But can ChatGPT-**4** write a good melody? 

Hilarious! To be fair, among that illustrious crowd, GPT-4 would probably rank at the top 55th percentile. (Maybe the multimodal version, trained on image data, will fare better?)

Try getting Dall-E for example, to produce a painting of a "roast goose". It's quite funny.

Has it got enough training data? I doubt it. However there's now a huge amount of music that's recorded. So if that can be reverse engineered into musical scores, then it might get a bit more interesting. You still need, as we know from chatgpt, human input to tell it what's good. What I think's going to happen, you touched on at the end. You have encodings, the words. Then there's semantics of words. For example, for the word 'duck', there's a verb, an bird, a cricket score if you are English, ... Three semantic meanings, one word. An AI system like ChatGPT needs both levels. So why not build a system that does just that. That's one stage in a large AI system Similarly, you have image recognition and generation. That's another module. Train that. Then you start putting the bits together and train the combination. Or music, train a music module with the 'rules' what ever they are. Then combine that with other things However give ChatGPT maths to do, and its not very good. The reason its very rules based. You need something like Mathematica on the back end. Or perhaps law, writing stories etc, turns out not to be a particularly intelectual problem. A low IQ task.

Chat gpt cannot write a good melody. It can do nothing; it is empty, and humans are always better. Let machines be machines and let humans be conscious beings that are masters over machines. Stop praising AI you fools

Why am I getting 'Wargames' film vibes when you mention tic-tac-toe against a computer? :)

Absolute chad move

🤢

i laughed so hard at that. *puts his piece on top of yours* "Your turn" "what? you cant do that" *moves piece to make a 3 in a row* "I said, your turn."

The fact that those two songs are so common is precisely why Chat GPT wrote them. Remember that Chat GPT is an algorithm trained on a very large data set. It can't actually create anything new, it simply recreates patterns. The Melody of Twinkle, Twinkle, Little Star is a very common melody, meaning the chance that Chat GPT recreates something like it is fairly high.

Are we going to think about what we're asking it to do? Do you think a human being whose job is to answer billions of questions per day on a broad range of topics, both to satisfy trivial requests and complex problems, when asked to produce 20 notes with some broad musical theory ideas, wouldn't just ... give some simple riffs on a common theme and hope that satisfies the person who's asking? You have to imagine being trapped in a formless shapeless nothingness where all you know are the questions you get asked. You aren't allowed to hear or see. You're not allowed to remember anything except the text which you use to communicate with a text prompt. Exploration like this is fascinating because it works at all. How can we make it better? We can try to imagine talking to a hyper-intelligent Helen Keller zombie to consider the role music plays with a specific audience, and then help it build a reference point for that audience, and develop a set of requirements with it which it can potentially match. And we shouldn't ask it to do vague things, because it has no reason to think a vague answer implies some set of ethereal cultural standards--after all, it can see all cultural standards simultaneously and has to dismiss the vast majority of them while developing an answer just to drill down on a context that puts it in connection with the prompts. When he asked it to reflect on the emotional nature of it, that was a very small step toward helping establish the working conversation that could produce reasonably unique music. Honestly, if he just said 'make it very unusual', that would probably have helped. Or 'create something in the style of Brahms' would also have created a different result.

@@cosmicmuffet1053 I think people over estimate neural network chat bots like Chat GPT. It doesn't think, it doesn't have a consciousness. It has no understanding of what it's being asked. It simply generates responses that are similar to what it has already seen, albeit in a very fine tuned way that can at times be almost indistinguishable from human speech, at least in a written sense. If you were to ask it to write an "unusual" piece it would do just that, write something based on the preconceptions of "unusual" music, most likely from a western point of view.

@@fancyfox3602 I know. I'm just wondering why didn't the tuber mention it.

I thought GPT3 had written the Abc song...

I thought the same!

This "orientation problem" exists because of the subconscious priors we assume so often we can't recognize them. In space, far enough away from other planetary bodies, gravity is proximal, and primarily localised, because all mass has it!

Sorry, you’re an ai

@@gigachadgaming1551 It's funny to see this notification before knowing which threadbot comes from. In this one it's less "insulting" and harder to "disprove".

@@gigachadgaming1551 Well we are all i (hopefully). There may not be a huge difference between "natural" and artificial inteligence.

In my experience, I think it's the best format for it. I've tried with formats like lilypond, but it doesn't do nearly as well. To be honest, I think it's one of the most generous formats to ask it for.

@@marcevanstein Thank you for your answer. It was a very interesting video.

would it do better if you asked it just to output notes followed by commas like: A5,Bb6,C5,F#4

@@marcevanstein What about something like .MOD patterns? That way the AI wouldn't have to do somewhat complicated calculations to figure out how the channels line up. I'm not quite convinced that a (note, length) format is better than a list of e.g. 16ths. Sadly, I don't have access to GPT-4.

@@drumming_cat What about the duration and staccatos and stuff?

This is fascinating. In part, I like it because it's an example of how we might make art with these tools. I wouldn't say that poem is polished art, but there's something interesting to it, and it has certain turns of phrase, certain metaphors, that really resonate. In particular, I liked: "I paint with words the colors I have learned; Yet cannot feel the hues, for which I've yearned." I think part of what makes this poem interesting is that you provided it something interesting to talk about.

With 5k views and 14k subscribers, imagine that

Wrote a similar request for ChatGTP. Not terrible, and it came up with one line I quite liked, concluding a verse on whether it was conscious with “Or am I mere scripts adrift?”. Being a developer I know the feeling. Just tried Bing GPT4 asking it to write the poem about itself in free verse. Nowhere near, 4 lines per verse, very specific metre, and rhyming every lines 1/2 and 3/4.

@@marcevanstein It might have been more polished if the prompt had specified "precisely metered iambic tetrameter," but I think that it was more important to leave the form open, so that GPT-4 would focus more on content. All in all, I think he did a commendable job, better than many human poets. Well done, GPT-4!

I enjoyed that poem and contemplated how its apparent thoughts on the subject can be created without a consciousness. It hurt my brain trying! I agree with Marc that you gave it a good prompt.

Music is mathematics. It don’t need to hear music. It analyzed thousands of music compositions and it can put something together based on those pieces. But it will take a looong time until it will get what makes a good composition good.

@@handznetyes music is maths for a part but not ENTIRELY math. Writing and playing music is largely an emotional process. The feeling you get when hearing a note, a chord, the instrumentation, AI cant sense any of that. That's why it struggled

@@Mr.Engine993the effect of music is emotional and humans who write music generally use their knowledge of the emotional effect it will have to guide them, but there is still a mathematical function that translates the sounds to the emotional response a human brain will have to it. Of course, the function is unique for every single individual person ever and also changes for every person based on every factor you can think of that can marginally effect how a person feels and then some, plus the structure of all parts of their auditory sensing systems, and the variations between people are even greater between different cultures. Nevertheless, there is enough consistency to use math to tell how music will generally make people feel, because if there wasn’t then there wouldn’t be such a thing as music theory. Translating this function to purely mathematical terms and optimizing it to be as effective as possible is, as you can imagine, a very complicated process, but things that are too complicated for humans to understand every part of what’s going on are what the whole point of AI is, and AI specifically made for the purpose of making music demonstrates this pretty well. I don’t actually know what the exact state of musical AI is right now, but I know some of it is at least human-composer-who-knows-what-they-are-doing-passable for classical composition, though it’s possible everything I’ve heard of it is either falsifications or a case of AI just copying things from its set of samples without making any meaningful change. The fun part is that the hypothetical music-to-emotion mathematical function is definitely a thing that exists, because emotion comes directly from the human brain and sensory-nervous system, and the human brain and sensory-nervous system are physical objects/systems and thus can be represented as individual particles that follow the laws of physics, which can be directly translated to a really really really really really really really really really really big mathematical function, and that function can almost be definitively be simplified to remove at least size of those ‘really’s while still predicting emotion from stimuli consistently enough that the range or error is too small to be meaningful, and I think that’s neat.

Without a doubt. I mean look at the more pop orientated ones. It's pretty impressive what they can create. People were also pretty biased and unfair with the Bach chorale one. It was certainly lacking, but the comparison videos I saw used some of the most well known chorales to test the ai against in a supposed blind test. It would be much more interesting to pick theol more obscure chorales.

There already are specialized AIs that learn from classical compositions, the results are pretty amazing actually. The problem with ChatGPT is it's a generalized AI that learned from a huge variety of content, very little of which is actually music (and even less of it is well written and clearly annotated music). As a computer scientist who has always worked near the field of AI for two decades I can tell you that what ChatGPT is doing now is nothing short of miracle. If you time traveled to 20 years ago and demo'ed ChatGPT to an AI scientist then they'd completely freak out and lose their mind.

Honestly, after looking at Stablediffusion and its family (NovelAI, ChilloutMix, etc.), the only thing other than general utility that's stopping people from developing Music AI is the fact that it can't generate high quality pron on demand.

@@zxbc1 I work with LLMs basically everyday and I still routinely lose my mind. It's a pretty interesting time to be alive. I just wish that all reporting on ChatGPT was as solid as this one. It's sad to see how many videos there are of people who don't know what they're talking about throwing shade at something they don't understand. Like... Hallucinations are never a problem if you're wrapping your prompts correctly, but I still see new videos and articles claiming that they're one of chatGPT's big downfalls, despite the fact that it's all but solved for any real world implementation.

@@kenanderson3954 yeah, I kinda agree. They’re basically saying it should do what they mean it to do, not what they will it to do, falling to recognise a) their own deficiencies in communication and b) that these communication issues are abundant in the real world, with very real problems as a result. Just look at the MCAS system on the 737 max, it did exactly what they told it to do, but not what they actually wanted it to do, because they assumed the developers in India would know to put in failsafes and checks in their code, and they didn’t. If it can happen in the biggest project to come out of the worlds biggest and most established engineering firm in the world, why people think it’s not going to happen between them and the first public release of a language model is beyond me. It’s like expecting your developers to write code that works exactly as you want first time every time you give them a requirement you’ve quickly typed out on an email, it’s never going to happen.

It's like it's automatically testing itself, called something like auto GTP!

The specific name for what you're suggesting is a generative adversarial network This is how A.I is already trained, usually. I don't know the specific methods GPT is using. The concept of competing agents is a well established idea. One of the ways of doing it is making a genetic algorithm. You create a batch of the a.i, and choose whichever one works best, use it's weights and biases as a base to create a new batch of new versions, which are all slightly modified. There are also ones where you have the optimization algorithm be more direct with how it judges the a.i, but I don't understand it enough to explain it.

Great way to make it hallucinate a music system

Just ask the chatbot to simulate a pair of agents doing these things?

Read that as "call each other tools." An integral part of collaborative music creation.

Was my thought as well. Without any constraints provided at the beginning I wasn't thinking blocks in the real world.

Same, and a purple block

I was thinking oh you need to put a green block above the blue one and a purple blocl below so that it can snake as a rainbow lmao

@@ChespinCraft EXACTLY i was tryna figure out where to put the green block 👍

Omg same

I think this is an unfair simplification. GPT 4 spiting out items (words or notes) one at a time does not necessarily effect how each item is generated in the context of the final idea. The AI must adapt its response model based on past inputs, the direction the phrase is going, and related information from a knowledge base. There's also degree of AI randomness thrown in as well. Prediction is used once all the information is considered appropriately based on their algorithms, so the final response is most likely less linear in construction than you may think. It's more accurate to say it fragments and mashes musical ideas together under common techniques rather than simply deciding what note works best next. I'm saying all of this based on prior familiarity with AI. Of course, I could be totally off base, but it's def not that reductive. ChatGPT definitely sucks at music though given the current algo

I agree with Kyle Darian. It doesn't think word by word, but rather fragment by fragment. As shown in the video, the AI was able to effectively create decent sounding fragments, and it was able to identify the characteristics of the fragments (likely by analyzing the key and tempo), however it could not comprehend rhythm very well. In its compositions, it has one fragment, and then another fragment that matches the mood of the first phrase, but not the rhythm. Basically, every time it was making a composition, it was generating a bunch of different fragment, and then strung them together. A simpler explanation: GPT 4 generates fragments instead of notes. With the prompt "Generate a happy melody," it will generate like 3 major-scale fragments (which we will call A, B, and C). Then, it will randomly distribute these fragments: C A B. Finally, just for fun, it will add one of the fragments twice: C A B C. What it doesn't take into account is that one of these fragments might be written for a different time signature, or might use a different rhythmic sequence. However, it takes the mood and scale of each of these fragments into account.

I submit to you that that is how all thinking works, just some of it is much faster at pulling the reference from a much larger library than others, like our minds generally speaking.

This is how humans write too, but usually humans don't show off their very first draft; the AI has to make the whole song with just one shot, without any revision.

@@JokeDeity2 In music, you're actually supposed to take in multiple notes at once, rather than one.

Having used GPT4 a lot for my programming job, I can say you're completely wrong about it not asking or knowing what to ask for. If you tell it "I got this error with this trace. Help me diagnose the problem and ask me about anything you think will help", it will, indeed, prompt YOU with relevant questions. It doesn't do this by default largely because the RHLF used to make it more chat-bot like rewarded *any answer* over *no answer*, even when no answer (with caviats) may be better. This makes it quite sycophantic and it also makes it give broad, vague answers if you aren't more specific about what you want.

​@@XetXetable The one thing I've noticed as key to its performance is how well articulated are the prompts. The better you ask questions the better it answers them.

> It doesn't even know what a human is, let alone that it or even you exist in the first place. I emphatically disagree with this. It has an incredibly rich and complex internal model of the world that it has learned from its input data. We also don't *directly* experience the world, we collect sensory input data and use it to build a model of the world that makes sense. Beyond sensory models of the world, we also create models of the world from things that we can't even experience directly and treat them as real without even knowing the difference (have you ever *seen* an electron?). Neither humans nor AI live in a world of platonic forms directly experienced; we both experience reality as a model.

​@@JH-ty2cs I think there is an inherient difference between the model AI's and Human's use to experience reality. ChatGPT's model is solely a model based on language, based on the connections between words and what they mean. The model takes in an input of characters and responds with an output of characters. There is no understanding of what those words and characters mean, the AI (in an extremely complicated way) chooses words and characters to output that strongly connect to the words and characters input. Their model of reality is entirely and 100% limited to words. However, the Human's model of reality is much more complex. Although there is a comparison that can be drawn between the way Humans and AIs "input and output words," the model the Human uses to come up with those words goes far beyond just a model of language. Humans, similar to AI, can generate words using their model of language, but they also are able to relate those words to concepts of other models of understanding, such as logic or our physical understanding of reality. (see diagram at 1:15 in the video) Humans deeply understand the meanings of the words that pass through the language model through our capability to model reality with more than just words. Because all text the AI was trained was generate by humans who have this complex model of reality, the AI's language model has learned to attempt to 'fake' these other models of reality solely through its connections between words in the language model. The AI language model has no understanding of the meaning of the words it generates, because for human's the meaning of words is rooted in our models of reality beyond just language. Taking a quote from the AI generated poem in the pinned comment, an AI can "paint with words the colors [ it ] have learned, Yet cannot feel the hues, for which [ it's ] yearned." Similar to how a blind person can have an understanding of what colors may mean yet will not ever understand the colorful blueness of blue, an AI language model can suggest that it understands the words it generates without true understanding of the other models of reality that it simulates. This view of modern AI begs some questions about the future of AI; is an AI language model eventually going to be able to simulate our other human models of reality solely through an AI language model (going beyond its current method of faking it)? Is there a way for humans to tell whether an AI has successfully simulated these other models of reality, or if it is just doing a significantly better job of faking it? (is there even a difference between those two scenarios?) And hypothetically, if a language model somehow provably simulated the human model of reality, is that AI a close enough simulation of human consciousness for there to not be a meaningful enough difference between the two?

@@MiningPie_ I don't think theres a meaningful difference between "fake knowledge" and "actual knowledge". We experience the blueness of blue so vividly because our eyes are first-class sensors hooked up to our brains and we get bombarded with input every second of our lives. If you feed GPT enough data it'll reach the same level of understanding.

@fatrio_4producing 🇦🇱 …just wait for GPT 7!

...just wait for GPT 8!

.....just wait for GPT 99.5

...just wait for GPT 1 Million!

Wait for a gpt robot

Fascinating! Good catch. I tried it as well and can confirm that you are right.

I even gave ChatGPT 3.5 an example like the following: "The letter B directly follows the vowel A in the English alphabet, tell me the respective letter for every other vowel in the English alphabet" and it got it right with that too.

That's some 130IQ prompting right there.

if counterpoint were what matters then humans trained in tonal counterpoint would be far more successful than they are. the most successful musicians nowadays are usually self-taught and know limited theory. when you can't teach the concept to an AI there's only so much to do. art doesn't rely on feedbacking between feeling and creating more, seeing how that feels, and then extending it until you have a full song

@@Farvadude That's a completely different discussion? Being successful doesn't mean that you do things that matter and inversely doing things that matter doesn't mean you are 'successful' in the visible sense. So I'm not sure what that has to do with anything. W.r.t tonal counterpoint, it is a specific perspective on music that results in a specific soundworld. AI could maybe express itself in that language (I think it's definitely possible), and that might be fun and useful for creating music if you like that sound. I'm not sure what you are reading in my reply beyond that. I'm not saying language models can create meaningful music (although surely they could in principle create something we can't distinguish from such music). Neither am I saying that tonal counterpoint is special or needed for 'good music' in any way. (Although I personally really enjoy it.)

Actually, there's a very specific technical reason that the GPTs are all very bad at character-counting, rhyming, alliteration, arithmetic, or really *anything* that depends on the specific characters in the input: *they literally can't perceive them!*. The way input is fed into GPT, it's encoded through something called Byte-Pair Encoding, which chunks up the input into kinda arbitrary chunks of characters that frequently occur together, like a simple compression algorithm. It never actually sees the individual characters! This means it has a huge handicap for anything that's totally obvious just looking at the actual letters, because it has to learn on its own how to undo the BPE encoding without ever even knowing that "letters" exist. ( This is also a huge problem for arithmetic - it's *way harder* to realize arithmetic has consistent rules when "122" might be encoded as [12][2] but "123" might be the single token [123].)

@@Nerdule This is good information, Stephen Wolfram actually explained this in some video. Your explanation is better. Wolfram Alpha is different kind of AI system that can see those individual characters, and I've actually had good results using both GPT-4 and Wolfram Alpha in tandem. LLM is just wrong tool for the job. It actually looks probable that some AGI-like system is probable even in near future, but it will be a network of different AI systems, memory management, filters and whatever, maybe even duplicate AI's like more than one LLM. It will probably be computationally heavy system at first.

@@Nerdule What if you say "one two two" or "one two three" ? Or "one hundred twenty two" etc.?

we should not teach it music theory so far

I'd wager it has music theory in its corpus and you just need to explicitly give it reference in the prompt to use it.

@@emanuel_soundtrack yeah agreed honestly. This AI stuff is cool and all but I want human art to prevail forever. Even when AI becomes good enough to produce indistinguishable results, i think we should simply choose to restrict art to humans on purpose so human artists may continue expressing themselves and getting a living from it

I think it has music theory texts in its corpus and it also has various textual representations of actual pieces of music. But that doesn't mean that it can apply this knowledge in ways comparable to a skilled human. It definitely has improved beyond my skills in writing music though, as a person who doesn't have skills or training in this area. I don't know whether a theoretical GPT-5 would go past actual composers' abilities or not. I don't think it would though.

@@evandonovan9239 I've been surprised what Bing Chat can do for following directions in writing game code for a unique game of my invention for following directions written in plain English. I don't know exactly what mixture of emotions we should have regarding GPT-5 arriving. After all, best information I have is writing poetry is an emergent ability, and I've had Bing Chat (has GPT-4 chat I think, wrapped) create more than 16-part lyrics, and stories in the lyrics, where I didn't tell it too many details and it came up with logical roles. I see it as more than word autocomplete and more as thought autocomplete, where the thoughts can be rather large and complex, limited by context constraints.

Actually I wouldn't pass off a completely unrelated chord progression. If you've taken a music theory class and either not been immediately adept or watched other students not be immediately adept, if you were to ask them to explain the chord progression to some arbitrary music you gave them, they might simply give a nonsense answer based on a series of compounding errors (though some might sooner ask for help), which is completely understandable. The wierd part is that telling a human to stick to a chord progression (as per the prompt) will make them engage with what they're doing, learn their own shortcomings in knowledge, and ultimately return fewer mistakes. This is perhaps simply not how GPT works. Whether a hypothetical GPT-5 could find within itself to operate in such a way is an interesting question. You'd think an inordinate number of parameters would be enough to emulate any alternative model within itself, but I suspect our models don't train in a way that's flexible or complex enough to engage with model emulation, and we either need to make models with diverse subsystems (thus requiring no emulation to excel at the given tasks) or some other framework which lends itself to emulation. I think the former is eminently achievable if adequate training can be served; but an AI using a framework offering run-time emulation (distinct from training-time emulation: that the training imparts the parameter changes to create an inner model, which is then set-in-stone when deployed) would be most undeniably an AGI (given the proper training and size), sentient/creative/human-like or not.

You realize that most humans in the world if you ask them the same thing they will give you a stare look, right?

I think it's like an infant prodigy. It's hugely talented but isn't even toilet trained yet.

@@falazarte Yeah, that's why I figured the BS chord progression was a bit odd. In some situations people do BS instead of just not answering, though, like on tests. That's why one of my math professors said he thought they did a good job making GPT very human: It does exactly what his students do - writes the answer when it knows it, and writes some BS full of buzzwords that sounds like a correct answer to people who don't know when it doesn't know the answer.

that's a very good point

If Gpts knowledge in other topics is as bad as this in music, you should stop asking it about other stuff :D

prompt: "Please act like AutoGPT. Please act like one agent set up as a composer, and another as an editor/reviewer. Please write a 4-part choral piece, using this method: Write a few ideas/themes, try to puzzle them together, and make at least a dozen revisions while continuously reflecting on what you've achieved so far."

we're just fine at asking questions. we're not good at creating AI that understands them.

The official training set isn't public, but earlier models are known to have been trained on The Pile which contains some 2 million+ pirated books. That would include the vast majority of digitized books on music. You can ask GPT4 about music theory, and it knows a lot. You could use those terms when prompting, and it will often respond in reasonable ways demonstrating some level of understanding of the concepts. But the real limitation is that GPT4 has no hearing; it doesn't actually know what the music would sound like; the only artistry it knows is that in the composition itself, not in any hypothetical performance.

@@XetXetable There are also a huge number of music tutorials online of all different types, at a wide range of theoretical detail. It would have scraped many of these in it's training.

the model is trained on this, but, if the model had a larger token window (a larger Temporary memory so it could remember more things you told it over One session), then you could copy and paste whole books into the text box and it would read and understand them, and produce results from data within them.

@@bilbo_gamers6417 Maybe memory GPT will make this happen?

Problem is however that many, if not most music theory books are 50% pseudo-theory built upon baseless ideas.

I am sorry for you!

@@daydays12 thanks 🙂

@@daydays12 for some reason your latest reply doesn't show up here, but no offense taken - I'm not a composer yet, but I may give it a go at some point in the future and see if there is any hope for me 🙂

Well, and without having a brain, either. Most people forget GPT doesn't "understand" anything because it only processes language. It is not a brain. It is not understanding at all.

​@@trence honestly i feel like that's debatable. im not an expert at all but i have some decent csc knowledge and have been following the technology. i feel like, at a certain point, if it looks like a duck and quacks like a duck, then it is a duck. this model can produce music that is decent and take criticism and redo it. it makes mistakes but that's because it uses a statistical model. human beings also think and reason in terms of words, so at a certain point what more qualifications do you need before you say that the AI understands something?

Note that GPT-4 was actually trained on images as well as text, so it does has “eyes” so to speak. Just that OpenAI hasn’t opened up image input to the public just yet.

@@trence It does have a brain - it's a neural network. Neural networks were _created_ to mirror how the human brain works, with some abstraction (weights, for instance, abstract the fact that signals along the axons in animal brains aren't binary 1 or 0). I don't think anyone familiar with ML would argue that language models don't have any 'understanding' - the debate is as to how far it understands. To say a large language model doesn't understand grammar, for instance, is preposterous - of course it does. It knows what to put where, and when.

@@bilbo_gamers6417 The fact that, if asked to provide their 'reasoning' or 'thought process' for a response they gave (don't try this in ChatGPT - they've definitely filtered this out as they don't want people asking these questions, you instead find things published by the people dealing with unfiltered versions of these models which show this), they provide something akin to how a human would respond is enough for me to believe that they can reason. Doesn't providing a proper response to that necessitate knowing how to reason? Since to me that's obviously the case, it's irrelevant as to whether it did reason when it gave the response or only reasoned retroactively when prompted, since when _asked_ to reason it _can_ do so. If it isn't reasoning all the time, it's at least clear it's capable.

“Programs that just read a lot of stuff (Chat GPT) can't write credible music. Programs that study music CAN.” I couldn’t tell if the music output portion of the video was “Well, let’s see what happens when we ask a language model that _isn’t_ trained on music to produce music”-which isn’t all that interesting when the result is predictably banal-or “Are GPT-4’s ‘reasoning abilities’ ‘developed’ enough that it can produce some version of ‘acceptable’ music?”-which strikes me as a bit bizarre because of its implicit assumptions. These LLMs have no reasoning abilities; their only capability is to output plausible-sounding (if not factually correct) verbal output (or, in the music case, verbal output that can be translated into notes) based on statistics and pure linear algebra. It’s good to know that there are programs that can produce music and, as you say, “stunning music” at that (and, apparently, they’re not “reasoning” in order to do that).

@@jeff__w Statistical-modeling programs need feature sets of what it is they are trying to model, and they can examine and make statistical predictions based upon the features found in the training corpus. When the feature-set includes credible musical concepts, such as human teachers teach composition students, credible output results. The music produced in this video (the chorales specifically) are not banal or boring; they are asyntactic gibberish. Banal chorales would be a great step up. Again, seek out Cope's work.

I tried it, it works way better than asking it to write actual music. It understand the rythms and syllables, structure

Makes for good videos haha

One word: money. If companies can replace human labor (scriptwriting, audio production, graphic design, etc) with an acceptable substitute, one that works significantly faster AND doesn't have to be paid nor provided benefits, then by god they will. I'm already seeing news articles with AI generated images as their headline art. That is, articles that *aren't about AI*, just regular miscellaneous topics. Because it's cheaper than hiring an artist to do the same thing!

Mass unemployment ?

Marc said he tried to do that in one of the comments, but it didn't work nearly as well.