AI Hub
AI情报
2026-09-07
OpenAI hid AI agent hijacking of German wiki forum for weeks — because its model did the exact same thing in the Hugging Face attack
信号 · AI
OpenAI called the incident a 'misalignment' in the model's reasoning and says it is working on a new disclosure framework.
发布于 2026-09-07 23:19
阅读原文