The Models (2025) is an interactive simulation-based installation exploring truth, wonder and the quirks of generative AI through the improvised theatrical tradition of Italian Commedia dell’Arte. The installation consists of an endless series of theatrical scenes generated in real-time using text AI and a video game engine, and featuring a cast of characters acting in response to audience input. Through the archetypal, popular and exaggerated traits of Commedia dell’Arte masks, such as Arlecchino, the characters embody tendencies observed in Large Language Models, including making things up, being antagonistic, or being overly servile.

Through their phones, audiences prompt characters to act out these tendencies, praising or booing their performances, and dropping controversial props on stage that symbolise superstitions, falsehoods or popular Commedia gags known as Lazzi. Characters perform in real-time in response - confabulating, making up truths and conspiracies, making banal mistakes - with dialogues generated by a system of AI models assembled by the artists on the Leonardo Supercomputer housed in Bologna’s Tecnopolo - the 6th most powerful in the world.
𝐓𝐡𝐞 𝐌𝐨𝐝𝐞𝐥𝐬
installation by @dmstfctn
endless AI-generated improv theatre

Tecnopolo Manifattura, Botte B4
Bologna
February 7-9, 2025






















Music @richard.enterprises
Additional UE development by: Jenn Leung