← 返回归档

帖子详情

查看 X 原文
G
Gary Marcus@GaryMarcus
⚠️ PSA: “AI assistants may fall prey to prompt injection attacks” ⚠️ jeffrey lee funk @jeffreyleefunk Agentic AI requires us to trust our emails and other messages and we really shouldn't. There is too much hidden content and AI models can’t tell the difference between text it’s supposed to read and instructions it’s supposed to follow. futurism.com/artificial-int… 🔗 View Quoted Tweet
媒体保存失败：[Errno 104] Connection reset by peer
帖子 ID
2111764732315398318
Markdown
/app/data/archive/2026/10/18/GaryMarcus/2111764732315398318/post.md
保存状态
complete
查看 Markdown 内容
---
tweet_id: "2111764732315398318"
author: "GaryMarcus"
published_at: "2026-10-18T10:22:01+00:00"
source_url: "https://x.com/GaryMarcus/status/2111764732315398318"
---

⚠️ PSA: “AI assistants may fall prey to prompt injection attacks” ⚠️

![jeffrey lee funk](https://pbs.twimg.com/profile_images/1954463348915048448/Zm_D78vG_normal.jpg)

jeffrey lee funk@jeffreyleefunk

Agentic AI requires us to trust our emails and other messages and we really shouldn't. There is too much hidden content and AI models can’t tell the difference between text it’s supposed to read and instructions it’s supposed to follow. [futurism.com/artificial-int…](https://futurism.com/artificial-intelligence/ai-agent-sucker-phishing-emails)

[🔗 View Quoted Tweet](https://x.com/jeffreyleefunk/status/2111618146998345949)