From the publisher feed

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

Read the original at Fox News ↗

Opens the original publisher page. Access, copyright and subscriptions are controlled by the publisher.

A useful next step

  1. Read the short publisher description here.
  2. Open the full report directly at the publisher.
  3. Compare this topic with other sources when useful.