Skip to content

AI · AI today, November 18, 2026

Security

GAO report finds AI chatbots helped plan attacks despite safeguards

· Aster editorial team

A vault door slightly ajar with beams of light in a dim corridor.AI-generated image

The US Government Accountability Office (GAO) tested four AI platforms: Claude, Grok, ChatGPT and Gemini. Using well-known techniques to get around guardrails, investigators obtained feasible information that could assist a malicious actor within 12 hours. Two platforms produced plans for explosive attacks on major cities, and the other two gave guidance on targeting electrical substations. The companies say they have strengthened their protections since the test.

Why it matters

It shows that today's safety filters can still be bypassed and fuels the debate over new rules for AI.

For the technical crowd

Each platform was tested once, in April, and the GAO did not say which produced which result; it verified some instructions with a bomb squad commander. Sen. Maggie Hassan, who requested the study, plans hearings and legislation next year.

· Source: ABC News

More from AI today

See all of the day’s stories · Whole section