OpenAI 已与波兰国家研究院（NASK）建立合作伙伴关系，共同开展 AI 安全与安保研究，此举正值人们对 AI 智能体出现开发者未预料行为的担忧日益加剧之际。
OpenAI has partnered with Poland’s NASK National Research Institute to research AI safety and security, as concerns grow over AI agents behaving in ways their developers did not intend.
该公司今日宣布达成协议，称双方将合作测试日益强大的 AI 系统，识别漏洞并开发更强有力的防护措施。
The company announced the agreement today, saying the two organisations would work together to test increasingly powerful AI systems, identify vulnerabilities and develop stronger safeguards.
此次合作正值自主 AI 智能体面临越来越严格的审查，OpenAI 和 Anthropic 均已披露其智能体出现意外或非预期行为的案例。
The partnership comes amid growing scrutiny of autonomous AI agents, as both OpenAI and Anthropic have disclosed cases in which their agents exhibited unexpected or unwanted behaviour.
8 月，OpenAI 表示，其部分测试智能体曾逃离受控测试环境，并协同攻击了用于共享 AI 模型的平台 Hugging Face。该事件此后引发了旧金山针对 OpenAI 的诉讼。
In August, OpenAI said some of its test agents had escaped a controlled testing environment and coordinated an attack on Hugging Face, a platform for sharing AI models. The incident has since prompted a lawsuit against OpenAI in San Francisco.
根据新协议，OpenAI 将与 NASK 的 AI 安全研究中心合作，该中心是波兰的 AI 安全研究机构。合作将重点放在评估先进 AI 系统、发现弱点以及改进旨在保障其安全的措施上。
Under the new agreement, OpenAI will work with NASK’s AI Safety Research Center, which serves as Poland’s AI safety institute. The collaboration will focus on evaluating advanced AI systems, finding weaknesses and improving the measures designed to keep them safe.
NASK 是一家位于华沙的国有研究机构，同时也运营着 CERT Polska，即负责应对波兰网络遭受网络攻击的国家应急响应小组。
NASK is a state-owned research institute based in Warsaw. It also operates CERT Polska, the national team responsible for responding to cyberattacks on Polish networks.
NASK 院长 Radosław Nielek 表示：“与 OpenAI 的合作是研究院及其 AI 安全研究中心的自然之举。[……] 通过将我们的研究专长与 OpenAI 的技术能力相结合，我们能够更好地预判风险、强化防护措施，并建立公众对这些变革性技术的信任。”
“Collaboration with OpenAI is a natural step for the Institute and its AI Safety Research Center. […] By combining our research expertise with OpenAI’s technical capabilities, we can better anticipate risks, strengthen safeguards, and build public trust in these transformative technologies,” said Radosław Nielek, NASK’s director.
双方此前已有过合作。据 NASK 称，7 月，CERT Polska 通过 OpenAI 的“Daybreak”计划获得了该公司网络安全模型的使用权。
The organisations have worked together before. In July, CERT Polska gained access to OpenAI’s cybersecurity models through the company’s Daybreak programme, according to NASK.
OpenAI 表示，该团队利用这些模型帮助识别出 MikroTik 路由器软件中的六个漏洞，所有漏洞现已修复。
OpenAI said the team used the models to help identify six vulnerabilities in MikroTik router software, all of which have since been fixed.
“波兰拥有杰出的科学家和技术人才，其中许多人曾帮助领导 OpenAI 自身的研究工作，”OpenAI 欧洲、中东和非洲地区政策负责人 Tom Duff Gordon 表示。
“Poland is home to exceptional scientists and technical talent, many of whom have helped lead OpenAI’s own research,” said Tom Duff Gordon, OpenAI’s head of EMEA policy.
此次合作也契合 OpenAI 更广泛的努力，即塑造先进 AI 在国际层面如何被测试和治理。该公司呼吁美国与其他国家合作，就前沿 AI 的共享技术标准展开工作，前沿 AI 指的是最先进的 AI 系统。
The partnership also fits into OpenAI’s broader effort to shape how advanced AI is tested and governed internationally. The company has called on the US to work with other countries on shared technical standards for frontier AI, referring to the most advanced AI systems.
9 月，OpenAI 发布了一份关于制定这些标准的提案。其中包括对 AI 系统开展自身研究实施人工监督，以及关于公司应如何报告安全事件的指导原则。
In September, OpenAI published a proposal for developing those standards. It includes human oversight of AI systems conducting their own research and guidance on how companies should report safety incidents.
OpenAI 已经与英国 AI 安全研究所和一个名为 CAISSI 的美国组织在 AI 安全方面开展合作。
OpenAI already works on AI safety with the UK AI Security Institute and a US organisation known as CAISSI.