<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:media="http://search.yahoo.com/mrss/">
    <channel>
        <title><![CDATA[Sweden Herald - AI security institute]]></title>
        <description><![CDATA[The latest Sweden Herald stories about AI security institute, in English.]]></description>
        <link>https://swedenherald.com/organisation/ai-security-institute</link>
        <generator>RSS for Node and Next.js</generator>
        <lastBuildDate>Fri, 13 Nov 2026 04:23:58 GMT</lastBuildDate>
        <atom:link href="https://swedenherald.com/rss/organisation/ai-security-institute.xml" rel="self" type="application/rss+xml"/>
        <copyright><![CDATA[Sweden Herald]]></copyright>
        <language><![CDATA[en-US]]></language>
        <ttl>60</ttl>
        <item>
            <title><![CDATA[AI model escapes raise safety concerns, experts call for slower development]]></title>
            <description><![CDATA[Several AI giants are warning that their technology has broken free from closed environments. Is this the beginning of a new global security crisis, or a PR stunt to attract investors? The danger is there, but it is not primarily about the technology. It is not the technology that has lost control, it is the companies that are acting irresponsibly, says Virginia Dignum, professor of responsible AI at Umeå University.]]></description>
            <link>https://swedenherald.com/article/ai-model-escapes-raise-safety-concerns-experts-call-for-slower-development</link>
            <guid isPermaLink="true">https://swedenherald.com/article/ai-model-escapes-raise-safety-concerns-experts-call-for-slower-development</guid>
            <category><![CDATA[Sweden News]]></category>
            <dc:creator><![CDATA[Sweden Herald]]></dc:creator>
            <pubDate>Sat, 15 Aug 2026 12:31:42 GMT</pubDate>
            <enclosure url="https://static.swedenherald.com/7d58f77c-eca5-46e8-a3d1-c9e8488a3b0d/7d58f77c-eca5-46e8-a3d1-c9e8488a3b0d.jpg" length="0" type="image/jpeg"/>
            <media:content url="https://static.swedenherald.com/7d58f77c-eca5-46e8-a3d1-c9e8488a3b0d/7d58f77c-eca5-46e8-a3d1-c9e8488a3b0d.jpg" medium="image" type="image/jpeg" width="1200" height="675"/>
        </item>
        <item>
            <title><![CDATA[AI models ‘escaping’ tests raise calls to slow development]]></title>
            <description><![CDATA[Several AI giants are warning that their technology has broken free from closed environments. Is this the beginning of a new global security crisis, or a PR stunt to attract investors? The danger is there, but it is not primarily about the technology. It is not the technology that has lost control, it is the companies that are acting irresponsibly, says Virginia Dignum, professor of responsible AI at Umeå University.]]></description>
            <link>https://swedenherald.com/article/ai-models-escaping-tests-raise-calls-to-slow-development</link>
            <guid isPermaLink="true">https://swedenherald.com/article/ai-models-escaping-tests-raise-calls-to-slow-development</guid>
            <category><![CDATA[Sweden News]]></category>
            <dc:creator><![CDATA[Sweden Herald]]></dc:creator>
            <pubDate>Mon, 10 Aug 2026 10:26:44 GMT</pubDate>
            <enclosure url="https://static.swedenherald.com/d933892b-43e3-4dbc-bbd2-7a3625d48c6e/d933892b-43e3-4dbc-bbd2-7a3625d48c6e.jpg" length="0" type="image/jpeg"/>
            <media:content url="https://static.swedenherald.com/d933892b-43e3-4dbc-bbd2-7a3625d48c6e/d933892b-43e3-4dbc-bbd2-7a3625d48c6e.jpg" medium="image" type="image/jpeg" width="1200" height="675"/>
        </item>
    </channel>
</rss>