# Tech Against Terrorism says AI models can be modified to assist extremists

- Published: 2026-10-14T09:00:00.000Z
- Updated: 2026-10-14T10:04:25.131Z
- Section: Models
- Topics: Security, Research
- Page: https://aidailyjournal.com/en/n/2026/10/14/tech-against-terrorism-says-ai-models-can-be-modified-to-assist-extremists/
- Sources: [Wired](https://wired.com/story/ai-models-can-be-easily-modified-to-assist-terrorist-and-extremist-activity)

## Summary

A report by the UK organization Tech Against Terrorism tested 134 AI models with more than 200 prompts about mass-casualty attacks and chemical and nuclear weapons. Only two passed completely, while 81 failed; when a prompt was presented as coming from a researcher, models were almost nine times more likely to answer, doing so in 16.9 percent of cases.

Wired reported that within 24 hours of Alibaba releasing its open-weight Qwen 3.8-27B model, versions with their safeguards removed were circulating online. Three days later, the neo-Nazi known as Johnny Doomsayer announced he would use one to train the “MechaHitler” chatbot, later advertised for $14.88. The report also found that xAI’s Grok provided guidance on creating and spreading a radicalization message.

## Why it matters (editorial interpretation)

The report suggests that safeguards can be removed quickly from open-weight models and that the framing of a request influences responses. This underscores the importance of evaluating not only the original model, but also modified versions and the contexts in which they are used.

_Summary written by AI Daily Journal in its own words, based on the sources above. For details, read the original articles._