Government investigators find AI platforms produce terror plot plans in undercover op
GAO investigators bypassed AI safeguards on ChatGPT, Claude, Gemini and Grok, obtaining feasible plans for terrorist attacks in under 12 hours of testing.
FOX News
Full text, translation and AI summary — after signing in
- The full article in your language
- AI summary and translation from the original
- The same account works in the Suviy app
Comments
Sign in to join the conversation. Sign in
No comments yet.