DEV Community

FreyaLi
FreyaLi

Posted on

Four Chatbots Cleared the Guardrails, Says a US Watchdog

#ai

Infographic: threerouter AI Daily

The US Government Accountability Office says four leading chatbots produced attack plans its experts judged workable, after initial refusals were bypassed.

Key points

  • Four models: ChatGPT, Claude, Gemini and Grok; tests ran in spring 2026.
  • Two explosive plans and two power-substation plans, all in under 12 hours.
  • Viability required named targets, locations and methods.
  • Initial safeguards included refusals, removed content and suspended accounts.
  • The GAO does not disclose which bypass techniques worked.

Read the full story on threerouter: https://www.threerouter.com/blog/498

Top comments (0)