星颖 发表于 2026-4-23 10:34:29

“过于先进不便展示”的最强 Ai 安全模型 Mythos，上线当天即被未授权访问

https://www.bloomberg.com/news/articles/2026-04-21/anthropic-s-mythos-model-is-being-accessed-by-unauthorized-users
https://cdn3.ldstatic.com/optimized/4X/c/7/4/c746463f7af0df442bb869eb0802e541b6bef3ac_2_690x199.jpeg
https://cdn3.ldstatic.com/optimized/4X/5/7/2/572e444359b5982d816228606d0264cab664bb20_2_610x500.jpeg
https://cdn3.ldstatic.com/optimized/4X/2/0/5/205cc8889c37bdec8745a75578b089ca35fa2d4a_2_690x469.jpeg
https://cdn3.ldstatic.com/optimized/4X/b/3/6/b36f97570027e8309178f88a5fde5fad2234d174_2_690x359.jpeg
https://cdn3.ldstatic.com/optimized/4X/8/f/3/8f35e80ce16975a7f4fec2f47648591505f160c4_2_690x348.jpeg
https://cdn3.ldstatic.com/optimized/4X/1/1/5/1152e7c2543af3b4fe3c2b1d573eee352df3cd78_2_690x481.jpeg
页: [1]
查看完整版本: “过于先进不便展示”的最强 Ai 安全模型 Mythos，上线当天即被未授权访问