Re: Anybody else playing with GPT4 and Lilypond?
This is nothing to do with GPT4, or guitars, so might be considered off-topic :) , but I'm aware of this paper due to Percival et al., which addresses sight-reading exercise generation: https://www.researchgate.net/publication/235925970_Generating_Targeted_Rhythmic_Exercises_for_Music_Students_with_Constraint_Satisfaction_Programming On 30/03/2023 05:57, Mike Blackstock wrote: re. "Anybody else playing with GPT4 and Lilypond?" I'm very much interestedin exploring its use to generate graded sight-reading material. My own instrument is classical guitar and we're not the best sight-readers[1]... it would be nice to have daily sight-reading exercises generated for practice, with midi. I could donate the use of a QEMU/KVM server instance for working on a project of that sort. [1] Guitarist John Williams: "Another thing I’ve noticed in master classes, is that players will come on and play the most difficult solo works from memory, and yet if you give them a part to play in one of the easier Haydn String Quartets, as I often do, they’re lost in no time, and have a very poor sense of ensemble or timing. Guitarists are among the worst sight-readers I’ve come across. Julian Bream and I are both dead average sight-readers by orchestral standards, but among guitarists, we are [considered] outstanding! " https://guitarteacher.com.au/interview/john-williams-interview/ On Wed, 29 Mar 2023 at 18:44, Saul Tobin wrote: I've seen some examples of other people succeeding in getting ChatGPT with GPT4 to compose simple music in other text based music formats. I've had limited success getting it to output Lilypond code. It is able to correctly structure the code with a score block, nested contexts, and appropriately named variables, and bar checks at the end of each measure. It seems to struggle to create rhythms that fit within the time signature beyond extremely simple cases. It also seems to struggle a lot to understand what octave pitches will be in when using relative mode. It also seems to have a lot of trouble keeping track of the relationship between notes entered in different simultaneous expressions. Just asking it to repeat back which notes appear in each voice on each beat, GPT4 frequently gives stubbornly incorrect answers about the music it generated. This makes it very difficult to improve its output by giving feedback. I'm curious whether anybody else has tried playing with this. I have to imagine that GPT4 has the potential to produce higher quality Lilypond output, given some of the other impressive things it can do. Perhaps it needs to be provided with a large volume of musical repertoire in Lilypond format. -- https://blackstock.media
Re: Anybody else playing with GPT4 and Lilypond?
re. "Anybody else playing with GPT4 and Lilypond?" I'm very much interested in exploring its use to generate graded sight-reading material. My own instrument is classical guitar and we're not the best sight-readers[1]... it would be nice to have daily sight-reading exercises generated for practice, with midi. I could donate the use of a QEMU/KVM server instance for working on a project of that sort. [1] Guitarist John Williams: "Another thing I’ve noticed in master classes, is that players will come on and play the most difficult solo works from memory, and yet if you give them a part to play in one of the easier Haydn String Quartets, as I often do, they’re lost in no time, and have a very poor sense of ensemble or timing. Guitarists are among the worst sight-readers I’ve come across. Julian Bream and I are both dead average sight-readers by orchestral standards, but among guitarists, we are [considered] outstanding! " https://guitarteacher.com.au/interview/john-williams-interview/ On Wed, 29 Mar 2023 at 18:44, Saul Tobin wrote: > I've seen some examples of other people succeeding in getting ChatGPT with > GPT4 to compose simple music in other text based music formats. I've had > limited success getting it to output Lilypond code. It is able to correctly > structure the code with a score block, nested contexts, and appropriately > named variables, and bar checks at the end of each measure. It seems to > struggle to create rhythms that fit within the time signature beyond > extremely simple cases. It also seems to struggle a lot to understand what > octave pitches will be in when using relative mode. > > It also seems to have a lot of trouble keeping track of the relationship > between notes entered in different simultaneous expressions. Just asking it > to repeat back which notes appear in each voice on each beat, GPT4 > frequently gives stubbornly incorrect answers about the music it generated. > This makes it very difficult to improve its output by giving feedback. > > I'm curious whether anybody else has tried playing with this. I have to > imagine that GPT4 has the potential to produce higher quality Lilypond > output, given some of the other impressive things it can do. Perhaps it > needs to be provided with a large volume of musical repertoire in Lilypond > format. > -- https://blackstock.media
Re: Anybody else playing with GPT4 and Lilypond?
I use chat.openai.com quite a bit for LilyPond. It almost never gives a correct or directly useful answer, but often gives me ideas where I can continue with LilyPond docs to figure out a solution. It's definitely good at explaining how code fragments work if you paste them in. This is a very similar situation to another esoteric language I use, OpenSCAD. These languages don't benefit from anywhere near the amount of training data that's available for languages like C++ and Python. That should improve over time, but for now it's a crap-shoot. Incidentally, I found Bing (supposedly based on GPT-4) is much worse than chat.openai.com, despite its ability to look up info on the web, and often just says it can't find anything. Regards, Curt On 3/29/2023 3:43 PM, Saul Tobin wrote: I've seen some examples of other people succeeding in getting ChatGPT with GPT4 to compose simple music in other text based music formats. I've had limited success getting it to output Lilypond code. It is able to correctly structure the code with a score block, nested contexts, and appropriately named variables, and bar checks at the end of each measure. It seems to struggle to create rhythms that fit within the time signature beyond extremely simple cases. It also seems to struggle a lot to understand what octave pitches will be in when using relative mode. It also seems to have a lot of trouble keeping track of the relationship between notes entered in different simultaneous expressions. Just asking it to repeat back which notes appear in each voice on each beat, GPT4 frequently gives stubbornly incorrect answers about the music it generated. This makes it very difficult to improve its output by giving feedback. I'm curious whether anybody else has tried playing with this. I have to imagine that GPT4 has the potential to produce higher quality Lilypond output, given some of the other impressive things it can do. Perhaps it needs to be provided with a large volume of musical repertoire in Lilypond format.
Re: Anybody else playing with GPT4 and Lilypond?
Hi Saul, A practical follow up question: what is currently the largest repertoire of publicly available Lilypond scores? Ideally, something like the complete Bach chorales or Mozart piano sonatas. Mutopia? Kieren.
Re: Anybody else playing with GPT4 and Lilypond?
I'm currently using "ChatGPT Mar 14 Version." Ken On Wed, Mar 29, 2023 at 5:15 PM Saul Tobin wrote: > > A practical follow up question: what is currently the largest repertoire of > publicly available Lilypond scores? Ideally, something like the complete Bach > chorales or Mozart piano sonatas. > > On Wed, Mar 29, 2023 at 3:43 PM Saul Tobin wrote: >> >> I've seen some examples of other people succeeding in getting ChatGPT with >> GPT4 to compose simple music in other text based music formats. I've had >> limited success getting it to output Lilypond code. It is able to correctly >> structure the code with a score block, nested contexts, and appropriately >> named variables, and bar checks at the end of each measure. It seems to >> struggle to create rhythms that fit within the time signature beyond >> extremely simple cases. It also seems to struggle a lot to understand what >> octave pitches will be in when using relative mode. >> >> It also seems to have a lot of trouble keeping track of the relationship >> between notes entered in different simultaneous expressions. Just asking it >> to repeat back which notes appear in each voice on each beat, GPT4 >> frequently gives stubbornly incorrect answers about the music it generated. >> This makes it very difficult to improve its output by giving feedback. >> >> I'm curious whether anybody else has tried playing with this. I have to >> imagine that GPT4 has the potential to produce higher quality Lilypond >> output, given some of the other impressive things it can do. Perhaps it >> needs to be provided with a large volume of musical repertoire in Lilypond >> format.
Re: Anybody else playing with GPT4 and Lilypond?
A practical follow up question: what is currently the largest repertoire of publicly available Lilypond scores? Ideally, something like the complete Bach chorales or Mozart piano sonatas. On Wed, Mar 29, 2023 at 3:43 PM Saul Tobin wrote: > I've seen some examples of other people succeeding in getting ChatGPT with > GPT4 to compose simple music in other text based music formats. I've had > limited success getting it to output Lilypond code. It is able to correctly > structure the code with a score block, nested contexts, and appropriately > named variables, and bar checks at the end of each measure. It seems to > struggle to create rhythms that fit within the time signature beyond > extremely simple cases. It also seems to struggle a lot to understand what > octave pitches will be in when using relative mode. > > It also seems to have a lot of trouble keeping track of the relationship > between notes entered in different simultaneous expressions. Just asking it > to repeat back which notes appear in each voice on each beat, GPT4 > frequently gives stubbornly incorrect answers about the music it generated. > This makes it very difficult to improve its output by giving feedback. > > I'm curious whether anybody else has tried playing with this. I have to > imagine that GPT4 has the potential to produce higher quality Lilypond > output, given some of the other impressive things it can do. Perhaps it > needs to be provided with a large volume of musical repertoire in Lilypond > format. >
Re: Anybody else playing with GPT4 and Lilypond?
I think you may have that impression based on GPT3.5. GPT4 is already being
used to generate working non-trivial computer programs based only on a
brief text description.
On Wed, Mar 29, 2023 at 3:58 PM Alexandre Loomis
wrote:
> > given some of the other impressive things it can do
>
> I think that's been exaggerated. It's very good at generating
> plausible-sounding text responses to prompts, everything else looks
> cherry-picked.
>
> On Wed, Mar 29, 2023 at 3:54 PM Nate
> wrote:
>
>> Hah yes. It once said \begn{music} and i said "are you making this up?"
>> "I'm sorry, you're correct. The start tag should be \begin{lilypond}.
>>
>> Its super handy but you have to watch it. It can be a pathological liar.
>> I asked it how to do something on the Akai Mini Play and it said to use
>> this button On the upper left corner. when i asked for clarification
>> instead of admitting it was mistaken it said it was white and next to
>> another button. Twice it doubled down before admitting it was wrong.
>>
>> On Wed, Mar 29, 2023, 6:44 PM Saul Tobin
>> wrote:
>>
>>> I've seen some examples of other people succeeding in getting ChatGPT
>>> with GPT4 to compose simple music in other text based music formats. I've
>>> had limited success getting it to output Lilypond code. It is able to
>>> correctly structure the code with a score block, nested contexts, and
>>> appropriately named variables, and bar checks at the end of each measure.
>>> It seems to struggle to create rhythms that fit within the time signature
>>> beyond extremely simple cases. It also seems to struggle a lot to
>>> understand what octave pitches will be in when using relative mode.
>>>
>>> It also seems to have a lot of trouble keeping track of the relationship
>>> between notes entered in different simultaneous expressions. Just asking it
>>> to repeat back which notes appear in each voice on each beat, GPT4
>>> frequently gives stubbornly incorrect answers about the music it generated.
>>> This makes it very difficult to improve its output by giving feedback.
>>>
>>> I'm curious whether anybody else has tried playing with this. I have to
>>> imagine that GPT4 has the potential to produce higher quality Lilypond
>>> output, given some of the other impressive things it can do. Perhaps it
>>> needs to be provided with a large volume of musical repertoire in Lilypond
>>> format.
>>>
>>
Re: Anybody else playing with GPT4 and Lilypond?
For some real fun i asked it to generate code that a potential solution would be recursive (without suggesting a recursive solution). The first time I stumped it and it went off for two hours. I asked it again later and it camenback with an interative solution without getting stuck . But i found that amusing On Wed, Mar 29, 2023, 7:07 PM Kenneth Wolcott wrote: > HI Saul; > > I asked ChatGPT to write some ABC notation. The result was...'okay'. > > I then asked for a very simple arrangement of some children's tune > and it got very confused about relative pitches. Since the rhythm for > the piece of music I requested was so simple it didn't have a problem > generating the score. I argued with ChatGPT about relative pitches in > Lilypond, I told it to go back and read the manuals :-) I gave up > asking ChatGPT about generating Lilypond scores after that. > > Ken Wolcott > > On Wed, Mar 29, 2023 at 3:44 PM Saul Tobin > wrote: > > > > I've seen some examples of other people succeeding in getting ChatGPT > with GPT4 to compose simple music in other text based music formats. I've > had limited success getting it to output Lilypond code. It is able to > correctly structure the code with a score block, nested contexts, and > appropriately named variables, and bar checks at the end of each measure. > It seems to struggle to create rhythms that fit within the time signature > beyond extremely simple cases. It also seems to struggle a lot to > understand what octave pitches will be in when using relative mode. > > > > It also seems to have a lot of trouble keeping track of the relationship > between notes entered in different simultaneous expressions. Just asking it > to repeat back which notes appear in each voice on each beat, GPT4 > frequently gives stubbornly incorrect answers about the music it generated. > This makes it very difficult to improve its output by giving feedback. > > > > I'm curious whether anybody else has tried playing with this. I have to > imagine that GPT4 has the potential to produce higher quality Lilypond > output, given some of the other impressive things it can do. Perhaps it > needs to be provided with a large volume of musical repertoire in Lilypond > format. > >
Re: Anybody else playing with GPT4 and Lilypond?
Correction: I don't think I'm using ChatGPT4, I'm using https://chat.openai.com/chat. Ken On Wed, Mar 29, 2023 at 4:06 PM Kenneth Wolcott wrote: > > HI Saul; > > I asked ChatGPT to write some ABC notation. The result was...'okay'. > > I then asked for a very simple arrangement of some children's tune > and it got very confused about relative pitches. Since the rhythm for > the piece of music I requested was so simple it didn't have a problem > generating the score. I argued with ChatGPT about relative pitches in > Lilypond, I told it to go back and read the manuals :-) I gave up > asking ChatGPT about generating Lilypond scores after that. > > Ken Wolcott > > On Wed, Mar 29, 2023 at 3:44 PM Saul Tobin wrote: > > > > I've seen some examples of other people succeeding in getting ChatGPT with > > GPT4 to compose simple music in other text based music formats. I've had > > limited success getting it to output Lilypond code. It is able to correctly > > structure the code with a score block, nested contexts, and appropriately > > named variables, and bar checks at the end of each measure. It seems to > > struggle to create rhythms that fit within the time signature beyond > > extremely simple cases. It also seems to struggle a lot to understand what > > octave pitches will be in when using relative mode. > > > > It also seems to have a lot of trouble keeping track of the relationship > > between notes entered in different simultaneous expressions. Just asking it > > to repeat back which notes appear in each voice on each beat, GPT4 > > frequently gives stubbornly incorrect answers about the music it generated. > > This makes it very difficult to improve its output by giving feedback. > > > > I'm curious whether anybody else has tried playing with this. I have to > > imagine that GPT4 has the potential to produce higher quality Lilypond > > output, given some of the other impressive things it can do. Perhaps it > > needs to be provided with a large volume of musical repertoire in Lilypond > > format.
Re: Anybody else playing with GPT4 and Lilypond?
HI Saul; I asked ChatGPT to write some ABC notation. The result was...'okay'. I then asked for a very simple arrangement of some children's tune and it got very confused about relative pitches. Since the rhythm for the piece of music I requested was so simple it didn't have a problem generating the score. I argued with ChatGPT about relative pitches in Lilypond, I told it to go back and read the manuals :-) I gave up asking ChatGPT about generating Lilypond scores after that. Ken Wolcott On Wed, Mar 29, 2023 at 3:44 PM Saul Tobin wrote: > > I've seen some examples of other people succeeding in getting ChatGPT with > GPT4 to compose simple music in other text based music formats. I've had > limited success getting it to output Lilypond code. It is able to correctly > structure the code with a score block, nested contexts, and appropriately > named variables, and bar checks at the end of each measure. It seems to > struggle to create rhythms that fit within the time signature beyond > extremely simple cases. It also seems to struggle a lot to understand what > octave pitches will be in when using relative mode. > > It also seems to have a lot of trouble keeping track of the relationship > between notes entered in different simultaneous expressions. Just asking it > to repeat back which notes appear in each voice on each beat, GPT4 frequently > gives stubbornly incorrect answers about the music it generated. This makes > it very difficult to improve its output by giving feedback. > > I'm curious whether anybody else has tried playing with this. I have to > imagine that GPT4 has the potential to produce higher quality Lilypond > output, given some of the other impressive things it can do. Perhaps it needs > to be provided with a large volume of musical repertoire in Lilypond format.
Re: Anybody else playing with GPT4 and Lilypond?
> given some of the other impressive things it can do
I think that's been exaggerated. It's very good at generating
plausible-sounding text responses to prompts, everything else looks
cherry-picked.
On Wed, Mar 29, 2023 at 3:54 PM Nate wrote:
> Hah yes. It once said \begn{music} and i said "are you making this up?"
> "I'm sorry, you're correct. The start tag should be \begin{lilypond}.
>
> Its super handy but you have to watch it. It can be a pathological liar. I
> asked it how to do something on the Akai Mini Play and it said to use this
> button On the upper left corner. when i asked for clarification instead of
> admitting it was mistaken it said it was white and next to another button.
> Twice it doubled down before admitting it was wrong.
>
> On Wed, Mar 29, 2023, 6:44 PM Saul Tobin
> wrote:
>
>> I've seen some examples of other people succeeding in getting ChatGPT
>> with GPT4 to compose simple music in other text based music formats. I've
>> had limited success getting it to output Lilypond code. It is able to
>> correctly structure the code with a score block, nested contexts, and
>> appropriately named variables, and bar checks at the end of each measure.
>> It seems to struggle to create rhythms that fit within the time signature
>> beyond extremely simple cases. It also seems to struggle a lot to
>> understand what octave pitches will be in when using relative mode.
>>
>> It also seems to have a lot of trouble keeping track of the relationship
>> between notes entered in different simultaneous expressions. Just asking it
>> to repeat back which notes appear in each voice on each beat, GPT4
>> frequently gives stubbornly incorrect answers about the music it generated.
>> This makes it very difficult to improve its output by giving feedback.
>>
>> I'm curious whether anybody else has tried playing with this. I have to
>> imagine that GPT4 has the potential to produce higher quality Lilypond
>> output, given some of the other impressive things it can do. Perhaps it
>> needs to be provided with a large volume of musical repertoire in Lilypond
>> format.
>>
>
Re: Anybody else playing with GPT4 and Lilypond?
Hah yes. It once said \begn{music} and i said "are you making this up?"
"I'm sorry, you're correct. The start tag should be \begin{lilypond}.
Its super handy but you have to watch it. It can be a pathological liar. I
asked it how to do something on the Akai Mini Play and it said to use this
button On the upper left corner. when i asked for clarification instead of
admitting it was mistaken it said it was white and next to another button.
Twice it doubled down before admitting it was wrong.
On Wed, Mar 29, 2023, 6:44 PM Saul Tobin wrote:
> I've seen some examples of other people succeeding in getting ChatGPT with
> GPT4 to compose simple music in other text based music formats. I've had
> limited success getting it to output Lilypond code. It is able to correctly
> structure the code with a score block, nested contexts, and appropriately
> named variables, and bar checks at the end of each measure. It seems to
> struggle to create rhythms that fit within the time signature beyond
> extremely simple cases. It also seems to struggle a lot to understand what
> octave pitches will be in when using relative mode.
>
> It also seems to have a lot of trouble keeping track of the relationship
> between notes entered in different simultaneous expressions. Just asking it
> to repeat back which notes appear in each voice on each beat, GPT4
> frequently gives stubbornly incorrect answers about the music it generated.
> This makes it very difficult to improve its output by giving feedback.
>
> I'm curious whether anybody else has tried playing with this. I have to
> imagine that GPT4 has the potential to produce higher quality Lilypond
> output, given some of the other impressive things it can do. Perhaps it
> needs to be provided with a large volume of musical repertoire in Lilypond
> format.
>
