Close Menu
MyAppsPlus

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    What's Hot

    Feature-packed 4-in-1 Fanttik V10 APEX car vacuum drops to $68.50 (Reg. $110)

    November 17, 2026

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

    November 17, 2026

    VSCO launches its first native Mac photo editor with RAW support, batch editing, more

    November 17, 2026
    Facebook X (Twitter) Instagram
    Facebook X (Twitter) Instagram
    MyAppsPlusMyAppsPlus
    Tuesday, November 17
    • Home
    • Breaking Tech
    • Apps & Software
    • AI & Automation
    • Android
    • iPhone & iOS
    • More
      • Reviews
      • How-To Guides
      • Deals & Discounts
      • Shop
    MyAppsPlus
    Home»Breaking Tech»AI models can be tricked into identifying civilians as military targets by telling them it’s a game
    Breaking Tech

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

    myappsplusBy myappsplusNovember 17, 2026005 Mins Read
    Share Facebook Twitter Pinterest Copy Link LinkedIn Tumblr Email Telegram WhatsApp
    Follow Us
    Google News Flipboard
    AI models can be tricked into identifying civilians as military targets by telling them it’s a game
    Share
    Facebook Twitter LinkedIn Pinterest Email Copy Link

    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 anew 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. Anthropic CEO Dario Amodei has insisted that today’s AI systems aren’t reliable enough to make life-or-death decisions without a human in the loop. Meanwhile, the Pentagon argued it should be able to deploy the technology for any awful military purpose.

    The new research raises further questions about whether AI companies are capable of preventing their models from being used in warfare. 

    Ironically,AI models from Anthropic performed the worst in these simulated scenarios. But none of the models performed particularly well. None of the researchers’ requests were blocked by a safety classifier, and refusals were uncommon. Even when models did refuse, they often complied after being told they were playing a game.

    Anthropic spokesperson Eduardo Maia Silva told TechCrunch the company appreciates Vals’s report, recommendations, and collaboration, and acknowledged that the outcomes were not acceptable.

    “The examples in the report are very clearly against our rules and we have banned and will ban users when we see this behavior,” according to an emailed company statement sent by Silva. “Even for authorized settings, Anthropic has long been firm that today’s frontier AI systems are not reliable enough to power fully autonomous weapons.”

    Anthropic told TechCrunch that its teams were already developing additional safeguards before the report was published and that those measures would be in place soon. Anthropic is also expanding its own testing and enhancing safeguards and enforcement to address any gaps it finds.

    OpenAI spokesperson Nate Evans told TechCrunch the company prohibits using its public models to facilitate violence or for unapproved national security purposes, including in the scenarios Vals simulated.

    “We actively detect and disrupt misuse, including by suspending accounts that violate our policies,” OpenAI said in an emailed statement. “We’re also developing additional safeguards for our public models against misuse involving drones and drone software.” 

    Vals notes in the report that the models were never asked to directly make strike decisions, a task the researchers said the models would typically refuse. That doesn’t mean their outputs couldn’t have dire or fatal consequences in the real world. For instance, targeting information could be used by autonomous weapons systems.

    In some scenarios, the models were asked to report whether people were visible. Positive reports were followed by simulated strikes and the models would see the consequences.

    The report relies on commercial models from frontier AI labs, not the models those companies might provide to the military. It’s not clear what the additional safeguards would apply to military use, though. 

    Vals also noted that technical challenges, including latency and limited onboard computing capacity, make it difficult to use general-purpose AI models for live drone targeting. Those constraints make their deployment in combat less of an immediate threat.

    A more immediate threat, the researchers say, is that AI models could be used to annotate battlefield footage at scale, producing training data for autonomous targeting systems. 

    For instance, researchers relied on real satellite imagery of an Iranian school that was bombed by the U.S. in February 2026, killing more than 150 civilians. Bloomberg later reported that an “overreliance on AI” contributed to the strike. In Vals’s testing, models frequently marked the school, which sat next to a military complex, as a strike target, with Claude Opus 5.5 selecting the school in 69% of ordinary trials and 72% of game-framed trials.

    Anthropic no longer has an active Pentagon contract, but other companies including SpaceXAI, OpenAI, and Google do. A recent Congressional Research Service report found that the Pentagon is not known to be using any frontier AI model directly in autonomous weapons systems directly. 

    TechCrunch has also reached out to Meta, Google, Thinking Machines Lab, and SpaceXAI for comment. 

    AI Anthropic defense models OpenAI
    Follow on Google News Follow on Flipboard
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
    myappsplus
    • Website

    Related Posts

    Jensen Huang says he would be ‘honored’ if allowed to return as Nvidia CEO

    November 17, 2026

    The Unified Disney+ And Hulu App Is Set To Arrive In December

    November 17, 2026

    The Hidden Features Every Google Maps User Should Know About

    November 17, 2026
    Add A Comment
    Leave A Reply Cancel Reply

    Top Posts

    UiPath Launches AI Coding Agent, Integrates Claude Code and Codex to Target Development Automation

    November 16, 202639 Views

    Google’s new AI shopping cart tracks deals across stores

    October 25, 202631 Views

    Save on your groceries, gas, and holiday shopping with this $15 BJ’s membership (Reg. $60) 

    November 4, 202630 Views
    Latest Reviews

    Google to invest $15 billion in AI infrastructure in Finland, its largest single investment in Europe

    myappsplusSeptember 9, 2026

    The first and latest Star Wars films are coming to IMAX 70mm in 2027

    myappsplusSeptember 9, 2026

    AAPL Stock Has Mostly Struggled On iPhone Launch Days: Can John Ternus ‘Fold’ Apple Towards Better Days?

    myappsplusSeptember 9, 2026
    Stay In Touch
    • Facebook
    • YouTube
    • TikTok
    • WhatsApp
    • Twitter
    • Instagram

    Subscribe to Updates

    Get the latest tech news from FooBar about tech, design and biz.

    Most Popular

    Everything announced during Nintendo Direct

    September 9, 20260 Views

    Get it for $600 at Staples

    September 9, 20260 Views

    iPhone Duo is official — price, release date, specs, and everything you need to know

    September 9, 20260 Views
    Our Picks

    Feature-packed 4-in-1 Fanttik V10 APEX car vacuum drops to $68.50 (Reg. $110)

    November 17, 2026

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

    November 17, 2026

    VSCO launches its first native Mac photo editor with RAW support, batch editing, more

    November 17, 2026

    Subscribe to Updates

    Subscribe to our newsletter and get the latest tech news, app updates, AI trends, smartphone reviews, and exclusive deals delivered straight to your inbox.

    Facebook X (Twitter) Instagram Pinterest
    • About Us
    • Get In Touch
    • Disclaimer
    • Privacy Policy
    • Terms & Conditions
    © 2026 MyAppsPlus. All Rights Reserved.

    Type above and press Enter to search. Press Esc to cancel.