But can China's new AI write a Good Melody?

[@imveryangryitsnotbutter]

It should be said that the main innovation of DeepSeek is not to improve on output, but rather to drastically reduce the required hardware needed to output something in the same ballpark as current AI models. It sacrifices a little bit of quality in exchange for being more affordable, more accessible to non-profit organizations, universities, research institutes, and having less negative impact on the environment. That's a trade-off I'll gladly accept any day.

[@marcevanstein]

to be sure! I mean, I've been so ambivalent about AI, because I find it really fascinating, and often times super helpful, but I really hate the resource hungry, closed, and amoral way in which it's being developed.

[@everythingisterrible8862]

It's not really very practical, getting only a few tokens generated a second. Consumer grade hardware isn't there. And it won't be there until NPU's, hardware that's the actual network in physical form, become the standard. It's a real post-AGI thing: You need a network to put on these things before they're able to do anything. (And knowing how gods-expensive it would currently be to print a human-scale 'brain' in a small form factor, it only makes sense to have a guarantee before dumping a trillion buckeroos on completely new computing paradigm foundaries.) Honestly IBM feels like the 'biggest loser' of the AI wars; they used to advertise this kind of thing back in the day, but there was little interest since you couldn't do anything that practical with them. DeepSeek is a fun model for enthusiasts. It's a candle in the wind compared to what will be made with the upcoming round of scaling in datacenters.

[@valhatan3907]

Finally someone made a point about the environment

[@Yarxk-j7w]

chatgpt 4o has around 1.8 trillion parameters which is 3x larger than deepseek r1, and chatgpt o1 has probably the same or larger size. If the performance difference is less than 10-20%, it is consider extremely efficient.

[@shadmium]

i always found the deepthink button hilarious

[@baldeagle6531]

You are saying 'always' like you had access to it 3 weeks ago. Also what's the problem with deepthink button? If it was useless, than CGPT wouldn't have added the same feature. In fact, deepseek has a far more structurally and logically correct responses in its thoughts and then it makes conclusions of them, which are sometimes wrong, even if the thoughts were correct.

[@abhishekak9619]

​@@baldeagle6531the name sounds funny.

[@Akuma.73]

@@baldeagle6531 Actually few months already. It's been available since the end of December. It was a V3 model though.

[@johnchessant3012]

8:09 "cher ami, you grasp the storm but forget the poetry. quartal harmonies need not be barbaric- make them sing. where is the rubato? the bass crawls where it should dance. and this ending- mon dieu, it stops rather than dissolves!" LOL

[@coltzhao]

Typical Chinese online talks… translated in English. One of the thing I noticed with fluent in both languages is that, DS can be wildly spit out weirdly and some time cynical/humorous even brutally insulting word, like the people in tieba arguing online . That also why I am not really buying the instillation thing.

[@ThisAMJ]

​@@coltzhao translated *into* English. One of the *things* you noticed *being* fluent in both languages. The rest of your comment is somewhat difficult to follow. DS can randomly spit out weird and sometimes cynical/humorous phrases, even brutal insults. *That's* also why I don't really buy the claims about its training.

[@coltzhao]

@ if you ever argue and talk on various Chinese online platform you know, the style is remarkably similar to deepseek sometime, and I never saw such mood/style in ChatGPT.

[@questtech2698]

"can a robot write a symphony?" "yes I can, can you?" from the director and producer of I, robot We, robots on theatres soon

[@hundvd_7]

This is dumb. I know we are already abusing chatbots for something they were not even designed to do, but the biggest issue here is having a _single_ conversation with each. Sometimes both Chet Jippity and DeepSeek just start off on the wrong foot. Like, you'd ask "what's 1 + 1" and _most_ of the time they answer 2, but sometimes it's wrong. Which is what I feel happened to _both_ of them here-but especially DeepSeek. And the important thing is, you _need_ to start a new conversation if the very first answer it gave was totally, catastrophically bad. I believe the logic behind it is that if the AI looks at the history of the conversation, and sees that it was dumb and had to be corrected or reprimanded, then it will _keep_ playing that role as that is statistically way more likely to happen than the "person" suddenly becoming a genius. *My suggestion,* if you're gonna make another such video in the future: - try at least 3 (preferably 5) conversations each, sending them the exact same message - play them all and quickly compare them, choosing only the best ones of each AI - continue the rest of the video as you would

[@michaelvarney.]

I broke R1 last with a question about modes and using Nashville numbers and Roman numeral analysis… it recursively puked for 5 min and invented/hallucinated five additional letter classes for the Nashville number system… 😅

[@TheGuyWhoGamesAlot1]

You should try Gemini models. They are technically multi-modal (understand multiple modalities such as text, images/video, and audio). I wonder if that audio understanding would help.

[@sarakzite6946]

Ive got two ideas that I can’t make myself because im very big noob in AI RL DL etc… 1) an ai coach for piano, that would help a student measure by measure, maybe an LLM that can read sheet music. 2) a fine tuned model that can create sheet, kinda like you did. I think it’s only a matter of months/years until someone does it, the second is probably already done. Thank you for your vid as usual, id love to see more ai music content ❤

[@Akuma.73]

7:30 Keep the prompt concise. Avoid words such as: Try, Oh, Please, Can you, Would you, Could you. Instead use a direct language, be dominant with the model, it tends to produce better results. Here is a better version: Write a fast, dramatic miniature Chopin-style prelude, featuring quartal harmony instead of triadic harmony. Incorporate aspects of Chopin's writing, reduce superficial elements. Decide the key (except C) and the time signature. And give me a list of beats on which to change pedal. From DeepSeek R1 paper: Prompting Engineering: When evaluating DeepSeek-R1, we observe that it is sensitive to prompts. Few-shot prompting consistently degrades its performance. Therefore, we recommend users directly describe the problem and specify the output format using a zero-shot setting for optimal results. It's better to start new chats rather than continue existing ones and keeping the prompt as direct as possible. Just FYI, I hope it was helpful! Happy seeking :)

[@RengokuGS]

That Image to music video was genius and I'd love a copy to that repo. Soooo good! Edit: Is it on the Patreon?

[@vladthemagnificent9052]

I'm afraid real Chopin would just have a stroke. I agree, it's 'kinda interesting'

[@HillHand]

If you use the Spellbook module for VCV Rack, t's got a CSV-like text based sequencing format called 'RhythML' which is easy to explain to these models and copy & paste like code snippets, so you don't have to worry about converting into MIDI or something.

[@nahlene1973]

you should've turned on the Deepthink button from the first prompt, as they are calling for different model (it's like you started from gpt4o then let gpto1 to pickup the previous jobs)

[@TommyGreenTeas]

Ahh now i hear moonlight in the storm! 👆🙂‍↔️☝️ C’est presque bien

[@grindx1292]

Hey Marc, I find the video slightly biased toward ChatGPT, for the fact of your consistency with using their o1 model. This differs from your fluctuations of use between DeepThink (deepseek r1) and non Deepthink (deepseek v3, vastly inferior to ChatGPT o1). Redoing this experiment with consistency among models will net greater results on Deepseek's end, no doubt.

[@TheJunky228]

I've tried getting llms to write melodies and play chords since I first ran them locally

[@poptropical3170]

9:30 giving me Legend of Zelda vibes

[@JestroGameDev]

The Chopin remixes (especially both revisions) sound like the active phase of Gohdan from Wind Waker

[@eldrago19]

It's a Chopin polonaise, I tell you! On a more serious note, this was very interesting, perhaps a reflection on DeepSeek's less structured training. Obviously if you wanted AI written music, repurposing a large language model is a roundabout way of achieving that. I think the intro music was by OpenAI and the outro was by DeepSeek as the intro felt more structured.

[@BBarNavi]

its melody: MEIYOU GONGCHANDANG JIU MEIYOU XIN ZHONGGUO

[@eti313]

Amazing how it wrote better music than Chopin without any human interaction-just the press of a button.

[@JestroGameDev]

Eh, I wouldn’t say better. Chopin had some pretty amazing stuff

[@thatguyalex2835]

I guess we can say the OpenAI is now on the Chopin block when Deepseek wrote a great melody. :)

[@GigaminxSolver33017]

Marc Evanstein i love your tic tac toe videos.

[@qandrshow-m7k]

don't we all

[@duddex]

Sia++ 😂 That’s great. How do you come up with these names?

[@marcevanstein]

Oh that's some honest to goodness human dad joke cringe. I do it myself :-)

[@luminousherbs]

you should’ve written your music-making program in C#

[@thatguyalex2835]

Welcome to the future, where open source AI can critique itself. :) Also, what brand is your shirt? The blue/gray looks good on you, bro.

[@IlstrawberrySeed]

Technically speaking, the o models are's chatGPT models, but a different line of "products."

[@mrCheeeseGuy]

i honestly thought it was going to write red sun in the sky🤣

[@maayansagman5771]

Cool vid, but why did deepseek think Copin was Fr*nch?

[@andybaldman]

These are all little more than random notes, which YOU are adding meaning to.

[@Draconic404]

This is like using a wrench as a hammer. This makes for a funny video, but if someone is seriously attempting to make a melody with ai, please use ai made for that and not chatbots

[@carljohanson3895]

Yeah idk who is going "oh no the reasoning model that was never stated to be made for making melodies can't create good sounding music" like what?

[@marcevanstein]

obviously I know that there are more dedicated music AI systems, but I actually still think that this is a really interesting kind of test. like, it's almost because this isn't what it was built to do that to me it gives me more insight about what these models are capable of. the last time I made one of these videos, the problems of getting the wrong number of notes in a measure, or lacking a larger sense of structure, we're really acute. but something about the metacognition, the "deep think" process has allowed the chat Bots to

[@zemlidrakona2915]

So ChatGPT writes better shitty music than Deepseek.

[@darkbrumoment]

deepthink is incredible lol

[@dariolapoma]

8:44...Smorz.

[@TJCyan]

hi

[@gabrielsandstedt]

OpenAI released the O3 model yesterday, it should be a lot better

[@hiranpeiris877]

RT

[@Mintymondos]

I was asking it about the CCP and then abt the anti government protests and it said that those aren’t happening and a majority of china support the ccp

[@JeffreyHow]

The populous support ratio for their government is much higher than here, that is a fact.

[@GoodBaleadaMusic]

Ask it about yesterdays US invasion of the Congo

[@imveryangryitsnotbutter]

Unfortunately the online version of the model self-censors. The engineers basically had to do this in order to avoid bringing the wrath of the CCP down on them. Luckily, if you download the source code, the model answers questions about the Chinese government honestly.

[@GoodBaleadaMusic]

@@imveryangryitsnotbutter Ask Chat GTP why the US military invaded the congo this week. You won't but others reading this look at the desperation in the westerner these days. They are so scared. Of the revenge coming.