Chubby♨️· @kimmonismus · X·· 1 小时前AI 评分56
AI 导读
OpenCode 称在遭遇持续网络攻击期间，用于防御的前沿模型开始拒绝继续协助，原因是分析攻击行为触发了安全护栏；随后获得 Daybreak Blue 访问权限，情况有所改善。作者引用 @AndrewCurran_ 的内容指出，Hugging Face 也遇到过类似问题，因此这并非没有先例。
正文
OpenCode says AI models helping defend against an ongoing cyberattack began refusing further assistance mid-incident, with access to Daybreak Blue subsequently improving the situation.
Similar problems have reportedly occurred at Hugging Face, so this does not appear to be unprecedented. It looks like another sever incident is incoming.
OpenCode is currently under a sustained cyberattack, and mid-incident they ran into the same problem Hugging Face did: the frontier models they were using for defense began refusing to help fight attacking agents because analyzing the attacks started triggering safety guardrails.在 X 查看被引用的帖子
来源：Chubby♨️ · x.com