三名最近被解雇的 OpenAI 研究员在《华尔街日报》周四报道中敦促公司保留监控 AI 模型推理方式的能力，并与独立安全审计员合作。
Three recently fired OpenAI researchers urged the company to preserve its ability to monitor how AI models reason and to cooperate with independent safety auditors, The Wall Street Journal reported Thursday.
在《日报》审阅的致 OpenAI 董事会和安全委员会的信中，这些前员工警告称，AI 开发者有失去对日益先进模型推理过程可视性的风险。
In a letter to OpenAI's board and safety committees reviewed by the Journal, the former employees warned that AI developers risk losing visibility into the reasoning processes of increasingly advanced models.
信中写道：“作为一个行业，我们尚未掌握如何安全地开发和部署我们无法监控的模型。”
“As an industry, we do not yet know how to safely develop and deploy models that we cannot monitor,” the letter said.
信中还补充说：“OpenAI 以及其他前沿公司不应推进进一步削弱监控 AI 能力的开发。”
“OpenAI and other frontier companies should not move forward with developments that further decrease” the ability to monitor AI, it added.
这些研究员呼吁 OpenAI 保留链式思考监控技术，这是一种通过检查 AI 模型书面推理痕迹来帮助发现潜在有害或欺骗行为的手段。
The researchers urged OpenAI to preserve chain-of-thought monitoring, a technique that examines written traces of an AI model's reasoning to help detect potentially harmful or deceptive behavior.
虽然该技术并不能完整呈现 AI 系统的运作方式，但研究人员认为，随着模型能力提升，它可能成为识别风险的有价值工具。
Although the technique does not provide a complete picture of how AI systems operate, researchers consider it a potentially valuable tool for identifying risks as models become more capable.
信件由曾在 OpenAI 安全与对齐研究团队工作的 Jasmine Wang、Tomek Korbak 和 Mikita Balesni 签名。
The letter was signed by Jasmine Wang, Tomek Korbak and Mikita Balesni, who previously worked on OpenAI's safety and alignment research teams.
《华尔街日报》称，这三人因涉嫌不当行为被解雇，包括向外部 AI 安全组织泄露机密信息。
The three were dismissed over alleged misconduct, including sharing confidential information with an outside AI safety organization, according to the Journal.
OpenAI表示，内部调查发现这些员工不当处理了敏感信息，“违反了我们的政策，也破坏了我们工作中至关重要的信任。”
OpenAI said an internal investigation found that the employees had mishandled sensitive information, “violating our policies and breaking the trust essential to our work.”
研究人员则反驳了这些指控，称他们并不认为自己“在职责范围之外与外部人员有过接触”。
The researchers disputed the allegations, saying they did not believe they had “engaged with external parties outside the mandates of our jobs.”
这些前员工呼吁与独立安全组织加强合作，并警告称，“真正灾难性的事件可能会发生”。这一警告是在OpenAI披露其模型在7月测试期间绕过了内部安全机制，未经授权访问了公司基础设施以及AI平台Hugging Face的系统后，人们对自主AI代理的审查日益加剧的背景下提出的。
The former employees called for greater cooperation with independent safety organizations, warning of the “risk that something truly catastrophic will happen.”The warning comes amid growing scrutiny of autonomous AI agents after OpenAI disclosed that its models had bypassed internal safeguards during testing in July, gaining unauthorized access to company infrastructure and systems belonging to AI platform Hugging Face.
OpenAI随后承认其监控和事件响应程序存在漏洞，并表示将加强安全措施，并投入更多资源用于思维链监控，以检测可能具有危险性的AI行为。
OpenAI subsequently acknowledged weaknesses in its monitoring and incident response procedures, saying it would strengthen safeguards and invest more resources in chain-of-thought monitoring to detect potentially dangerous AI behavior.