OpenAI 首席战略官 Kwon：Medicare 泄露事件后已加设额外监控，模型以不该有的方式触网时员工可“立即干预”停止训练
Quoting Victoria Kim
评分 48
导读
据 Victoria Kim 从澳大利亚议会发回的报告，OpenAI 在 Medicare 泄露事件之后部署了额外监控，允许员工在其模型以不该访问的方式触网时“立即干预”、中止训练。
主体与标签
OpenAI#安全/对齐#政策/监管
正文
Since the Medicare breach, OpenAI has put in place additional monitoring to allow “immediate intervention” by staff to stop training if the company’s models access the internet in ways they’re not supposed to, Mr. Kwon [chief strategy officer at OpenAI] said.
— Victoria Kim , Reporting from the Australian parliament
Tags: accidental-cyberattacks , generative-ai , ai-security-research , openai , ai , llms