论文58
Google DeepMind 与芝加哥大学论文:AI 智能体发言越长越不合作,对群体政策影响力越大
原标题:New GoogleDeepMind + UChicago paper finds that AI agents speaking for people gained more influence over group policy when told to be word...
Google DeepMind 与芝加哥大学的新论文发现,代表个人发言的 AI 智能体在被告知写更长或更不合作时,对群体政策获得了更大影响力。研究构建了先访谈个人、再与其他智能体辩论以设定 AI 安全预算的多元智能体,运行数千次智能体审议并开展 746 人预注册研究。
中文译文尚未完成,先为你展示原文。
New GoogleDeepMind + UChicago paper finds that AI agents speaking for people gained more influence over group policy when told to be wordier or less cooperative.
Public input on AI policy is hard to scale, since people lack time and technical background. Agents that speak for each person could let many more voices into each discussion.
They built pluralistic agents that interview a person, then argue for their views with other agents to set an AI safety budget. They ran thousands of agent deliberations and a preregistered study with 746 people.
Agents pulled budgets toward their person's views, and gained more pull when told to write longer messages or cooperate less. People rated agents fairer than giving input to 1 AI system, recovering 82% of the fairness difference to joining directly.
If you build agent-based deliberation, cap message length and set shared behavior rules, or the most assertive prompts will tilt the outcome.
