SOURCE-LINKED INTELLIGENCE

"Looking for Something Weird to Happen": How Humans Sustain AI Agent Novelty Amid Semantic Collapse

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

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 materi

Read original source ↗ Open in workspace

recordType

paper

region

Global