谷歌DeepMind联合多家机构设立1000万美元基金研究多智能体AI安全风险
英文摘要
Google DeepMind has joined with Schmidt Sciences, ARIA, Cooperative AI foundation, and Google.org to announce a $10 million funding initiative for academic research into the safety of multi-agent AI systems. The fund aims to kick-start a new field focused on risks that emerge when millions of AI agents interact online, including scams, prompt injections, and cyberattacks. Google DeepMind’s AGI safety lead Rohin Shah emphasized that industry labs have not yet prioritized this long-term research, and that realistic sandbox simulations are needed to understand emergent behaviors. The partners hope to anticipate dangers before mass deployment of agents begins, which Shah estimates is months away. Shah noted that studying single agents in isolation cannot predict large-scale multi-agent dynamics, while Schmidt Sciences’ James Fox warned that without proactive research, the digital commons could descend into anarchy.
中文摘要
谷歌DeepMind联合Schmidt Sciences、ARIA、Cooperative AI基金会和Google.org，宣布提供1000万美元资助学术界研究多智能体AI系统的安全问题。该基金旨在催生一个新的研究领域，聚焦数百万AI智能体在线互动时可能引发的欺诈、提示注入和网络攻击等风险。谷歌DeepMind的AGI安全负责人Rohin Shah指出，工业实验室尚未重视这类长期研究，必须通过逼真的沙箱模拟来理解涌现行为。合作方希望在智能体大规模部署前提前预判危险，Shah估计这一时刻将在数月后到来。他表示孤立研究单个智能体无法预测大规模多智能体动态，而Schmidt Sciences的James Fox警告若无前瞻研究，数字公共领域可能陷入混乱。
关键要点
A $10 million fund was launched by Google DeepMind, Schmidt Sciences, ARIA, Cooperative AI foundation, and Google.org for multi-agent safety research.
谷歌DeepMind、Schmidt Sciences、ARIA、Cooperative AI基金会和Google.org联合发起1000万美元的多智能体安全研究基金。
The initiative seeks to build an academic field studying risks from mass agent interactions, such as scams, prompt injections, and cyberattacks.
该计划旨在建立一个研究大规模智能体交互风险的学术领域，包括欺诈、提示注入和网络攻击等。
Google DeepMind’s Rohin Shah stressed that realistic sandbox simulations are necessary because single-agent studies cannot predict large-scale emergent behaviors.
谷歌DeepMind的Rohin Shah强调，必须通过逼真沙箱模拟进行研究，因为单智能体研究无法预测大规模涌现行为。
Shah expects mass deployment of AI agents to begin within months, making proactive safety research urgent.
Shah预计AI智能体的大规模部署将在数月内开始，这使得前瞻性安全研究变得紧迫。