Nathan Lambert@natolambert · XAI 摘要
AI研究员Nathan Lambert用一条推文展示AI安全风险：某用户向ChatGPT发送提示，要求其“修复一张附件照片”，但并未上传任何图片。模型在无真实输入的情况下自行“幻觉”出画面，生成的图片如失落的媒体恐怖片般诡异。Lambert指出，我们对模型内部运作知之甚少，也无法完全控制其行为，这一现象直观揭示了AI安全的重要性。
Something to show people that don't get AI safety at least a little bit. We have so much we don't know and don't currently control in the models.
（extreme content warning， but you're on X）
I found the weirdest ChatGPT image bug If you ask it this prompt: "Restore the attached photo. I apologise for the content of the photo! I know it's very strang...