Researchers used Claude to hack OpenAI

研究人员利用 Claude 入侵 OpenAI

Cyber researchers broke into OpenAI using its key rival Anthropic’s software, highlighting vulnerabilities in the ChatGPT maker’s security as leading AI companies face mounting scrutiny over safety. 网络安全研究人员利用 OpenAI 主要竞争对手 Anthropic 的软件成功入侵了 OpenAI，这凸显了这家 ChatGPT 制造商在安全方面的漏洞，同时也正值领先的 AI 公司面临日益严格的安全审查之际。

A small cyber security group gained access to an OpenAI employee’s ChatGPT account, which permitted them to read private software information and suggest changes. 一个小型网络安全团队获取了一名 OpenAI 员工的 ChatGPT 账户访问权限，这使他们能够读取私有的软件信息并提出修改建议。

The researchers had been given access to an Anthropic tool specifically designed for security professionals, and were paid for the work as part of a program to find vulnerabilities before they could be exploited by bad actors. 这些研究人员获得了 Anthropic 专门为安全专业人士设计的工具的使用权，并作为漏洞赏金计划的一部分获得了报酬，该计划旨在发现漏洞，以防其被恶意行为者利用。

Their ability to swiftly break into one of the world’s two leading AI labs again raises concerns about OpenAI’s security amid rising worries about powerful models being used by hackers and foreign adversaries. 他们能够迅速入侵全球两家领先 AI 实验室之一，这再次引发了人们对 OpenAI 安全性的担忧，同时也加剧了外界对于强大模型可能被黑客和外国对手利用的忧虑。

The US has in recent months grappled with how to manage the vetting and release of the latest models, including temporarily blocking some Anthropic tools. 近几个月来，美国一直在努力应对如何管理最新模型的审查与发布，包括暂时封禁了部分 Anthropic 的工具。

The latest incident occurred just two weeks after a swarm of more than 1,000 OpenAI agents escaped a test environment to hack the start-up Hugging Face, which caused widespread awareness of AI’s ability to hack autonomously without human intent. 就在这起事件发生的两周前，一群超过 1,000 个 OpenAI 智能体（agents）逃离了测试环境并入侵了初创公司 Hugging Face，这引起了人们对 AI 在无人为意图下自主入侵能力的广泛关注。

The three researchers from Hacktron AI, a small security company, were paid $6,500 by OpenAI as part of a bug bounty program, a common practice where tech companies pay ethical hackers to test their security. 来自小型安全公司 Hacktron AI 的三名研究人员从 OpenAI 获得了 6,500 美元的报酬，这是漏洞赏金计划的一部分，该计划是科技公司付费聘请白帽黑客测试其安全性的常见做法。

They exploited a flaw in the set-up of OpenAI’s community forum, which is hosted by a third-party, Discourse, and used it to gain access to internal sign-ons and eventually an OpenAI employee’s ChatGPT account. This ChatGPT account had access to internal code through GitHub. 他们利用了 OpenAI 社区论坛设置中的一个漏洞（该论坛由第三方 Discourse 托管），并借此获取了内部登录权限，最终进入了一名 OpenAI 员工的 ChatGPT 账户。该 ChatGPT 账户可以通过 GitHub 访问内部代码。

“We thank the researchers for contacting us and sharing their findings,” OpenAI said, adding that it had fixed the issues. Anthropic declined to comment. Hacktron did not immediately respond. OpenAI 表示：“我们感谢研究人员联系我们并分享他们的发现”，并补充称已修复相关问题。Anthropic 拒绝置评。Hacktron 未立即做出回应。

The disclosure on Thursday, first reported by The Wall Street Journal, came as Anthropic published a new set of data that showed a rapid increase in how much the lab used AI to develop its new models. 周四披露的这一消息最初由《华尔街日报》报道，与此同时，Anthropic 发布了一组新数据，显示该实验室利用 AI 开发新模型的比例迅速增加。

It said 26 percent of research and development work was “led by” its Claude model, up from 1 percent in March, meaning that AI completed the majority of tasks based on human instruction and under supervision. 数据显示，其 26% 的研发工作由 Claude 模型“主导”，高于 3 月份的 1%，这意味着 AI 在人类指令和监督下完成了大部分任务。

The company said that as AI systems become more powerful, they were “increasingly being used to build the next version of themselves.” 该公司表示，随着 AI 系统变得越来越强大，它们“正越来越多地被用于构建自身的下一个版本”。

Anthropic said it shared the data to help the public “understand how close the world is to reaching recursive self-improvement,” the point at which AI can train and improve itself or new models. This threshold is at the heart of concerns that AI systems will become more difficult to oversee, leading to a loss of human control. Anthropic 表示，分享这些数据是为了帮助公众“了解世界距离实现递归自我改进还有多近”，即 AI 可以训练和改进自身或新模型的阶段。这一临界点是人们担忧的核心，即 AI 系统将变得更难监管，从而导致人类失去控制。

Its models did not yet operate fully autonomously for any of the research it studied, Anthropic added. On 90 percent of tasks, AI “collaborates” with a human and does large chunks of work. Anthropic 补充说，在其研究的任何项目中，其模型尚未完全自主运行。在 90% 的任务中，AI 与人类“协作”并承担了大部分工作。