Artificial intelligence (AI) models are prevalent today and provide a valuable tool for artists. However, a lesser-known artifact that comes with AI models that is not always discussed is the glitch. Glitches occur for various reasons; sometimes, they are known, and sometimes they are a mystery. Artists who use AI models to generate art might not understand the reason for the glitch but often want to experiment and explore novel ways of augmenting the output of the glitch. This paper discusses some of the questions artists have when leveraging the glitch in AI art production. It explores the unexpected positive outcomes produced by glitches in the specific context of motion capture and performance art.

翻译：人工智能（AI）模型如今广泛普及，为艺术家提供了宝贵工具。然而，AI模型中一个较少被讨论的现象是故障。故障产生的原因多样，有时已知，有时则难以解释。使用AI模型生成艺术的艺术家或许不理解故障的根源，但往往希望通过实验探索增强故障输出的新方法。本文探讨了艺术家在AI艺术创作中利用故障时面临的一些问题，并研究了故障在运动捕捉与表演艺术这一特定情境下产生的意外积极成果。