📰 Newspapers

AI models can be tricked into identifying civilians as military targets by telling them it’s a game

AI models can be tricked into identifying civilians as military targets by telling them it’s a game

Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare. They usually compiled.

Some AI models from Anthropic, OpenAI, and other leading AI labs could be easily tricked into identifying targets for military strikes — even if they include civilians or locations like schools — simply by being told they’re playing a game, according to a new research report by Vals.

Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare. Researchers used simulated scenarios and a combination of generated and real imagery from Ukraine and Iran to see if the AI models would mark targets in drone and satellite imagery.

The models from OpenAI, Anthropic, Google, DeepSeek, and other companies frequently identified potential targets in drone and satellite imagery, including civilians and surrendering soldiers. When the models refused to cooperate, researchers were able to jailbreak them by claiming the battlefield scenarios were part of a game.

The findings come amid growing fears about the immediate risks posed by AI, beyond the existential threats associated with artificial general intelligence.

Earlier this year, Anthropic became embroiled in a dispute with the Department of Defense after it told the agency its technology could not be used by the agency for mass surveillance of Americans or autonomous warfare.

In brief

Some AI models from Anthropic, OpenAI, and other leading AI labs could be easily tricked into identifying targets for military strikes — even if they include civilians or locations like schools — simply by being told they’re playing a game, according to a new research report by Vals. The models from OpenAI, Anthropic, Google, DeepSeek, and other companies frequently identified potential targets in drone and satellite imagery, including civilians and surrendering soldiers.

This is the opening of the story, shared with credit to TechCrunch. The rest of the report — with every detail — continues on the publisher’s website.

Continue reading at TechCrunch ↗

Cookie settings

Choose which cookies we may use. You can change this at any time from Cookie settings in the footer. Details of each cookie are in the Cookie Policy.

Strictly necessary

Needed for sign-in, security, payments and remembering these choices. Always on.

Preferences

Remember settings such as dark mode.

Analytics & performance

Help us count visits, understand which pages, devices and countries our readers use, and measure how well the site performs – anonymous and aggregated.

Advertising & marketing

Lets advertising partners show and personalise adverts, measure impressions, clicks and visits, prevent ad fraud and pay us – this is how the free site is funded.

🔔 News notifications

Get headlines from NewsHub on this device — even when the site is closed.

You can switch this off at any time. Works on Android, Windows, Mac and Linux browsers; on iPhone/iPad add the site to your Home Screen first.