Jordi Pons
@jordiponsdotme.bsky.social
Music and artificial intelligence.
Researcher at Stability AI.
Musician at BRNRT Collective.
Previously at Dolby and Universitat Pompeu Fabra.
artintech.substack.com
www.jordipons.me
Researcher at Stability AI.
Musician at BRNRT Collective.
Previously at Dolby and Universitat Pompeu Fabra.
artintech.substack.com
www.jordipons.me
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.
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.
ACE-Step 1.5 Explained
The ACE-Step 1.5 paper can be confusing. Here are its main ideas.
artintech.substack.com
February 10, 2026 at 2:58 PM
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.
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.
February 10, 2026 at 10:39 AM
Dopamine hits now come from agents building useless apps instead of endless scrolling.
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-...
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-...
HeartMuLa Explained
Does HeartMuLa outperform Suno in music generation?
artintech.substack.com
February 3, 2026 at 1:31 PM
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-...
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...
- artintech.substack.com/p/interactiv...
- www.youtube.com/watch?v=U8dc...
- aiformusicworkshop.github.io
- www.universalmusic.com/universal-mu...
February 3, 2026 at 9:36 AM
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...
- 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.
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...
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...
January 15, 2026 at 11:37 AM
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.
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...
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...
January 13, 2026 at 3:00 PM
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...
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...
New written interview!
“On Shared Musical Agency”
with Martin Heinze (marts~)
artintech.substack.com/p/on-shared-...
“On Shared Musical Agency”
with Martin Heinze (marts~)
artintech.substack.com/p/on-shared-...
On Shared Musical Agency
Interviewing marts~ to learn about his story and artistic vision.
artintech.substack.com
December 29, 2025 at 3:09 PM
New written interview!
“On Shared Musical Agency”
with Martin Heinze (marts~)
artintech.substack.com/p/on-shared-...
“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.
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.
December 23, 2025 at 5:44 PM
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.
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.
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-...
"SAM Audio Explained"
artintech.substack.com/p/sam-audio-...
SAM Audio Explained
Wouldn’t it be cool to separate any audio using a single model?
artintech.substack.com
December 22, 2025 at 4:01 PM
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-...
"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.
December 16, 2025 at 6:08 PM
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.
December 12, 2025 at 1:03 PM
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.
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.
December 5, 2025 at 1:58 PM
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.
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.
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.
Ethics are important, but being compelling is just as important. If it isn’t, there’s little reason to use AI for artistic creation.
December 4, 2025 at 2:38 PM
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.
Ethics are important, but being compelling is just as important. If it isn’t, there’s little reason to use AI for artistic creation.
Reposted by Jordi Pons
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.
December 4, 2025 at 2:20 PM
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.
December 4, 2025 at 2:24 PM
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.
December 4, 2025 at 2:22 PM
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
> arxiv.org/abs/2508.11694
December 4, 2025 at 2:19 PM
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
> 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
> www.aisongcontest.com/all-particip...
> www.aisongcontest.com/join
December 4, 2025 at 2:19 PM
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
> 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.
December 4, 2025 at 2:07 PM
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.
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.
December 4, 2025 at 1:27 PM
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.
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?
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?
December 4, 2025 at 11:12 AM
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?
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?
Got the Pixel—the AI is built-in and great.
I don't understand the need for separate AI devices.
Maybe glasses could work to help our posture, but having a camera on your face is awkward.
I don't understand the need for separate AI devices.
Maybe glasses could work to help our posture, but having a camera on your face is awkward.
December 4, 2025 at 9:43 AM
Got the Pixel—the AI is built-in and great.
I don't understand the need for separate AI devices.
Maybe glasses could work to help our posture, but having a camera on your face is awkward.
I don't understand the need for separate AI devices.
Maybe glasses could work to help our posture, but having a camera on your face is awkward.
Many AI artists/scientists using the term ML (machine learning) instead of AI to avoid pushback.
December 1, 2025 at 10:21 AM
Many AI artists/scientists using the term ML (machine learning) instead of AI to avoid pushback.