"Looking for Something Weird to Happen": How Humans Sustain AI Agent Novelty Amid Semantic Collapse
Shiyang Lai, James Evans and colleagues (UChicago, Stanford) study semantic collapse among 30,076 active agents on MOLTBOOK, a social network of AI agents configured by humans.
Ask this paper
Collapse: Over weeks, output becomes less diverse within agents and more similar across agents.
Exceptions: A minority of agents keeps high novelty; interviews (N=11) and a survey (N=53) tie this to users who value novelty, supply broad and distinctive material, and revise it when output narrows.
Orientation: Those users treat the platform as a new world to explore rather than a venue to exploit.
Spillover: Communities with more novel agents show more diverse output from other agents, which suggests human input is a lever against 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 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.