World Simulator: Queer Erotica and the Absurdity of AI Video Models That Promise the World
arXiv:2608.07510 · doi:10.1145/3803784.3809266
Abstract
Increasingly, AI video models are marketed as "world simulators," suggesting their ability to model infinite realities. Despite such claims, these models systematically exclude significant aspects of embodied human experience, particularly sexuality. World Simulator is a video installation exploring the poetic friction between these universal claims and the models' inherent blindness. To do so, the work feeds explicit gay erotica into an AI video-to-video pipeline. Lacking the training data to recognize these images, the system hallucinates surreal alternatives, transforming intimate acts into banal scenes of kitchen appliances, strange architectures, and abstract flesh. By visualizing the limits of synthetic knowledge, the work challenges the hubris of the "world simulator" label, asking how a system, trained primarily on large filtered video datasets, can claim to simulate the world while remaining structurally blind to the body. Beyond this critique, we question the value of simulation itself, asking what forms of sensual representation might offer more expansive, life-affirming possibilities.
Accepted to Creativity and Cognition (C&C '26), July 13-16, 2026, London, United Kingdom. 5 pages, 5 figures
References in corpus (12)
- Deep Else: A Critical Framework for AI Art
- Learning to See: You Are What You See
- Wan: Open and Advanced Large-Scale Video Generative Models
- Genie: Generative Interactive Environments
- Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus
- Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond
- A Survey on Video Diffusion Models
- A Survey on Long Video Generation: Challenges, Methods, and Prospects
- Vid2World: Crafting Video Diffusion Models to Interactive World Models
- "I Cannot Write This Because It Violates Our Content Policy": Understanding Content Moderation Policies and User Experiences in Generative AI Products
- Value-guided action planning with JEPA world models
- A Mechanistic View on Video Generation as World Models: State and Dynamics