Science & technology | I predict a riot

How America built an AI tool to predict Taliban attacks

“Raven Sentry” was a successful experiment in open-source intelligence 

 U.S. Soldier surveys the back of a CH-47 Chinook during flight over Kabul, Afghanistan.
Photograph: Jeffery Harris/Polaris/Eyevine

In the summer of 2020 American intelligence analysts in Afghanistan got a warning from “Raven Sentry”, an artificial-intelligence (AI) tool that they had been operating for a few months. There was a high probability, the AI told them, of a violent attack in Jalalabad, the capital of the eastern Nangarhar province, at the beginning of July. It would probably cause between 20 and 40 casualties. The attack came, a little late, on August 2nd, when Islamic State struck the city’s prison, killing some 29 people.

Explore more

Chinese business goes global

From the August 3rd 2024 edition

Discover stories from this section and more in the list of contents

Explore the edition

More from Science & technology

How to reduce the risk of developing dementia

A healthy lifestyle can prevent or delay almost half of cases

GPT, Claude, Llama? How to tell which AI model is best

Beware model-makers marking their own homework


Gene-editing drugs are moving from lab to clinic at lightning speed

The promising treatments still face technical and economic hurdles, though


How Ukraine’s new tech foils Russian aerial attacks

It is pioneering acoustic detection, with surprising success

The deep sea is home to “dark oxygen”

Nodules on the seabed, rather than photosynthesis, are the source of the gas

Augmented reality offers a safer driving experience

Complete with holograms on the windscreen