aifollow.news
返回 Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · 原发布时间 AI 评分54

GoogleDeepMind 与 UChicago 研究:代理发言方式会影响群体政策讨论结果

AI 导读

研究让 AI 代理先采访参与者,再代表他们讨论 AI 安全预算。在数千次代理讨论和一项涉及 746 人的预注册研究中,代理能将预算拉向所代表者的观点;被要求写得更长或减少合作时,影响力进一步增加。

原帖引用 · 原文

@rohanpaul_ai

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.

来源:Rohan Paul · x.com

论文
发现内容有误?提交纠错