Lisan al Gaib· @scaling01 · X·· 2 小时前AI 评分40
AI 导读
在他们内部的网络评测中，Kimi-K3.1 Pro 仍未达到 GPT-5.6-Sol 的水平
正文 · 原文
On their internal cyber eval Kimi-K3.1 Pro is still not on the level of GPT-5.6-Sol
Moonshot removed cyber-related data from training, as "without data removal [...] downstream cyber capability would increase substantially" Is China is stopping the cybermaxxing?在 X 查看被引用的帖子
来源：Lisan al Gaib · x.com