当直接操作变成猜测：AI介导的多感官可视化中的生产性摩擦
When Direct Manipulation Becomes a Guess: Productive Friction in AI-Mediated Multisensory Visualization
浏览论文内容
中文总结 AI 辅助
本研究提出“生产性摩擦”概念，以解决AI介导多感官可视化中确定性交互与概率推断不匹配的问题，通过四种摩擦设计暴露推断边界、匹配动作效果、使随机分支可感知并归因感官一致性。
中文摘要 AI 辅助
生成式可视化日益将大语言模型嵌入直接操作和多感官交互中。语音、注视、触摸、手势、声音和触觉可以使概率推断感觉像熟悉的、确定性的工具使用。我将这种差距称为确定性-可供性不匹配：确定性交互线索持续存在，而AI削弱了可预测性、局部性、可逆性或来源性。通过将《钢铁侠2》中的可变形界面与《银翼杀手2049》中的系统进行对比阅读，我提出了生产性摩擦，包括其细节反映模型不确定性的跨感官渲染。四种摩擦暴露了推断边界，使动作与效果匹配，使随机分支变得可感知，并归因于感官一致性。
英文摘要
Generative visualization increasingly embeds large language models within direct manipulation and multisensory interaction. Speech, gaze, touch, gesture, sound, and haptics can make probabilistic inference feel like familiar, deterministic tool use. I call this gap a deterministic-affordance mismatch: deterministic interaction cues persist while AI weakens predictability, locality, reversibility, or provenance. Reading the malleable interfaces of Iron Man 2 against systems from Blade Runner 2049, I propose productive friction, including cross-sensory renderings whose detail reflects model uncertainty. Four frictions expose the inference boundary, match action to effect, make stochastic branches tangible, and attribute sensory agreement.
发表机构
- University of Waterloo（滑铁卢大学）
机构由 AI 辅助整理，请以论文原文为准。
