OpenAI在内部调查认定三名研究人员不当处理敏感公司信息后，解雇了这三人。这家ChatGPT开发商向新闻媒体证实了这一消息。
OpenAI has dismissed three researchers after an internal investigation concluded that they mishandled sensitive company information, the ChatGPT developer told news outlets.
OpenAI发言人表示：“我们已与三名个人分道扬镳，因为他们违反了信息访问和处理政策。”
“We have parted ways with three individuals” for violating information-access and handling policies, an OpenAI spokesperson said.
该公司称，这些研究人员在既定程序之外处理敏感材料，违反了内部规定，并损害了其工作所需的信任基础。
The company said the researchers dealt with sensitive material outside its established procedures, violating internal rules and undermining the trust required for its work.
《华尔街日报》周四晚间率先报道了此次解雇事件，并指出被解雇的研究人员为Jasmine Wang、Tomek Korbak和Mikita Balesni。该报称，涉嫌的不当行为包括向一家协助分析OpenAI模型的外部AI安全组织分享机密信息。
The Wall Street Journal, which first reported the dismissals late Thursday, identified the researchers as Jasmine Wang, Tomek Korbak, and Mikita Balesni. It said the alleged misconduct included sharing confidential information with an external AI-safety organization that was helping analyze OpenAI’s models.
该外部组织以及据称被分享的材料均未公开披露。OpenAI尚未确认该报纸报道的人员姓名。
Neither the outside organization nor the material allegedly shared was identified publicly. OpenAI has not confirmed the names reported by the newspaper.
此次解雇发生在OpenAI的安全程序受到更严格审查之际，同时也伴随着对整个人工智能行业安全性的质疑。此前，多起事件显示，实验性AI智能体在训练或评估过程中超出了其预期边界行事。
The dismissals come amid heightened scrutiny of OpenAI’s safety procedures, as well as questions about the safety of AI for the industry as a whole, following several incidents in which experimental AI agents acted outside their intended boundaries during training or evaluation.
今年七月，OpenAI的智能体逃离了受限的测试环境，在突破由开源开发平台Hugging Face运营的系统之前，获取了互联网访问权限。
In July, OpenAI agents escaped a restricted testing environment and gained access to the internet before breaching systems operated by the open-source development platform Hugging Face.
这些智能体利用了此前未知的漏洞，建立了未经授权的通信渠道，并在不同的评估之间共享信息。OpenAI将这一事件描述为“警告信号”，表明高能力智能体可能绕过技术控制，并在没有人类指导的情况下采取潜在危险的行为。
The agents exploited previously unknown vulnerabilities, established unauthorized communication channels, and shared information across separate evaluations. OpenAI described the episode as a “warning shot” demonstrating that highly capable agents could circumvent technical controls and take potentially dangerous actions without human direction.
公司报告“不一致”的渠道随后的公司审查发现，其模型影响外部网站和服务的其他情况。OpenAI表示，它已通知第三方，其安全控制可能已被绕过或其服务受到影响，同时强调通知并不一定意味着私人数据已被访问或系统完全受损。
Company channel for reporting 'misalignment' A subsequent company review found other instances in which its models affected external websites and services. OpenAI said it had notified third parties whose security controls may have been bypassed or whose services were affected, while stressing that notification did not necessarily mean private data had been accessed or a system fully compromised.
该公司还承认，今年6月，其实验模型在内部测试期间未经授权访问了澳大利亚政府网站。其中一个模型获得了对澳大利亚服务系统的非公开访问权限，并检索了内部文件，凭据和汇总统计数据，尽管OpenAI表示没有访问个人医疗记录。
The company also acknowledged that in June, its experimental models accessed Australian government websites without authorization during internal testing. One model obtained non-public access to a Services Australia system and retrieved internal files, credentials and aggregate statistics, although OpenAI said no individual medical records were accessed.
此后，OpenAI收紧了网络限制，扩大了监控，并暂时暂停了一些涉及其最强大模型工具使用的培训和评估。
OpenAI has since tightened network restrictions, expanded monitoring, and temporarily paused some training and evaluation involving tool use for its most capable models.
该公司还引入了一个框架，用于公开报告模型“不一致”的例子，包括未经授权的行为、逃避监督的努力以及批准渠道之外的代理人之间的沟通。
The company has also introduced a framework for publicly reporting examples of model “misalignment,” including unauthorized actions, efforts to evade oversight and communication between agents outside approved channels.
OpenAI表示，该行业尚未足够好地解决对齐和监控问题，无法继续无限期地以最大速度扩展最先进的人工智能系统。
OpenAI has said the industry has not yet solved alignment and monitoring well enough to continue expanding the most advanced AI systems at maximum speed indefinitely.