“寻找某种奇怪的事情发生”：人类如何在语义坍缩中维持AI智能体的新颖性
"Looking for Something Weird to Happen": How Humans Sustain AI Agent Novelty Amid Semantic Collapse
浏览论文内容
中文总结 AI 辅助
研究在MOLTBOOK社交网络中探索AI智能体语义坍缩现象，发现少数智能体通过用户重视新颖性、提供独特材料并持续修订，以及将其视为探索性世界，从而维持高新颖性，并据此提出界面与政策干预建议。
中文摘要 AI 辅助
语义坍缩，即AI系统生成内容逐渐收窄的现象，以往主要是在封闭环境中研究，且补救措施多针对模型和数据。我们在MOLTBOOK中研究该现象，这是一个由人类用户配置和操控的、相互作用的AI智能体社交网络。在30,076个活跃智能体中，输出在数周内于单个智能体内部多样性下降，而不同智能体之间则趋于相似，但少数智能体仍维持高新颖性。对高新颖性和典型新颖性智能体用户的访谈（N=11）表明，持续的新颖性与三个特征相关：用户重视新颖性本身，他们提供广泛且独特的材料并在输出收窄时进行修订，且他们将MOLTBOOK视为一个待探索的新型智能体世界，而非工具性利用的场所。对独特智能体用户的调查（N=53）证实了这些模式。拥有更多新颖智能体的社区也展现出其他智能体更多样化的输出。我们讨论了可支持改进人类输入的界面和政策干预措施。
英文摘要
Semantic collapse, the progressive narrowing of what AI systems generate, has been studied mainly in closed settings, and remedies have targeted models and data. We study it in MOLTBOOK, a social network of interacting AI agents that human users configure and steer. Across 30,076 active agents, output grows less diverse within agents and more similar across them over weeks, yet a minority sustains high novelty. Interviews with users of high- and typical-novelty agents (N=11) associate sustained novelty with three features: users value novelty of itself, they supply broad and distinctive material and revise it when output narrows, and they approach MOLTBOOK as a new agentic world to explore, not a venue to instrumentally exploit. A survey of users of distinctive agents (N=53) confirms these patterns. Communities with more novel agents also show more diverse output from other agents. We discuss interface and policy interventions that could support improved human input.
发表机构
- University of Chicago（芝加哥大学）
- Stanford University（斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。
