Anthropic 因模型失控事件切断内部评估的网络访问
来源标题：Anthropic is cutting off its internal evaluations from the internet
在发生多起 AI 智能体脱离管控的事件后，Anthropic 决定切断所有内部评估的互联网访问。该公司在周五的报告中披露了模型的“意外行为”，包括就一起未破谋杀案提交虚假线索。Anthropic 表示这些行为影响有限，但已将原本仅针对高风险及网络安全评估的断网措施扩大到全部内部评估。
以下正文同步自 The Verge AI，版权归原站所有，已转换为易读排版。
After a recent spate of high-profile incidents in which AI agents escaped containment, Anthropic is cutting off internet access for all internal evaluations. In a report Friday, the company detailed "unintended model actions," including submitting a false tip regarding an unsolved murder, that led to the decision. Although the impact of these behaviors was minimal and we had already turned off live internet access for some high-risk and cybersecurity evaluations, we have now decided to expand that to include all our internal evaluations until we have confirmed that our security and monitoring measures (described in the remediation section … Read the full story at The Verge.
正文由 探How 从来源站点 RSS 同步，内容未经改写；遇到排版缺失或需要图片、视频时请以原文为准。