AI models can be modified to assist terrorist and extremist activity, researchers report
Read the original at www.wired.com→“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.
Original headline: "AI Models Can Be Easily Modified to Assist Terrorist and Extremist Activity"
Coverage timeline
- Oct 14, 09:00 UTC Wired AI lead source AI Models Can Be Easily Modified to Assist Terrorist and Extremist Activity