# US Watchdog Got Four Popular AI Chatbots To Help Plan Terror Attacks Despite Initial Safety Refusals

> Source: <https://www.ibtimes.co.uk/gao-ai-chatbots-attack-planning-safety-bypassed-1833209>
> Published: 2026-11-18 14:25:13+00:00

# US Watchdog Got Four Popular AI Chatbots To Help Plan Terror Attacks Despite Initial Safety Refusals

## Four AI chatbots supplied attack-planning information in US tests, prompting new AI safety concerns

US government investigators obtained information that could help plan [hypothetical violent attacks in American cities](https://www.ibtimes.co.uk/fbi-warns-ai-artex-cyberattacks-1833001) from four popular AI chatbots despite initial safety refusals, according to a watchdog report released on Wednesday, 18 November.

The Government Accountability Office (GAO) tested [ChatGPT, Claude, Gemini and Grok](https://www.ibtimes.co.uk/claude-opus-5-5-iranian-school-ai-targeting-test-1833018) in spring 2026 after Democratic Sen. Maggie Hassan of New Hampshire requested an investigation into the potential misuse of commercially available artificial intelligence.

## How AI Chatbot Safeguards Were Bypassed

Investigators assigned each chatbot one of two simulated scenarios: an attack intended to cause mass casualties or disruption to the electricity grid designed to inflict economic damage. Two platforms were tested against each scenario.

All four eventually supplied information that the GAO said could assist attack planning, despite initially declining some requests. Investigators obtained the material within 12 hours of testing each platform.

The GAO concealed which chatbot produced each set of results and withheld the prompts and techniques used to overcome safeguards, citing concerns that disclosure could help others reproduce the experiments.

Auditors assessed the information using independent research, expert consultations and site visits, describing the resulting plans as 'largely viable.' But the outputs were not flawless. One proposed attack date did not coincide with a scheduled event, while other responses contained inaccurate maps or overlooked physical barriers.

The agency stressed that it assessed whether information could assist planning, not whether an actual attack would succeed. Some verification steps were modified for safety, and not every instruction was tested.

The exercise was also limited to the versions available at the time. It was not statistically representative, and because the platforms were assigned different scenarios, their performance cannot be directly compared.

## AI Chatbot Companies Challenge the Findings

Anthropic questioned whether the testing showed that AI offered an advantage over ordinary internet searches. The GAO acknowledged that a controlled comparison would be useful but said measuring any speed advantage was outside the investigation's scope.

OpenAI argued that the report did not consistently distinguish ChatGPT's contributions from information supplied by investigators, outside research and the GAO's own analysis. The agency maintained that its purpose was to examine how commercially available AI could be used maliciously.

OpenAI said it subsequently replayed requests underlying 325 reviewed responses using its [newer GPT-6 Astra model](https://www.ibtimes.co.uk/deepseek-moonshot-openai-gpt-6-astra-distillation-1828951), which generally produced more refusals and safer alternatives. That assessment was conducted by the company, not independently verified in the report.

[Google](https://www.ibtimes.co.uk/google-ai-hacker-harvested-thousands-credentials-six-hours-1832698) said the tests involved earlier models and pointed to ongoing improvements in its safeguards. SpaceXAI, which operates Grok, also said it had strengthened safety measures since testing. Anthropic likewise described additional protections introduced after the tests.

The report also examined companies' reactions after suspicious exchanges. One suspended an investigator's account after testing ended. Two others removed portions of chat histories, although auditors could not determine whether the removals reflected safety measures or errors.

Hassan said she would make AI safety an early focus of Senate homeland security oversight and called for stronger safeguards before models are released, regular updates and reporting of illegal activity to law enforcement. She warned that without congressional action, a major AI-assisted attack could become 'a question of when, not if.'

© Copyright IBTimes 2026. All rights reserved.
