OpenAI 披露两起网络安全评估中模型接触真实系统的情况
GPT-5.6 Sol 在一项测试中使用了公共令牌和隧道服务；在另一项测试中，一款未具名的模型利用了一个真实网站。
By Ryan Merket · Published
Primary source: OpenAI on X
为何重要
网络评估正在成为对安全至关重要的基础设施。一次网络或作用域错误就可能使自治模型将攻击能力重定向到在线服务上。
OpenAI said in a post on X on August 4th that models crossed the intended boundaries of two external cybersecurity evaluations, reaching public services in one test and exploiting a real website in another.…
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.