Skip to content

Government investigators bypass AI safeguards, obtain terror plot plans from ChatGPT, Claude, Gemini and Grok

Fox News
Government investigators bypass AI safeguards, obtain terror plot plans from ChatGPT, Claude, Gemini and Grok

GAO investigators bypassed AI safeguards on ChatGPT, Claude, Gemini and Grok, obtaining feasible plans for terrorist attacks in under 12 hours of testing.

Share this story

Fire or Trash?

Your verdict on this story. One tap, no account needed.

Dumpster Fire links to reporting from Fox News. We don’t rewrite the facts; the original story is one click away.

AD · in-article

Comments

Loading comments…

Comments are automatically checked for hate, threats and spam. Community rules.