AI 导读
提示词注入术语提出者 Simon Willison 认为，对最强模型（尤其 Anthropic 的模型）而言，提示词注入可能已不再是大问题，但对更便宜的弱模型仍是真实风险。Ethan Mollick 表示其测试结果与此一致，如今已无法简单通过注入提示词要求提高论文成绩。
正文
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.
@nateberkopec I'm cautiously starting to suspect it may not be a problem with today's strongest models - Anthropic in particular are very confident about their ability to avoid prompt injections - but it's still a real concern for cheaper, weaker models在 X 查看被引用的帖子
来源：Ethan Mollick · x.com