Miju Labs

← All buyers · Stability AI

J

Jordi Pons

Research Scientist · Stability AI

medium confidenceTier B · Map and watchImage, video & audio modelsaudio

Recent posts

Jordi Pons
Research Scientist at Stability AI
I don’t want AI to generate my music. AI is simply part of my sound design exploration. I start a song by composing and producing it myself. NOT using AI for: - Melody - Harmony - Rhythm - Arrangement - Guitar performance - Editing and production - Mixing But I use AI to: - Generate samples with Stable Audio. - Transform samples and guitars into weird sounds with Stable Audio. - Generate percussive and texture layers with Moises. I’m interested in discovering what music can sound and feel like when I embrace the unique possibilities of AI. In this track, I explore uncanny sound design. Uncanny means something strange or unsettling because it feels oddly familiar or goes beyond what feels natural. Listen to the experimental sounds and transformed guitar textures in the middle section, from 0:55. Dalí’s melting clocks are uncanny because they feel familiar but unsettling. I mix uncanny sounds with familiar elements like funk guitars and pop rhythms, creating a balance between familiar and experimental sounds. So… I’m NOT interested in using AI to reproduce existing aesthetics more efficiently. AI media is often criticized for being low-effort slop and for threatening artists’ livelihoods because AI can automate creative work. But AI in art is not always used for automation or efficiency. The most interesting uses of AI come from artists exploring what AI makes possible that wasn’t possible before. I think the narrative around AI art needs to evolve to include more underground artists. More artist-centered work can help challenge the idea that AI inevitably produces low-effort content. Underground art is to culture what the runway is to fashion: a place where new ideas can appear before they become products and everyday experiences. If the current state of AI art feels like low-effort slop, our role as artists is to make new proposals and explore new ways of using AI meaningfully.
393 comments • 1 reposts
Jordi Pons
Research Scientist at Stability AI
3 rules for AI art. I build interactive music experiences that are unequivocally AI, driven by artistic intent, and culturally rooted. This artist statement grew out of three characteristics I’ve noticed in AI artworks I find compelling: 1. Unequivocally AI. AI is a new generative medium. Build new things that feel AI. 2. Artistic intent. Make deliberate choices, not low-effort content. 3. Culturally rooted. Connect with your audience. UNEQUIVOCALLY AI Generative AI enables experiences and aesthetics that were previously not possible. The role of the artist is to rigorously push the boundaries of what “unequivocally AI” means. ARTISTIC INTENT AI media is often criticized as low-effort and for threatening artists’ livelihoods. The narrative around AI art must evolve: Low-effort content → AI as a medium for storytelling Replacing artists → AI in service of artistic agency Storytelling and artistic agency lie at the heart of AI art. CULTURALLY ROOTED For AI art to have cultural impact, we must build compelling narratives and make work people want to experience, share, and talk about. Otherwise, our feeds will be flooded with low-effort AI content while artists struggle to build sustainable careers around (AI) art. MY PRACTICE I’m personally interested in exploring better interactive (active listening) music experiences as the music industry converges on AI remixing. AI remixing is a poor interactive experience that is fully functional (covers in other genres) instead of artistic (unexpected, novel interactions with music). I explore interactive games that turn active listening into a familiar experience, relying on beats inspired by popular culture to meet audiences where they already are.
3311 comments
Jordi Pons
Research Scientist at Stability AI
Fresh results from July 2026 at Music Arena. Happy to see the community is finding Stable Audio 3 Medium as useful as we do. It has been independently evaluated, and Medium is the second-best and fastest model for instrumental music generation, with open weights! Music Arena: lnkd.in/eAPA9pvb Stable Audio 3, explained in 5 figures: lnkd.in/eJYFM_bk 14 unconventional uses of Stable Audio: lnkd.in/efqp8WRu Huge shoutout to the Music Arena team ❤️
441 comments • 5 reposts
Jordi Pons
Research Scientist at Stability AI
I have absolute pitch (except when I don’t). In high school, I noticed that the transcription in the music textbook was four semitones off. That’s when I first thought I might have absolute pitch. This also became apparent when I started playing the clarinet. Unlike the piano, the clarinet is a transposing instrument: the note written on the page is not the pitch that sounds. My ear immediately recognized the sounding pitch, even though it did not match the note I was reading. For most instruments and situations, I can quickly name notes without a reference tone. Yet, I struggle with: - Black-key notes (accidentals) - Non-Western / non-classical instruments - Chords and full mixes - Long motifs So why does this happen to me and to many others? In this post, I review the science behind my “absolute pitch impostor syndrome”: - Absolute pitch might be a spectrum - The role of classical piano training - Semitone errors are common - Perceptual biases shape pitch perception WHAT IS ABSOLUTE PITCH? Absolute pitch (also known as perfect pitch) is the rare ability to identify or produce musical notes without a reference. THE ABSOLUTE PITCH SPECTRUM In psychological science, human abilities are often simplified into binary categories: you either have an ability or you don’t. Early work by Bachem (1937) challenged this view by proposing four levels of absolute pitch: - Genuine absolute pitch: Fast, certain, and accurate, even with chords. - “Pseudo” absolute pitch: Slower, uncertain, and approximate. - “Quasi” absolute pitch: Approximate pitch estimation with a reference tone. - No absolute pitch. More recent research by Van Hedger et al. (2020) suggests that genuine and “pseudo” absolute pitch are not separate abilities, but different points along the same continuum. PIANO TRAINING SHAPED MY PERCEPTION The piano is an instrument through which many learn music. As a result, many musicians develop stronger pitch associations for white-key notes and pitch labels can become partly associated with the piano’s timbre, a phenomenon sometimes called “absolute piano”. SEMITONE ERRORS Semitone errors occur most often on black-key notes, which is consistent with the idea that early piano training emphasizes white-key notes. Further, semitone errors also become more common with age. PERCEPTUAL BIASES AND PITCH PERCEPTION I often struggle to name every note in a fast solo. But once it ends, I can usually identify the final note. This is consistent with the recency effect, a well-known phenomenon. A similar effect appears in chords and recordings with many instruments. Research shows that listeners naturally pay more attention to the highest voice in polyphonic music. SO.. DO I HAVE ABSOLUTE PITCH? I’ve never been fully confident about my absolute pitch abilities. While I can quickly identify most.. [i’ve reached linkedin’s character limit, read the original piece: lnkd.in/eqfdbAP3]
365 comments

Why they are on the map

Senior author of ARC post-training (2025) and Stable Audio Open; LinkedIn lists him as Research Scientist at Stability AI. source — evidence dated 2025-05

Shapes what 'good data' means.

How Stability AI buys data

2026 Series B ($76M) investors include Universal Music, Sony Music, Warner Music and Electronic Arts, so the focus is licensed data and pro workflows. Nov 2025 UK High Court ruling in Getty v Stability went largely for Stability. Open 2026 role 'Research Scientist, Professional Creative Workflows' targets 'controllability, editability, consistency, brand adherence, and production usefulness'. No human-data vendor named.

CEO Prem Akkaraju and CTO Hanno Basse. Research is split into image/3D/video and audio (Stable Audio) groups. The VP Research (Varun Jampani) has left for Arcade. Current open roles are few (7 on Greenhouse).

Full dossier pending

This person was mapped in pass 1. Career, what they have said on the record, interviews, connections, why they matter to us and how to reach them are added in pass 2.