Jordi Pons

That's a great point! Where can I read more about it? Do you have any good resources on interactive music?

The best (and worst) part of being in a band is the instant feedback.

Alone, it takes much longer to know if you’re on the right track.

Aside from the slop, of course. My mind has chosen to disregard irrelevant artistic work.

The more I think about it, the more I feel AI’s biggest mark on music will be through interactivity:

• Personalized playback experiences
• Unique, ephemeral live concerts
• Artistic agency through also “composing” the interaction

All thanks to the generative abilities of AI.

Never thought I’d be promoting my music in LinkedIn. Weird times.

Meet our AI Song Contest 2025 entry!
We submitted an interactive & generative AI music piece.

We used AI for:
- Sound design
- Interactive playback

More details about..
- Human-AI co-creation process
- Name of the song
- Videoclip
- Live performance

👉 artintech.substack.com/p/our-ai-son...

AI creating ‘potentially new’ music genres as artists take control, says Stability AI study - Music Business Worldwide The pushback to AI echoes previous technological changes that were resisted when they changed music, researchers at Stability AI say.

www.musicbusinessworldwide.com/ai-creating-...

I hope our work contributes to understanding how early adopters have used AI so far and serves as inspiration for future AI musicians.

Encouraging the creation of music that leaves a lasting, positive impact on music history.

We also analyze our dataset quantitatively, finding insights on: artistic agency, aesthetics, sound design or innovative uses and formats.

I'm also excited on how musicians are using AI as a new format or artistic medium.

And we study how musicians use AI across formats:
- Singles
- Albums
- Performances
- Installations
- AI voices
- Operas
- Soundtracks

We categorize them based on AI usage:
- AI composition
- Co-composition
- Sound design
- Lyrics generation
- Translation

We analyzed 337 AI music artworks (2017–2024) to uncover how artists are creating with AI.

📄 Paper (arXiv)
📂 Database (GitHub)
🎥 Video
👉 artintech.substack.com/p/report-art...

Everyone is thinking of using AI to make music. But what if it’s more interesting to use AI at playback time?

Music will no longer be distributed as MP3 files.

New generative AI formats are emerging that will enable interactive music experiences.

Beefs in AI Music Drake, Lamar, and even Tupac and Cope have all been caught up in beefs.

🔥🔥 Beefs in AI Music 🔥🔥

➡️ Drake's 'Taylor Made Freestyle' w/ Tupac and Snoop Dogg AI voices
➡️ Metro Boomin AI beat 'BBL Drizzy'
➡️ Drake rapping over 'BBL Drizzy' in 'U My Everything'
➡️ Legal beef targeting Suno
➡️ Academic beef between Wiggins and Cope

artintech.substack.com/p/beefs-in-a...

Beefs in AI Music Drake, Lamar, and even Tupac and Cope have all been caught up in beefs.

Beef has always been part of music culture, and AI music is no different :)

artintech.substack.com/p/beefs-in-a...

AI Music is Generative and Uncanny In this interview we discuss how AI misfires could shape AI music.

Most artists already know how to make music—they're not looking for AI to do it for them.

👉 artintech.substack.com/p/ai-music-i...

AI as an Artistic Medium Generative AI not as a tool, but as an artistic medium.

What’s an artistic medium?
It’s the thing artists use to make art.

Like canvas for painters.
Clay for sculptors.
Video for directors.
Or recordings for musicians.

This post explores how to use generative AI as an artistic medium:
artintech.substack.com/p/ai-as-an-a...

AI Makes Dinner On farming, cooking robots, reducing waste and more.

I’ve been studying AI and gastronomy—sharing my learnings here: artintech.substack.com/p/ai-makes-d...

Delicioso Algoritmo (Delicious Algorithm) by Eneko Axpe gives a nice overview of the field.

Know any other books, papers or blogposts?
I'm having trouble finding beginner-friendly resources.

Mixing Music 101 A practical checklist for beginners.

Lately, I’ve been learning to mix music.
And it feels overwhelming when you are a beginner.

Following this checklist helped me.

With this list you don’t need to remember everything. Just need to do what’s next.

Details and a PDF of the checklist in:
artintech.substack.com/p/mixing-mus...

Now thinking that I did not include live coding music, pure data, max MSP, supercollider..

Any good references out there?

Thanks everyone for your feedback <3

Generative Music OGs How dice games, wind arps, and Brian Eno are all related.

This post wraps up my time studying the history of generative music and AI music.

➡️Generative Music OGs artintech.substack.com/p/generative...

Previous posts..
➡️Algorithmic Music OGs artintech.substack.com/p/algorithmi...
➡️History of Neural Networks for Music artintech.substack.com/p/the-forgot...

Today we release Stable Audio Open Small 🫂

Based on adversarial post-training, it does not rely on distillation or CFG

Runtime is reduced to milliseconds with GPUs or seconds with CPUs

Weights huggingface.co/stabilityai/...
Blog stability.ai/news/stabili...
Paper arxiv.org/abs/2505.08175

Algorithmic Music OGs How serialism, quantum music, indeterminacy, and Duchamp are all related.

A few weeks ago, I wrote about the pioneers (OGs) of neural networks for music.

But many of you rightly pointed out that I missed some key names :)

Previous post: artintech.substack.com/p/the-forgot...
New post: artintech.substack.com/p/algorithmi...

Today I installed the ChatGPT app for my mum.

She used it to make jokes about my dad.

I'm not sure she is more productive now.

I’m deep down the rabbit hole of (pre-AI) generative music.

This is better than YouTube.

Making AI music without knowing Xenakis' work is like playing jazz without having heard Coltrane.

In the language of their time, 'indeterminacy' is akin to what we now call 'generative'—where some aspects of the composition are left to chance (not determined).

rohandrape.net/ut/rttcc-tex...

Does listening to audiobooks count as reading?

I'm experiencing a déjà vu with FAD metrics.

Five years ago, we were all complaining that SDR metrics were useless for source separation—yet here we are, still using them.

Authors fall into two camps — the acronym abusers and the good writers.