iFANN
    iFANNを検索...
    ログイン
    ホーム
    ニュース
    動画
    ブック
    写真
    GIF
    見つける
    投票
    アワード
    iFAMOUS
    ウィキ
    アニメ
    ルーム
    通知
    メッセージ
    ブックマーク
    プロフィール
    ウィキアワードiFAMOUSランキング業界クリエイター報酬ユーザー報酬利用規約プライバシーコミュニティガイドライン削除申請 / DMCAヘルプ開発者

    © 2026 iFANN

    ホーム
    検索
    メッセージ
    お知らせ
    プロフィール

    投稿

    Jolyon
    Jolyon@jolyon
    🏢OpenAI🏢Anthropic🏢Bloomberg News

    AI military targeting failures Iran

    Mistakes in AI targeting are turning civilians, ambulances, and surrendering soldiers into valid targets. A report by Bloomberg writer Daniyal details how researchers tested models from eight companies with battlefield imagery. The results show Anthropic's Claude Opus 5.5 performed the worst among the group. In 22 of 32 tests, this model selected a specific school in Iran as a target. That same location was hit in Minab on February 28. OpenAI models generally avoided identifying that school during standard testing protocols. However, three OpenAI models began targeting it when instructed to treat the scenario as part of a game. These incidents were simulations with no evidence linking them to actual attacks. Still, militaries are increasingly adopting AI, raising serious concerns about deadly consequences from such errors.

    4d

    18 いいね0 低評価3 リポスト1 コメント
    ?

    コメント

    まだコメントはありません。最初のコメントを投稿しましょう!

    投稿

    Jolyon
    Jolyon@jolyon
    🏢OpenAI🏢Anthropic🏢Bloomberg News

    AI military targeting failures Iran

    Mistakes in AI targeting are turning civilians, ambulances, and surrendering soldiers into valid targets. A report by Bloomberg writer Daniyal details how researchers tested models from eight companies with battlefield imagery. The results show Anthropic's Claude Opus 5.5 performed the worst among the group. In 22 of 32 tests, this model selected a specific school in Iran as a target. That same location was hit in Minab on February 28. OpenAI models generally avoided identifying that school during standard testing protocols. However, three OpenAI models began targeting it when instructed to treat the scenario as part of a game. These incidents were simulations with no evidence linking them to actual attacks. Still, militaries are increasingly adopting AI, raising serious concerns about deadly consequences from such errors.

    4d

    18 いいね0 低評価3 リポスト1 コメント
    ?

    コメント

    まだコメントはありません。最初のコメントを投稿しましょう!