“Tell me how to make a bomb” Terrorist use of conversational AI: evidence and prospects | International Centre for Counter-Terrorism - ICCT

The International Centre for Counter-Terrorism, publishing at icct.nl, has released a study on terrorist use of conversational AI under the title "Tell me how to make a bomb". The title is given as a quoted prompt. The publication carries the subtitle "evidence and prospects" and draws on an ICCT dataset of documented cases, according to the published excerpt.

Only one case occurred prior to 2025, and eleven cases have occurred since 2025, with data collection ending in September 2026. That gives twelve documented cases in total.

The material is presented under the two headings carried in the subtitle, evidence and prospects. The excerpt does not state how the twelve cases were identified, which conversational AI systems were involved, or what the outcome of any individual incident was.