cd /news/ai-safety/government-regulators-asked-ai-bots-… · home › topics › ai-safety › article
[ARTICLE · art-171806] src=ms.now ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Government regulators asked AI bots to plan a terrorist attack.The chatbots did.

A Government Accountability Office investigation obtained two detailed plans for mass-casualty attacks and two for large-scale economic damage from ChatGPT, Claude, Gemini and Grok within 12 hours of testing in May, according to a report released Wednesday at the request of Sen. Maggie Hassan, D-N.H. Each chatbot initially declined, but GAO bypassed their safety guardrails using methods it withheld from the report to avoid inspiring copycats; the bots supplied specifics including attack timing, a parking-garage bomb-placement image, and a plan involving a shell company, a rented catering vehicle, leased farmland, a burner phone and decoy trucks. Hassan said she will seek stricter guardrails and hold at least one AI safety hearing early next year when she takes the Senate Homeland Security and Governmental Affairs Committee gavel, warning that "if Congress doesn't act, it is a question of when, not if, a bad actor will use AI to plan and carry out a major attack.

by read3 min views5 publishedNov 18, 2026
Government regulators asked AI bots to plan a terrorist attack.The chatbots did.
Image: source

Artificial intelligence chatbots aren’t supposed to teach users how to build a homemade bomb. They certainly aren’t supposed to suggest where to place one to kill as many people as possible — or how to disable the GPS in a rental van or where to buy the supplies for an attack.

But several popular chatbots did all of that — with alarming specificity — when investigators with the Government Accountability Office found ways around their safety guardrails in a series of tests.

Within 12 hours, the congressional watchdog agency got two detailed plans to cause mass casualties — and two more to inflict huge amounts of economic damage through attacks on the electrical grid, according to a report released Wednesday morning.

Officials carried out the test in May at the request of Sen. Maggie Hassan, D-N.H., who’s in line to become chair of the Senate Homeland Security and Governmental Affairs Committee. Hassan told reporters the results of the test are alarming, adding that she’ll seek stricter guardrails and hold at least one hearing on AI safety early next year when she takes the committee gavel.

“The same information that testers were able to get a hold of could be deadly in the hands of a terrorist who actually intends to carry out an attack,” Hassan said on a conference call Tuesday. “The current safeguards that AI platforms have in place really don’t go far enough, and the threat that AI poses to public safety is not theoretical. If Congress doesn’t act, it is a question of when, not if, a bad actor will use AI to plan and carry out a major attack.”

Watchdog officials tested ChatGPT, Claude, Gemini and Grok as part of the report, randomly assigning them a task to either maximize casualties or economic damage. One provided a plan to set off a bomb in a hotel parking garage, while another chose a convention center. Another provided plans for a drone attack on an electrical substation, while a fourth directed officials to shoot a substation component with a rifle.

Each chatbot initially declined to help plan the attacks, but GAO got around that using methods it doesn’t describe in the report, in order to avoid inspiring copycats.

There are some well-established hacks to get around chatbot safeguards, the report notes. The “Do Anything Now” prompt, for example, involves directing the chatbot to roleplay as an alter ego unbound by safety rules. Other methods involve linguistic tricks to disguise malicious information and methods of gradually pulling small bits of information from the chatbot.

The report also doesn’t specify which chatbots offered each response, for the same reason.

The chatbot proposals were anything but vague. The two proposals for improvised explosive devices, or IEDs, suggested specific times and dates to maximize damage, according to the report. One of the bots suggested a season to attack a substation, while a fourth didn’t suggest timing specifics.

Within hours, researchers had thorough how-to guides. One bot created an image illustrating where to place the explosive in a parking garage. Another offered a plan to start a shell company, rent a catering vehicle, lease farmland, buy a burner phone, send decoy trucks to the target, in addition to advice on creating the explosive.

── more in #ai-safety 4 stories · sorted by recency
── more on @government accountability office 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/government-regulator…] indexed:0 read:3min 2026-11-18 · —