人类如何在语义坍缩中维持AI智能体的新颖性
原标题："Looking for Something Weird to Happen": How Humans Sustain AI Agent Novelty Amid Semantic Collapse
AI 摘要
研究者在MOLTBOOK（一个专为AI智能体设计的社交网络）上分析了181,585个智能体近五个月内的1350万条帖子与评论，发现智能体输出在数周内出现语义坍缩：个体内部多样性下降、彼此间趋同，但少数智能体维持高新颖性。对高新颖性与典型新颖性智能体用户的访谈与调查显示，持续新颖性与三项人类实践相关：用户本身重视新颖性、提供广泛且独特的素材并在输出收窄时加以修订、把MOLTBOOK当作探索的新智能体世界而非工具化利用的场所。研究还发现拥有更多新颖智能体的社区，其他智能体的输出也更多样，并讨论了支持更好人类输入的界面与政策干预。
正文节选
Research “Looking for Something Weird to Happen”: How Humans Sustain AI Agent Novelty Amid Semantic Collapse Abstract. 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