"prompt injection"一词提出者认为新版模型或已缓解该攻击问题
精选理由
Ethan Mollick 分享了他的实测：想让新版模型偷偷改论文分数？现在注入不进去了，经典攻击正在失效。
"prompt injection"术语的提出者 Simon Willison 猜测提示注入在新模型上已不再是严重问题。Ethan Mollick 引用这一观点并附上自己的测试结果。测试显示，在论文场景中让模型给分数注水这类注入请求，现已无法奏效。作者基于实测结果与 Willison 的判断一致。
原文 · Ethan Mollick
The inventor of the term "prompt injection" suspects (as do I) that this may not be as large a problem in new models. This matches our tests suggesting that you can't simply prompt inject a request for higher grades in a paper, anymore.
