INDBInternet News Database 2.5 Updated 1 min ago · 374 sources Show or hide images Light or dark

Government investigators find AI platforms produce terror plot plans in undercover op

Save Like Comments Compare coverage
Image from Fox News

Summary

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

Description from Fox News.

Who is covering this

  1. Fox News Right Factuality: Mostly factual US
    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.

Comments

Comments need JavaScript.