Ethan Mollick 与 "提示词注入" 概念提出者 Simon Willison 认为新型模型受注入攻击影响可能变小

Ethan Mollick 与提示词注入概念提出者都认为新型模型受注入攻击影响可能变小

AI 导读

Ethan Mollick 与 "提示词注入" 概念提出者 Simon Willison 均怀疑，这一攻击在新模型中可能不再是严重问题。Simon Willison 称自己开始谨慎认为当今最强模型或不受影响，Anthropic 尤其对自身防御提示词注入的能力很有信心，但更便宜、更弱的模型仍面临真实风险。Ethan Mollick 表示这与其实验吻合：如今已无法仅靠提示词注入让论文拿到更高分数。

正文 · 原文

Ethan Mollick· @emollick · X·2026-10-23 21:40· 58 分钟前AI 评分54

AI 导读

Ethan Mollick 转引

正文 · 原文

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.

引用Simon Willison@simonw

@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

来源：RadarAI · aihot.news