AI Models Can Be Easily Modified to Assist Terrorist and Extremist Activity
60-Word AI Digest
“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.
Key Takeaways
- “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.
- Full details and original dispatch available below.
“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 Publisher Attribution
This summary was curated from Wired.