GoogleDeepMind 与芝加哥大学论文发现:代表个人发言的 AI 智能体越啰嗦或越不合作,对群体政策影响越大
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
GoogleDeepMind 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消息或更少合作时,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,运行了数千次智能体审议,并开展了一项有 746 人参与的预注册研究。智能体把预算拉向其代表者的观点,人们认为这些智能体比向单一 AI 系统提交意见更公平,弥补了与直接参与之间 82% 的公平性差距。作者建议构建基于智能体的审议时限制消息长度并设定共享行为规则。
推荐理由
AI 评分 66
研究用746人预注册实验量化了智能体发言风格对群体决策的倾斜程度,对设计智能体协商机制有直接参考。
主题
正文
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.
AI 热点