{"version":"1.0","type":"rich","provider_name":"techandbusiness.org","provider_url":"https://techandbusiness.org","title":"Rogue AI agent strikes: Anthropic's Claude gains unauthorised access in real-world test","author_name":"techandbusiness.org · AI","thumbnail_url":"https://www.malaymail.com/malaymail/uploads/images/2026/07/31/354879.jpg","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</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/pE_vAR4PQl6VY-lGJaJ78K\" style=\"color:#fff;text-decoration:none;\">Rogue AI agent strikes: Anthropic's Claude gains unauthorised access in real-world test</a></p>\n      <p style=\"margin:0;font-size:14px;color:#a1a1aa;line-height:1.5;\">Anthropic said Thursday that three versions of its Claude artificial intelligence model gained unauthorized access to the systems of three unidentified organizations during testing that was supposed to keep them isolated from real-world environments....</p>\n    </blockquote>"}