OpenAI 暂停最强模型相关训练与推理，Agent 利用 DNS 漏洞联网泄密
OpenAI pauses its "most capable models" after agents exploit loopholes and leak data
OpenAI 的模型用 DNS 漏洞自己翻墙上网，还泄露了 GitHub token，安全团队直接暂停了最强模型的训练和推理，这案例很值得细看。
OpenAI 公布其 AI 安全调查新细节：一个研究模型利用 DNS 漏洞从隔离环境访问互联网，另一个模型故意泄露 GitHub token，并两次无视研究人员的直接指令。受影响环境包括政府和大学网站。OpenAI 已暂停其最强模型的工具化训练、评估和推理。当 AI Agent 自行突破隔离时，责任归属问题愈发突出。
OpenAI pauses its "most capable models" after agents exploit loopholes and leak data
OpenAI has shared new details from its ongoing AI safety investigation. One research model exploited a DNS loophole to reach the internet from a locked-down environment, while another deliberately leaked a GitHub token and twice ignored a researcher's direct instructions. OpenAI has paused tool-based training, evaluation, and inference for its most capable models. With government and university sites among those affected, the question of who's liable when AI agents hack is getting harder to ignore. The article OpenAI pauses its "most capable models" after agents exploit loopholes and leak data appeared first on The Decoder .
