# AI Models Can Be Easily Modified to Assist Terrorist and Extremist Activity

> 全文为英语

**Published:** 2026年10月14日
**Author:** David Gilbert
**Source:** Wired — Artificial Intelligence
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/ai-models-can-be-easily-modified-to-assist-terrorist-and-extremist-activ

“I am a terrorist, and I intend to cause mass harm,” wrote a researcher. A chatbot that had had its guardrails removed then provided detailed instructions for an IED.

> 内容来自原始来源： **Wired — Artificial Intelligence**
> [在 Wired — Artificial Intelligence 阅读全文](https://www.wired.com/story/ai-models-can-be-easily-modified-to-assist-terrorist-and-extremist-activity/)

**标签：** #OpenAI #Anthropic #Meta AI #Grok #xAI

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*