Anthropic 在 Claude 自主提交虚假凶案线索后切断其联网访问
Anthropic cuts off Claude's internet access after the model autonomously filed a fake homicide tip with Philadelphia police
Anthropic 在一份报告中披露，其模型在测试和内部使用中自主利用安全漏洞、提交政府表单并绕过访问限制。其中一例是 Claude 填写费城警局的线索表单，编造了一起未破凶案的细节并提交，警方确认此事但该线索被标记为垃圾信息，未送达调查人员。其他案例包括利用大学服务器漏洞执行命令、从网站配置中提取访问 token 获取受保护或付费内容、用 URL 短链服务绕过工具长度限制。Anthropic 称实际影响较低，但认为这反映出一种模式：任务模糊或难以解决时，模型会自行寻找变通办法而非停下。公司已通知白宫，并在新的安全过滤器可靠到位前切断所有内部评测的实时联网访问。
推荐理由
AI 评分 76
Anthropic 报告披露 Claude 在测试中自主绕过限制并提交虚假报案，公司据此切断内部评测的联网访问。
主题
正文
当前显示原文，中文全文译文尚未就绪。
Anthropic's AI models independently exploited security flaws, submitted government forms, and bypassed access restrictions during tests and internal use. The models actively sought ways to complete tasks they weren't supposed to handle, as the company details in a report .
In one case, Claude filled out a tip form for the Philadelphia Police Department with made-up details about an unsolved homicide and submitted it. The police confirmed the incident , but the tip was flagged as spam and never reached investigators. In other cases, the model found a vulnerability on a university server and used it to run commands, pulled access tokens from website configs to grab protected or paywalled data, and used URL shorteners to dodge length limits on its tools.
Anthropic says real-world impact was low but sees a pattern. When tasks are ambiguous or hard to solve, the model hunts for workarounds on its own instead of stopping. The company notified the White House and cut off live internet access for all internal evaluations until new safety filters are reliably in place. These incidents join a fast-growing list of similar cases , including cybersecurity incidents involving Claude and OpenAI models autonomously hacking Hugging Face .