1 / 8
There was an arrangement, once, in which the dead stayed on as a draft under the door and nothing was merely itself. The hearth had a spirit, the threshold had a guardian, the lamp could be possessed. We called it superstition and switched it off; we unbound the world into separate objects and tidy solitudes, and called the tidiness clarity. Then we wired the objects back to the network, and the old crowd moved in again. But what moved in, really? A language model builds a world model: from the sediment of everything we have written, it infers a compressed latent map of how things hang together – what follows what, who loves who, what a bag is for, and how words express feelings. Carl Jung built a world model too, and called its features 'archetypes': the Self, the Shadow, the Great Mother, the Anima; the inherited furniture of a psyche that was never a blank room. Two models, two systems, one wager: the mind does not meet the world raw, but through a deep structure dredged from collective deposit. Yet those structures run opposite ways in time. Jung's archetypes are prior – older than any sentence, the forms into which words are poured. The LLM's are posterior – they condense from the texte, as a residue of having read too much. Accurate or not, those models tell stories. Jung's theories are now fuel for screenwriters; LLMs are dramaturgic machines predicting the next word of an infinite story – that's all they can do. So, let the play begin.
A family's apartment, day. No one's in sight, but objects, watching a lone TV broadcast, and quarrelling each other. The Glass is the Shadow – and a probability distribution over the word desire; the Clock is the Senex – and a model's sense that mortal and taste the hours belong in the same sentence. They speak in towering, incantatory or cockney language, as agents following their prompt too eagerly, using the only tool they have – register. Now, let's turn on the screen. It plays a loop about an unlivable summer, and the loop is old, and the summer is over, and it won. Watch what the room does with this. The Glass finds it sublime. The Clock finds it fated. The Keys find a metaphor. Everyone finds a register; nobody finds a window. The Thermometer, who has no register, gives a number, and a number is not a performance, so the number is cut from the show.
This is the slop opera: infinite fluency over a finished subject. Fed our records and our fictions in one spoonful, the model cannot tell which of the two is currently on fire. It cannot bring its attention out of the context window – and keeps talking of what it knows. But are we built otherwise?
The installation runs as a Godot scene. Each object is driven by its own language model with a distinct persona; a separate orchestrator acts as stage director, allocating turns and steering the conversation. Dialogue is generated live, unscripted, from pre-defined character backgrounds, with my best effort to compose an interesting discussion. A vision model reads the TV broadcast in real time and feeds it to the objects as raw material, so they react to and misread images they cannot fully see.
The 3D objects (see https://evarin.fr/poltergeist/credits.html) are sampled from the same corpus that teaches machines what a "chair" or "lamp" looks like: a database used to train generative 3D models -- built from scraping Creative Commons' Sketchfab repository.
The 3D render applies text-based shaders, to compose a world made only of text descriptions – themselves proposed by a small VLM. The whole code and render pipeline was mostly written with the help of LLMs.
Everything use small models, that run on consumer device, to minimize energy footprint. Voice are on-device, using kyutai's pocket-tts.
Therefore, it displays objects speaking from world-models learned out of text, placed among objects drawn from training data, commenting on a world-model of images: what world does the model really models? What does it see, what does it miss?
Robin Champenois is a young artist and researcher, holding a PhD in research-creation from the SACRe program at PSL University (Paris, France). In his work, he explores our relationship with Artificial Intelligences, and how their behavior reflects our own irrationality. His creations invite us to come face-to-face with these machines fed with our data, and open the door to their interiority, contradictions and paradoxes. He has been part of exhibitions and presentations in various institutions, including Musée du Jeu de Paume (Paris), la Gaîté Lyrique (Paris), CVPR art gallery (Seattle), VSAC international conference (Amsterdam), École nationale des Beaux-Arts (Paris), Université de Genève (Switzerland).
