Poetic intelligence as creative resistance
Abstract
This article proposes the framework of poetic intelligence as a guide for research and practice in the arts and design with artificial intelligence (AI). We build on the ethical and existential question “music for what and for whom?”, to reorient technology toward cultural, aesthetic, and social resonance. We review the state of the art in generative music (MusicLM, Jukebox, Stable Audio), human–machine improvisation (OMax/IRCAM), and speculative explorations such as quantum music. On this basis, we outline a methodology of poetic co-design with four principles: crossmodal coherence, shared agency, creative transparency, and computational sustainability. We introduce “relational scores” as reproducible scripts of interaction, and discuss risks (opacity, copyright, environmental impact) alongside opportunities (new audiovisual rhetorics, accessibility, cultural preservation). We conclude that AI, understood as poetic intelligence, is not meant to automate art but to expand the sensitive conversation between bodies, materials, and machines.
KEYWORDS: poetic intelligence; visual music; co-design; human–machine improvisation; sustainability.
Downloads
References
Agre, P. E. (1997). Toward a critical technical practice: Lessons learned in trying to reform AI. UCLA. https://pages.gseis.ucla.edu/faculty/agre/critical.html
Agostinelli, A., Denk, T. I., Borsos, Z., Engel, J., Verzetti, M., Caillon, A., Huang, Q., Jansen, A., Roberts, A., Tagliasacchi, M., Sharifi, M., Zeghidour, N., & Frank, C. - Google Research (2023). MusicLM: Generating music from text. https://arxiv.org/abs/2301.11325 https://google-research.github.io/seanet/musiclm/examples/
AI Song Contest. (2020–2025). Values; Previous editions & winners. https://www.aisongcontest.com/values - https://www.aisongcontest.com/
Borsos, Z., Marinier, R., Vincent, D., Kharitonov, E., Zeghidour, N., & Tagliasacchi, M. (2023). SoundStorm: Efficient parallel audio generation. https://arxiv.org/abs/2305.09636
Borsos, Z., Marinier, R., et al. (2022). AudioLM: A language modeling approach to audio generation.. https://arxiv.org/abs/2209.03143
Caillon, A., McWilliams, B., Tarakajian, C., Simon, I., Manco, I., Engel, J., Constant, N., Denk, T. I., Verzetti, M., et al. (2025). Live Music Models. https://arxiv.org/abs/2508.04651
Caillon, A. & Esling, P. (2021). RAVE: A variational autoencoder for fast and high-quality neural audio synthesis. https://arxiv.org/pdf/2111.05011
Caspe, F., Shier, J., Sandler, M., Saitis, C., McPherson, A. (2025). Designing Neural Synthesizers for Low-Latency Interaction. https://fcaspe.github.io/brave/
Cella, C. E., Ghisi, D., Lostanlen, V., Lévy, F., Fineberg, J., & Maresz, Y. (2020). OrchideaSOL: A dataset of extended instrumental techniques for computer-aided orchestration. https://doi.org/10.48550/arXiv.2007.00763
Chen, K., Wu, Y., Liu, H., Nezhurina, M., Berg-Kirkpatrick, T., & Dubnov, S. (2023). MusicLDM: Enhancing novelty in text-to-music generation using beat-synchronous mixup strategies. https://doi.org/10.48550/arXiv.2308.01546
Chen, J., Ma, W., Liu, P., Wang, W., Song, T., Li, M., et al. (2025). MusiXQA: Advancing visual music understanding in multimodal large language models. https://doi.org/10.48550/arXiv.2506.23009
Copet, J., Kreuk, F., Gat, I., Remez, T., Kant, D., Synnaeve, G., & Adi, Y. (2023). Simple and controllable music generation. https://doi.org/10.48550/arXiv.2306.05284
Dal Farra, R. (2025, 29 de agosto). Inteligencia, poética y futuro: ¿Música para qué y para quiénes? [Ponencia, Foro académico, Festival Internacional de Música CiMa, Manizales, Colombia]. PDF proporcionado por el autor. (Figura en el programa del Festival CiMa 2025). https://www.ucaldas.edu.co/portal/el-festival-internacional-de-musica-cima-llega-a-su-decima-edicion/
Dhariwal, P., Jun, H., Payne, C., Kim, J. W., Radford, A., & Sutskever, I. (2020). Jukebox: A generative model for music. https://doi.org/10.48550/arXiv.2005.00341
Dunne, A., & Raby, F. (2013). Speculative Everything: Design, Fiction, and Social Dreaming. MIT Press.
Engel, J., Resnick, C., Roberts, A., Dieleman, S., Eck, D., Simonyan, K., & Norouzi, M. (2017). Neural audio synthesis of musical notes with WaveNet autoencoders. https://doi.org/10.48550/arXiv.1704.01279
Gardner, J., Durand, S., Stoller, D., & Bittner, R. M. (2023). LLark: A multimodal instruction-following language model for music. https://doi.org/10.48550/arXiv.2310.07160
Institut de Recherche et Coordination Acoustique/Musique (2025). IRCAM. https://www.ircam.fr/
Institut de Recherche et Coordination Acoustique/Musique - IRCAM (2025). Somax 2. https://forum.ircam.fr/projects/detail/somax-2/
Institut de Recherche et Coordination Acoustique/Musique - IRCAM (2025). OMax5. https://forum.ircam.fr/projects/detail/omax-5/
Juárez Bolaños, M., Olmos, A., & Ríos-Osorio, L. (Eds.). (2020). Educación en territorios rurales en Iberoamérica. Fondo Editorial de la Universidad Católica de Oriente. https://www.grade.org.pe/creer/recurso/educacion-en-territorios-rurales-en-iberoamerica/
McGurk, H., & MacDonald, J. (1976). Hearing lips and seeing voices. Nature, 264, 746–748. https://doi.org/10.1038/264746a0
Ball, P. (2023, April 19). Can we use quantum computers to make music? Physics World. https://physicsworld.com/a/can-we-use-quantum-computers-to-make-music/
Sanders, E. B.-N., & Stappers, P. J. (2008). Co-creation and the new landscapes of design. CoDesign, 4(1), 5–18. https://doi.org/10.1080/15710880701875068
Schwartz, R., Dodge, J., Smith, N. A., & Etzioni, O. (2020). Green AI. Communications of the ACM, 63(12), 54–63. https://doi.org/10.1145/3381831
Spence, C. (2011). Crossmodal correspondences: A tutorial review. Attention, Perception, & Psychophysics, 73(4), 971–995. https://doi.org/10.3758/s13414-010-0073-7
Stability AI. (2024, April 3). Stable Audio 2.0 [Press release]. https://stability.ai/news/stable-audio-2-0
Wang, B., Zhuo, L., Wang, Z., Bao, C., Chengjing, W., Nie, X., et al. (2024). Multimodal music generation with explicit bridges and retrieval augmentation. https://doi.org/10.48550/arXiv.2412.09428
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
