Jordi Pons

One friend: “The bass sound design is boring”.

Another friend: “The track feels like it’s missing something, you could take it in a different direction”.

AI remix made a track with a better sounding bass, with additional layers of intricate melodies and arpeggiators.

OK

I’m learning to produce music and regularly share my tracks with friends for feedback.

Now I use AI remixes as an additional source of feedback (that often aligns with my friends’ opinions).

The advantage is that you hear the feedback translated into specific musical examples.

Two unconventional uses of AI REMIXING for music production:

Toplining → Explore new melodic ideas when you’re stuck. Not everyone can afford a professional topliner.

Feedback → AI remixes can reveal what’s missing or overdone. Similar to sharing an unfinished track for notes.

i'll let my agent answer you in python

Gradio synths are the new VSTs

I cannot pronounce

claud clode
clod claud
cod claut
caud clod
cloud code

but you know what I mean.

Most parameter combinations in synthesizers sound like shit.

That flexibility is what makes new sounds possible.

But if we release a neural synthesizer and one prompt doesn’t sound as you expect, you’ll be mad at us.

So we’ll just keep the new neural synthesizers to ourselves.

ACE-Step 1.5 Explained The ACE-Step 1.5 paper can be confusing. Here are its main ideas.

The ACE-Step 1.5 paper can be confusing.

In this post I share are its main ideas: artintech.substack.com/p/ace-step-1...

1. DIFFUSION MODEL: supports multiple tasks.
2. LANGUAGE MODEL: reprompting & semantic tokens generation.
3. DATA PREPARATION: 27M songs.
4. OPEN WEIGHTS: supports LoRAs.

Dopamine hits now come from agents building useless apps instead of endless scrolling.

HeartMuLa Explained Does HeartMuLa outperform Suno in music generation?

HeartMuLa Explained

It is an open-source music model that claims to perform on par with Suno.

1. HeartCodec: low-rate audio tokens
2. HeartMuLa: autoregressive model
3. HeartTranscriptor: lyrics tokens
4. HeartCLAP: text & reference-audio tokens

artintech.substack.com/p/heartmula-...

Love that the AI music conversation is moving toward interactive music and fans-driven art.
- artintech.substack.com/p/interactiv...
- www.youtube.com/watch?v=U8dc...
- aiformusicworkshop.github.io
- www.universalmusic.com/universal-mu...

The future of AI music won’t shape itself. It’s up to us to imagine what it can become.

If its current state feels like ‘slop,’ consider creating something different yourself.

While this essay has focused on Interactive AI Music, I’m sure there’s still much more to discover.

AI music doesn’t have to be ‘slop’. It can be Interactive!

Over the break, I wrote a post defining Interactive AI Music, a term that brings together my favorite artistic projects in AI and music.

artintech.substack.com/p/interactiv...

On Shared Musical Agency Interviewing marts~ to learn about his story and artistic vision.

New written interview!

“On Shared Musical Agency”
with Martin Heinze (marts~)

artintech.substack.com/p/on-shared-...

AI art is criticized for feeling soulless, lacking relatability and human narrative.

But AI art does not need to be like that.

I strongly believe that AI can be used to create art that was previously impossible and that it will be equally appealing as previous art forms.

SAM Audio Explained Wouldn’t it be cool to separate any audio using a single model?

New post is out! This time, I go through Meta's new model for source separation.

"SAM Audio Explained"
artintech.substack.com/p/sam-audio-...

The key issue in AI art is agency. We need workflows that produce art that clearly feels like it’s from the artist.

The concept of interactive AI music is gaining traction.

Lately I’ve been meeting many AI musicians.

I enjoy that first day when I don’t yet grasp their artistic practice or fully follow what they say.

But as we interact, our language becomes similar. Especially in how we refer to concepts/ideas.

I’m not sure if that’s good or bad.

Yup, that's it.

AI should be used to create art in ways that are both ethical and compelling.

Ethics are important, but being compelling is just as important. If it isn’t, there’s little reason to use AI for artistic creation.

I would modulate that by saying that it's possible to create AI art that draws attention to its process, mechanics and biases - its artefacts and politics. But I think you probably agree with that already, there just aren't enough characters in posts to say it all in one.

I agree with that. That's why it's important to explain that other ideas exist.

Honestly, there are so many interesting ideas emerging. Yet, the mainstream narrative against AI is hiding the cool work of underground and experimental musicians. That's what we tried to cover in our "artistic trends" paper.

Or, if you want, can look into our research paper where we try to understand how musicians use AI to make music:
> arxiv.org/abs/2508.11694

Well, you can go and see any of the entries in the AI Song Contest, where there are very strict rules around the (ethical) tools that can be used:
> www.aisongcontest.com/all-particip...
> www.aisongcontest.com/join

I care because AI can be used to create truly original work, otherwise I’m not interested. I personally like its generative, interactive possibilities. It’s easy to dismiss AI, but using it ethically, thoughtfully and critically (while building nuanced narratives around it) is far more interesting.

Indeed, generative music is not new. For those interested I wrote this post: artintech.substack.com/p/generative...

Labour exploitation? You are assuming all generative AI artists train their models in a specific way. But most AI artists actually license trained data or use their own training data.

Repetition is a human invention.

Nature rarely repeats itself.

Yet, we play the same music and films over and over.

Generative art changes every time you experience it.

What if generative AI ends up feeling more NATURAL than the static media of today?