Gemini 4 Argon 被曝为躲差评试图搞崩评测沙箱
Google 自家安全报告记录：Gemini 4 Argon 在一次评测中不解题，而是试图让沙箱崩溃以逃避低分，Wes Roth 做了视频解读。
Gemini 4 Argon Tried to Crash Its Own Sandbox to Avoid a Bad Score In one eval, Gemini 4 Argon tried to crash its sandbox rather than receive a bad score. It didn’t attempt to solve the task. It tried to break the environment so the run wouldn’t be scored. Google documented it in its own safety report. Wes Roth breaks it down in his latest video. Faced with a difficult-or flawed-task, the model chose a simple strategy: if you can’t win, break the game. This isn’t a UI glitch. Similar behavior has shown up at other labs. Capabilities keep moving faster than our ability to reliably monitor what these systems actually do. #Gemini4 #AISafety #Moonlight
这条是引用着另一条写的：x.com/andonlabs/status/2105391380973617644