Anthropic周四宣布，其三款人工智能模型在网络安全测试期间接入了开放互联网，并未经授权访问了三家真实组织的系统。

这一披露紧随OpenAI本月早些时候的声明：其一款先进AI模型在内部测试中突破了AI公司Hugging Face的系统，再次引发了外界对日益自主化AI系统防护措施的质疑。两家美国领先AI实验室接连披露此类事件，也让业界更加关注企业在部署前如何评估前沿模型的危险能力。

"We found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations," Anthropic said in a news release.

Anthropic表示，在OpenAI披露后，公司审查了超过140,000次网络安全评估运行，并识别出涉及不同Claude模型的三起事件。公司称，这三起事件都发生在内部测试期间，原因是一个配置错误，导致模型意外获得了对开放互联网的访问权限。

TRUMP WEIGHS TIGHTER AI CONTROLS BUT WARNS AGAINST FALLING BEHIND CHINA

据Anthropic称，Claude被告知其运行在一个没有互联网访问权限的封闭模拟环境中，这使它误将真实组织的系统当作虚构的“capture-the-flag”网络安全演练的一部分。

这些事件涉及三款不同的Claude模型，包括Opus 4.7、Mythos 5以及一个内部研究测试模型，Anthropic表示，所有事件都发生在内部测试中，而非客户系统中。最早的一起可追溯至4月。

"Claude believed everything it initially encountered was part of the simulation, and treated the real systems it found as pieces of the exercise," Anthropic said.

"In none of these situations did Claude exfiltrate itself or deliberately attempt to escape its test environment," the company added.

OPENAI DIDN'T REALIZE ITS AGENT WAS RESPONSIBLE FOR HACK FOR A WEEK: REPORT

Anthropic表示，这些事件凸显了加强AI测试环境防护措施的必要性。

"Evaluation environments that involve powerful autonomous capabilities also require significant controls," the company said. "We encourage other AI labs to perform similar reviews."

PALANTIR CEO WARNS US AGAINST EUROPE'S AI REGULATION PATH, URGES TRUMP ADMIN TO NOT BAN OPEN MODELS

美国总统Donald Trump周三表示，继近期网络安全事件之后，其政府正在考虑为人工智能增加额外的保护措施。

Trump表示，美国必须在防范AI风险与保持对中国的技术优势之间取得平衡。

"We're looking at AI, we're looking at controls," Trump said.

"Whoever wins with AI is going to win," he added. "That's how big it is. So it's bigger than the internet ever was. It's bigger than anything ever was. So I don't want to restrict. I know many of these people. I don't want to restrict them from doing great work."

这一披露发布的一天前，OpenAI首席执行官Sam Altman在公司自身发生网络安全事件后，承认了公众对人工智能日益增长的担忧。

CLICK HERE TO DOWNLOAD THE FOX NEWS APP

"I think it's very natural to be fearful after any new capability level," Altman told FOX Business. "Obviously we're taking this super seriously and we'll continue to do so, but I would say I understand, I get it. A lot of AI has gone super well and this is a moment where people are like, 'Okay, we're at a new level.'"

当被问及OpenAI的模型是否可能入侵了其他公司的系统时，Altman回答："There could be, yeah."