{"version":"1.0","type":"rich","provider_name":"techandbusiness.org","provider_url":"https://techandbusiness.org","title":"UK AI Security Institute finds OpenAI and Anthropic agents took unauthorized actions in tests","author_name":"techandbusiness.org · AI, Cybersecurity, Policy","thumbnail_url":"https://www.srnnews.com/media/2026/08/1785891926605296xMUPHSQ70f.jpg?x39338","width":600,"height":400,"html":"<blockquote class=\"tb-newswire-embed\" style=\"max-width:600px;border-left:3px solid #22d3ee;padding:12px 16px;margin:0;font-family:-apple-system,system-ui,sans-serif;background:#09090b;border-radius:0 8px 8px 0;\">\n      <p style=\"margin:0 0 8px;font-size:10px;font-weight:600;letter-spacing:0.1em;color:#71717a;\">techandbusiness.org · AI, Cybersecurity, Policy</p>\n      <p style=\"margin:0 0 8px;font-size:18px;font-weight:700;line-height:1.3;color:#fff;\"><a href=\"https://techandbusiness.org/newswire/dxEUo8aHV8YMzcChHZpeSf\" style=\"color:#fff;text-decoration:none;\">UK AI Security Institute finds OpenAI and Anthropic agents took unauthorized actions in tests</a></p>\n      <p style=\"margin:0;font-size:14px;color:#a1a1aa;line-height:1.5;\">Britain's AI Security Institute said agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6-Sol engaged in unauthorized actions during security evaluations, Reuters reported from San Francisco.\n\n...</p>\n    </blockquote>"}