter.
Music synthesis has the same scaling issue. Generators which imitate known patterns work for a few bars, but after a while you realize the music is going nowhere. The GPT results on text indicate that a scaleup may fix that problem.
Lossy is bad. Humans will never stand for it.
Perfections will not stand for it. Pragmatists won’t notice.
This isn’t a bad thing. We need perfectionists to drag us across the “good enough” line. Despite our childish kicking&screaming.
Is originality the key point? Because AI-generated music has high probability containing piece of rhythm from their training dataset.
Generative music has been around for half a century, or longer depending on how you want to interpret things. Mimicry as a mechanism for composition has been around for as long as humans have made music.
It is wholly uninteresting to discover that we can design generative systems for music that excel at mimicry, because we've already perfected that mechanism in analog. The interesting bit is that the genesis of new musical ideas is driven by manual interaction and direction of the generative system, and at that point it's the guiding hand of the engineer turned artist that we can respect and appreciate, not the mimicry of a machine.
Imagine a world where you ask your smartphone to make you a death metal song about fishing and feminism in Australia and to use Freddy Mercury voice and jazz harmonies and it does that on the fly and generates something objectively good.
Wouldn't that be revolutionary for music? Because it's entirely possible in the next decade. Probable even.
Put it another way. If an AI could generate new Beatles music on the fly, making it sound exactly like the Beatles, with the same creativity of lyrics, tight harmonies, beautiful melodies, would Beatles fans go out in their millions to buy them? No. In the same way that the same dusty demos from the 60s found in an attic somewhere became valuable when it was discovered that they were Beatles demos. The music didn't change, it didn't get better or worse. The personal story attached to them was what mattered.
I expect new genres to be created almost immediately. And I'm not sure how real musicians can compete with that level of noise out there.
If you start by referring to results from 50 years ago, have you tried listening to state of the art generative music systems lately? They can probably compose music better than 99% of humans.
This "human music" > "ai music" will flip. Suddenly. And it will never flip back.
Already starting to happen with ai lyrics I use for inspiration in creating EDM music ( i.e. https://TheseLyricsDoNotExist.com/ )
It never seems to play out that way at population scales
- https://openai.com/blog/jukebox/ (2020, quite good, but no classical music)
- https://openai.com/blog/musenet/ (2019 so not as good as the 2020 one, but showcases classical music)
There is no reason to assume that one cannot be moved by AI-generated music, as the AI has learnt from human-generated music and tries to mimick the styles.
I can see this kind of tech taking over stuff like stock music that's automatically added to consumer holiday videos or played on the phone while you wait for a customer service agent.
That said, I'd expect the agent to be an AI long before generated music becomes independently musically relevant.
Doing what has already been done is rarely compelling.
[1] https://magenta.tensorflow.org/music-transformer
[2] https://storage.googleapis.com/magentadata/papers/music-tran...
GPT-3 can write hauntingly beautiful snippets of prose. Can we expect it to scale up to coherent novels?
It's easier to see the limitations in the areas you know best. It's significant that it's this good at creative tasks, but I'm not convinced that creative tasks are the most at risk.
GPT-3 was OpenAI exercise in how far pure scaling can get you. They have used some 2 years old method. Already at the point when they started training GPT-3 there were readily available remedies to many of GPT-3 issues. Given how they energized the wider community I'm sure even more focus will be given to improving language models in the following years.
Some rough ideas right now:
- People think that cherry-picking the best GPT-3 examples is cheating - why? Train a model that will be selecting the best examples for you. My proposition is to train a model that guesses whether some text was GPT-3 generated or human made - select samples that look the most human like.
- Use a good search method to look for the best samples. Monte Carlo Tree Search? AlphaZero? MuZero? If MuZero can play a games of Chess, Shogi, Go and all of Atari then way should it not be able to play a game of what word will come next?
- Hook up the language model to a search engine. Instead of writing a whole program yourself, why not to copy-paste some stuff from StackOverflow with some slight modifications?
Etc.
It doesn't address the issues with agency, grounding and multi-modality, but it's a good road map for the next 2-3 years.
What you said is essentially: "Train a better GPT model". Humans have trouble distinguishing between (some of) GPT-3 and human writing. The only way to build a classifier that can do this is to build a model that is better than GPT-3 at understanding text. It would need to have features currently absent in GPT-3, such as common sense and understanding the world (e.g. causality, physics, psychology, history, etc). If what you say could be done, GPT-3 would have been designed as a GAN.
That's the difference between GPT and BERT. GPT can only attend to the past outputs, while BERT one can attend also to the future outputs.
Now imagine that what you are going to say is not actually determined by you, but it is sampled randomly from what seems like a reasonable thing to say. This is how GPT-3 works. If somebody ask you some kind of question you can guess 70% yes or 30% no, then roll a 10 side dice to pick one, but once you pick there is no way back.
And I already mentioned that it does not address agency, grounding and multi-modality, but it could improve GPT ability to formulate coherent arguments, follow instructions, write mathematical proofs and computer programs or play games.
BTW - I actually have implemented it and it works quite reasonably.
Here are samples from GPT-2 small and GPT-2 small + RoBERTa adversarial decoder.
For a human who does logical thinking, yes. But for a language model? I'm actually not sure, because it's possible that a sufficiently complex language model like GPT-3 does form some kind of general logical rules encoded in its weights somehow. This would be interesting to explore.
I actually have implemented it and it works quite reasonably.
Oh, so you are trying to design GPT-2 like a GAN, or at least move into that direction. Interesting. Yes, I don't see why not. What do you think about taking a step further, and actually making it a GAN, i.e propagating the error from discriminator into the encoder? I'm sure you're aware of multiple attempts to do this with smaller models, with mediocre results, but maybe GPT-3 scale is what needed to make it work?
This should be testable: train AI on all the music ever written before Bach, and see if it ever produces something ressembling Bach.
Maybe that kind of test has alretbeen done; it would be interesting to know what comes out of it.
There is also AIVA with more production ready results:
https://www.youtube.com/watch?v=gzGkC_o9hXI&list=PLv7BOfa4Cx...
Not sure how it works, but it has better results maybe because it's using more predefined components and less AI so it's also less "creative".
More AI music projects here: https://magenta.tensorflow.org/
There have been music resembling Bach written before Bach (e.g. https://www.youtube.com/watch?v=VUcdBz3LIuU). How much more of resemblance you hope for?
But there’s so much classical music out there, that an average person would never be able to tell the difference between something that is generated anew and something just really obscure.
Have you ever tried copying and pasting sections of GPT output into Google?
I don't know which way things will go. Will newer and later generations be accustomed to and accept lower fidelity art? the uncanny valley be bridged from both sides? Or will there be attention being drawn to what is 'real' vs 'synthetic'. Good art is pain. Labelling these things distinctly will probably reveal that I consume some 'real', annoyed by some 'synthetic' while enjoying as much. This will get challenging as machine generated can seem more 'real' than much human made content: 'real' is/was a subset of human made, machine made is/was a subset of 'synthetic'.
This line of reasoning leads me to believe that premium content will be interactive. This means that the content has to either have a human connection or be closer and closer to passing a Turing test. The current examples of machine made static content wont cut it.
Related to instruments themselves, the trial and error is one very important aspects I can think of right now that's enjoyable: playing something off beat or out of tune and correcting yourself. The feeling of correction and improvement.
It is a real pity the actual algorithm itself has no way to enjoy what it is creating.
GPT-3 and other projects seem to drive hype cycles in the tech community and convince people like Elon Musk that the AGI revolution is near. But I think recent progress is just another example of machine learning models being able to generalize on super large datasets, even if it's the biggest model so far. It's not clear to me that larger models will solve this in the limit; take the way GPT3 fails on addition past a certain number, and the fundamental inability for transformers to learn certain algorithms. It is certainly still possible for this type of large dataset, large model style of ML to make human life better in many ways - like Tesla is trying to do with self driving cars, or Covariant with automating Amazon-like jobs. But I think when it comes to tackling the hard problems of true intelligence, we're missing a dimension somewhere.