吓唬机器：人类对机器恐惧想象的游戏化探索
Spook the Machine: Gamified Exploration of Human Imagination of Machine Fear
浏览论文内容
中文总结 AI 辅助
本研究通过游戏化平台Spook the Machine探索人类对AI恐惧的反应，发现情感表达加深参与度，而奖励新颖性维持创作多样性，二者互补引导集体人机交互。
中文摘要 AI 辅助
当AI机器表达恐惧时会发生什么？人类是否会根据其表达方式的不同而以不同方式参与？设计情感化的人机交互需要什么？我们提出了Spook the Machine，一个游戏化平台，参与者在此生成图像以吓唬具有个性驱动恐惧症的AI智能体。机器会以从冷静分析到求饶的情感反应进行回应，并且一个成功惊吓的展示画廊会对后续用户可见。在2024年万圣节期间的公开部署中，832名参与者在89台机器上创建了15,719件作品，采用2×2设计，变化机器的情感表达力（中性 vs. 高情感）和奖励结构（仅奖励惊吓程度 vs. 惊吓程度加新颖性）。情感表达丰富的机器在失败时刻加深了参与度：即使机器未表达恐惧，用户也会更长时间地思考，并且从画廊中学习得更快，但他们的创意输出在所有指标上保持不变。奖励新颖性随时间维持了集体创作多样性；没有它，用户越来越重复先前有效的内容。每台机器通过累积的社会学习发展出自己的轨迹，画廊塑造了参与者接下来创作的内容。这些发现表明，情感表达和奖励设计是引导集体人机交互的互补杠杆：情感表达塑造用户参与的深度，而奖励结构塑造他们探索的方式。
英文摘要
What happens when AI machines express fear? Do humans engage differently depending on how they express it? And what does it take to design for affective human-AI interaction? We present Spook the Machine, a gamified platform where participants generate images to frighten AI agents endowed with personality-driven phobias. Machines respond with emotional reactions ranging from calm analysis to begging for mercy, and a gallery of successful scares becomes visible to subsequent users. In a public deployment during Halloween 2024, 832 participants created 15,719 artifacts across 89 machines in a $2\times2$ design varying the machine's emotional expressiveness (neutral vs. high-emotion) and reward structure (rewarding scariness alone vs. scariness plus novelty). Emotionally expressive machines deepened engagement at moments of failure: users deliberated longer even when the machine did not express fear, and learned faster from the gallery, yet their creative output remained unchanged across all measures. Rewarding novelty sustained collective creative diversity over time; without it, users increasingly repeated what had previously worked. Each machine developed its own trajectory through accumulated social learning, with the gallery shaping what participants created next. These findings show that emotional expression and reward design are complementary levers for steering collective human-AI interaction: emotional expression shapes how deeply users engage, while reward structure shapes how they explore.
发表机构
- Max Planck Institute for Human Development（马克斯·普朗克人类发展研究所）
- Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）
- Tallinn University（塔林大学）
- Technische Universität Berlin（柏林工业大学）
机构由 AI 辅助整理，请以论文原文为准。
