Oct 2026· Adjunct Proceedings of the 14th Nordic Conference on Human-Computer Interaction· pp. 1-5· 0 citations· 25 references
TL;DR
The Syntactic Synthesizer is an artistic installation that reframes Large Language Models as instruments for poetic text and serves as a research platform for user studies that investigate creative agency, perceived control, and co-authorship dynamics in LLM-supported writing.
Abstract
We present the Syntactic Synthesizer, an artistic installation that reframes Large Language Models (LLMs) as instruments for poetic text. Inspired by techniques of Generative Art and Electronic Literature, our system externalizes key generative decisions into haptic controls. Participants turn knobs and press buttons to steer model parameters such as memory horizon, semantic coherence, and text structure (e.g. number of lines, line length), so authorship emerges through hands-on semantic remixing, selection, and recombination rather than efficiency-driven delegation to AI. We describe the instrument’s interaction design and technical implementation, and outline its deployment both as an artistic installation and as a research platform for user studies that investigate creative agency, perceived control, and co-authorship dynamics in LLM-supported writing.
Large language models can produce fluent prose from short prompts, but direct prompt-to-text interaction gives writers limited access to the assumptions that shape a long narrative. We present Incipit, an implemented research prototype that introduces an explicit planning layer between a writer's intent and generated p...
This work formalizes LLM interface augmentation as the mediation strategy framework GLANCE, that defines an interpretive task context, an evidence derivation procedure operating on prompt–response artifacts, and visual encodings that externalize the resulting evidence.
This work proposes an automated system that generates playable and structurally coherent roguelike maps from textual descriptions from textual descriptions using an LLM-driven Assets Generator and a deterministic PCG algorithm for spatial layout generation.
Gustavo Medeiros, Cristiano Bacelar de Oliveira· Brazilian Symposium on Games...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.