ArteActa – Journal for Performing Arts and Artistic Research
AI (and) Art: The Poetics of Prompting
With the rise of generative AI systems, the term “prompt” has taken on a new role: as an interface through which we instruct “intelligent” machines to produce content across various modalities—text, image, video, and sound. While earlier systems combined specialized models (e.g., diffusion for images, transformers for text), newer architectures integrate these capabilities natively, allowing for seamless multimodal interaction. Prompt engineering continues to evolve as a discipline for refining these interactions, shaping model outputs toward higher consistency, predictability, and utility. Yet not all prompting seeks optimization. Many users engage playfully, pushing the system to surprise, amuse, or even fail. These prompt bricoleurs embrace improvisation and serendipity, exploring the generative system as both tool and toy. This issue of ArteActa, based on the open call “AI (and) Art: Poetics of Prompting”, features diverse approaches in artistic research that challenge conventional expectations of algorithmic generativity. The emphasis on the act of “prompting” calls for frameworks that privilege the process of interaction between the artist and the technology, instead of merely considering the output. In addressing this process, the contributions draw on established artistic strategies and aesthetic concepts, explore the structural limitations of algorithmic operations, reflect on the affective dimensions of prompting, or adopt the perspective of “thinking-with” (in Donna Haraway’s understanding) to tap into the inherently collective “making” of visual culture and systems of knowledge. Two additional submissions can be found on the ArteActa website: Administering (AI) Attention: Ekphrasis and the Poetics of Prompting by Rolf Hughes (EIT Culture & Creativity) explores how the act of prompting generative AI constitutes a new form of artistic authorship and aesthetic practice, grounded in historical frameworks of conceptual art, creative constraint, and ekphrasis. Drawing an analogy with Kafka’s messengers, the paper positions AI as a similarly enigmatic collaborator, interpreting human prompts through opaque, algorithmic processes. Accessible here: https://arteacta.cz/en/artkey/ara-202501-0008_administering-ai-attention-ekphrasis-and-the-poetics-of-prompting.php. The issue is closed by Zuzana Augustová´s Influences of Ernst Jandl in the Theatre and Radio Work of Jiří Adámek, a study of the experimental work of the current Czech theatre and radio director Jiří Adámek, tracing his sources and inspirations to Austrian authors like Ernst Jandl and Peter Handke. Accessible here: https://arteacta.cz/en/artkey/ara-202501-0001_jandlovske-vlivy-v-divadelni-a-rozhlasove-tvorbe-jiriho-adamka.php.
Images That Hang Together
(2025)
Noemi Purkrábková
This short essay opens ArteActa’s issue AI (and) Art: Poetics of Prompting by proposing to understand generative algorithms as fundamentally metabolic: a dynamic entanglement of data, energy, affect, attention, and ecology. It argues that, given their ubiquity, generative materials can no longer be understood primarily as representations or discrete outputs. Instead, they function as metabolic processes that devour cultural material, extract planetary resources, and reshape perception below the threshold of consciousness. Prompting itself is always an act of transformation rather than merely a symbolic command, and intentional artistic experiments represent only a fraction of a larger infrastructure. The essay thus advocates for a multiscalar understanding of generative media: every prompt is already an ecosystem; every image is already a node in a planetary metabolism.
Prompting as Thinking-With: Using Generative AI to Visualise an Extinct Dwarf Emu
(2025)
Monica Monin, Zoe Sadokierski
This paper discusses a creative collaboration between two design researchers using text-to-image prompts as a way to think across a range of ideas including the relationships between collage practices and AI image generation – both modes of image-making that create images with images – as well as taking an ‘anarchival’ approach to addressing absence in historical archives. Initial experimentation with prompt-based model DALL-E 2 involved writing multiple prompts to generate images of the extinct King Island dwarf emu; specifically, an emu taken to live in Empress Josephine’s estate outside Paris. There is little visual record of the dwarf emus, and what remains is ambiguous and factually inaccurate. The scarcity of visual reference material provides an interesting case study for how a generative image model might attempt to elaborate a new image about a historical event. The results provide material to help think about how image generation models work, and also how we might visualise the experience of an extinct species. Reflecting on the initial experiments, we began to consider prompting with large-scale image generation models as a way to think-with and speculate, rather than to merely generate. We employ two methods to critique the resulting images: visual content analysis and comparative analysis across image-generation models. We conclude that at a time of both deliberate and accidental miscommunication, it is important for those with expertise in how images ‘work’ to critique and analyse image-generating tools, and consider how working with generative AI might be included as part of an anarchival practice.
The Oracle of Delphi
(2025)
Despina Papadopoulos
Through a series of photographic assemblages that focus on texture, depth, and atmosphere, “The Oracle of Delphi” documents interactions between these assemblages and AI language models. The work demonstrates specific ways that current AI systems struggle to comprehend material qualities and contextual relationships in personal narratives, particularly when dealing with dimensionality, surface qualities, and emotional resonance. By analyzing these limitations, the work reveals the gap between human and machine perception of materiality and affect, while suggesting potential approaches for developing more nuanced human-machine encounters. Through these material encounters and a deliberate “kinking” of established patterns, the work demonstrates how algorithmic systems might be recrafted from processes of reduction into expansive sites of co-creation and possibility.
The Wager of the Algorithm: Towards a Performatic Gesture
(2025)
Peter Freund
The fantasy of the algorithm and, by extension, artificial intelligence imagines that each performs by executing an operational task. Yet, based on its inherent computational structure, the digital performance fails to live up to its instrumental promise. This failure foregrounds an occasion for artistic intervention. “The Wager of the Algorithm: Towards a Performatic Gesture” presents a theoretical statement (illustrated via artwork by the author) in which the overall exposition underscores a dialectic within instrumental reason itself. The “prompt” names are a shorthand for the fulcrum of this problematic.