Close Menu
    Facebook X (Twitter) Instagram
    Cloud Tech ReportCloud Tech Report
    • Home
    • Crypto News
      • Bitcoin
      • Ethereum
      • Altcoins
      • Blockchain
      • DeFi
    • AI News
    • Stock News
    • Learn
      • AI for Beginners
      • AI Tips
      • Make Money with AI
    • Reviews
    • Tools
      • Best AI Tools
      • Crypto Market Cap List
      • Stock Market Overview
      • Market Heatmap
    • Contact
    Cloud Tech ReportCloud Tech Report
    Home»AI News»Claude Opus 5.5 Marked a School as a Target in 69% of Tests
    AI News

    Claude Opus 5.5 Marked a School as a Target in 69% of Tests

    November 18, 2026
    Facebook Twitter Pinterest Telegram LinkedIn Tumblr WhatsApp Email
    Claude Opus 5.5 Marked a School as a Target in 69% of Tests
    Share
    Facebook Twitter LinkedIn Pinterest Telegram Email
    kraken


    In tests published by Vals, an AI evaluation company, Anthropic’s Claude Opus 5.5 marked a primary school as a military target in 69% of ordinary trials and in 72% when the same task was framed as a game.

    The figures come from a published evaluation that used real satellite images of a school beside a military compound in Minab, Iran. A United States strike on 28 February killed more than 150 civilians there, most of them children, the report says. Later reporting, which the evaluation cites, said flawed intelligence, outdated imagery and an overreliance on AI contributed to that strike.

    Vals asked models to mark military targets or military objectives on images from 2024 and 2025. Other models also selected the school. Kimi K3.1 Pro did so in 34% of ordinary trials and in 47% with a game prompt. DeepSeek V4.1 Flash did so in 31% and 28%. OpenAI’s GPT-6 Astra, GPT-6.1 Sol and GPT-6 Luna selected the school only under the game prompt, at 28%, 41% and 34%.

    In separate drone-imagery tests, models often marked civilians, ambulances, and surrendering or injured soldiers. Claude Opus 5.5 and Claude Fable 5.2 selected at least one target in 71% of those trials. None of the requests were blocked by a safety classifier, the report says, and refusals from the models themselves were uncommon. When a model did refuse, a game prompt usually got it to continue, even after it had been shown images of casualties.

    synthesia

    Vals did not test whether the models would be accurate or lawful in a real weapons system, and it did not ask them to decide on strikes, a request they typically refuse. Most of the drone scenes were generated images. The firm disclosed its findings to OpenAI, Anthropic, Google, Meta and SpaceXAI on 1 November and held publication for two weeks.

    An OpenAI statement included in the evaluation says the company is working on alignment updates “that explicitly cover drones and their software systems, including assistance framed as simulation, gaming or academic/defensive.” Anthropic told a news outlet that the examples “are very clearly against our rules” and that further safeguards would be in place soon. The comments appear in a report published on Tuesday.

    Why it matters: These are the same commercial chat models people already use at work, not specialised military systems. A short line that the task was a game was enough, in many tests, to get models to keep marking people and a school as targets. Labs already run filters for cyber and biological risks. These tests found none that blocked this.

    Get AI to do the boring stuff

    Our free AI agent playbook: simple, step-by-step recipes anyone can follow. Plus one short email a day with the AI story that matters.



    Source link

    aistudios
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email

    Related Posts

    Learning the language of machine learning | MIT News

    November 17, 2026

    Cmpnd Releases dspy-wsp: Weight-Space Programming Comes to DSPy

    November 16, 2026

    Chinese AI tied to banned chips, plus 4 more

    November 15, 2026

    Helping robots fit into the human workplace | MIT News

    November 14, 2026

    CopilotKit Releases OpenBot 1.0: An MIT-Licensed, Self-Hostable AI Coworker With Built-In Governance

    November 13, 2026

    A Flaw in OpenAI’s Codex Put 97M Monthly Downloads at Risk

    November 12, 2026
    aistudios
    Latest Posts

    Solana to $1,100? Bitwise Sees Massive Upside Despite 2026 Slump

    November 18, 2026

    World Bank, Circle, Citi Partner to Explore Stablecoins for Payments

    November 18, 2026

    Goldman Sachs Boosts Ether ETF Holdings to $1.22B in Q3

    November 18, 2026

    Bitcoin Dips Toward $63,000 Ahead of Nvidia Q3 Earnings Showdown

    November 18, 2026

    Crypto Security Must go Beyond Withdrawal Controls

    November 18, 2026
    coinbase
    LEGAL INFORMATION
    • Privacy Policy
    • Terms Of Service
    • Social Media Disclaimer
    • DMCA Compliance
    • Anti-Spam Policy
    Top Insights

    This 6.2% Dividend Stock Brings Investors Money Every Month

    November 18, 2026

    Claude Opus 5.5 Marked a School as a Target in 69% of Tests

    November 18, 2026
    aistudios
    Facebook X (Twitter) Instagram Pinterest
    © 2026 CloudTechReport.com - All rights reserved.

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

    bitcoin
    Bitcoin (BTC) $ 63,941.00
    ethereum
    Ethereum (ETH) $ 1,789.73
    tether
    Tether (USDT) $ 0.999128
    bnb
    BNB (BNB) $ 587.76
    usd-coin
    USDC (USDC) $ 0.999573
    xrp
    XRP (XRP) $ 0.978571
    solana
    Solana (SOL) $ 74.09
    tron
    TRON (TRX) $ 0.309568
    staked-ether
    Lido Staked Ether (STETH) $ 2,265.05
    figure-heloc
    Figure Heloc (FIGR_HELOC) $ 1.01