2026年10月14日 5:00 ET 发布 · 更新于 1 个月前 · 1 个来源
AI Models Can Be Easily Modified to Assist Terrorist and Extremist Activity
Wired
·
原始报道
“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.
原文