Back

Motion & Video

Crossing Pavements (3D)  |   Generative Castles (AI)  |   BIRDS  |   Audio-Visual Movements  |   Misc.








Generative Castles
2024

Midjourney, RunwayML, After EffectsA generative audiovisual music video exploring surveillance as a system of machine perception. Using an iterative prompting workflow across RunwayML and Midjourney, the project investigates how computational systems interpret and reconstruct visual and sonic information.

The work examines how recognition systems produce “legible” versions of reality through classification, patterning, and distortion. It considers the aesthetics of machine interpretation, in which visibility is shaped as much by algorithmic constraints as by human intent.

Produced in 2024 during a pivotal early phase of AI video synthesis, the piece archives and captures a distinct visual artifact and unpredictable textures characteristic of early-gen models.

While I maintain a critical stance toward the adoption of generative AI in creative practices, engaging with these tools was central to the methods of this project. Under the guidance of Refik Anadol, I approached AI as a subject of inquiry, feeding and learning machine perception tools to dissect, expose, and critique the subtle biases embedded within these systems.