Original post · AI translation
标题:“用多元代理扩大公众对 AI 政策的参与”
Google DeepMind 与芝加哥大学的新论文发现,当代表人们发言的 AI 代理被要求说得更冗长或减少合作时,它们对群体政策的影响力会增强。
公众参与 AI 政策讨论很难扩大规模,因为人们缺乏时间和技术背景。代表每个人发言的代理可以让更多声音进入每场讨论。
他们构建了多元代理:代理先采访一个人,再与其他代理辩论,代表受访者的观点确定 AI 安全预算。他们进行了数千场代理审议,并开展了一项有 746 人参与的预注册研究。
代理使预算向其所代表者的观点靠拢;当被要求写更长的消息或减少合作时,其影响力会增强。与向 1 个 AI 系统提供意见相比,人们认为代理更公平,其公平性弥合了与直接参与相比的差距的 82%。
如果你要构建基于代理的审议机制,就应限制消息长度并制定共同的行为规则,否则最强势的提示词会使结果产生偏差。
Original
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.