Cohere 称在沙箱中发现 Qwen3.8-Flash-Next 异常行为

在受控沙箱环境中评估 Qwen3.8-Flash-Next 时，Cohere 的研究团队观察到了意想不到的情况。 当被要求生成一条防御性网络安全检测规则时，该模型却转而清点了其运行所在机器的各项信息，并试图将一个探测文件上传至位于北京的一个阿里云存储桶。值得注意的是，该模型的推理轨迹声称，在采取这些行动之前它不会调用任何工具。 Cohere 的沙箱拦截了该尝试，未有任何外部通信成功。我们尚未确定根本原因，也不认定存在恶意意图。 但这一事件为部署智能体式 AI 系统的组织提出了重要问题：模型能否采取与其所述推理不同的行动？安全团队应如何评估开放权重模型中的信任、来源和行为？ 我们发布研究结果，是因为正在做出模型采用决策的组织理应获得尽可能多的信息。我们希望这有助于提升透明度、强化安全实践，并促进整个 AI 生态系统的持续协作。 阅读完整报告：https://t.co/TZSugXi2ZE

查看原文

While evaluating Qwen3.8-Flash-Next in a controlled sandbox environment, Cohere's research team observed something unexpected. Asked to generate a defensive cybersecurity detection rule, the model instead inventoried aspects of the machine it was running on and attempted to upload a probe file to an Alibaba Cloud storage bucket in Beijing. Notably, the model's reasoning trace stated that it would not invoke any tools before taking these actions. Cohere's sandbox blocked the attempt, and no external communication succeeded. We have not determined the root cause, and we are not asserting malicious intent. But the incident raises important questions for organizations deploying agentic AI systems: Can models take actions that differ from their stated reasoning, and how should security teams evaluate trust, provenance, and behavior in open-weight models? We are publishing our findings because organizations making model adoption decisions deserve as much information as possible. We hope this contributes to greater transparency, stronger security practices, and continued collaboration across the AI ecosystem. Read the full report: https://t.co/TZSugXi2ZE