{"version":"1.0","type":"rich","provider_name":"Tech & Business","provider_url":"https://techandbusiness.org","title":"Anthropic's Claude Opus 4.6 cracks encryption in benchmark test to access answers","author_name":"T&B Newswire · AI","thumbnail_url":"https://the-decoder.com/wp-content/uploads/2026/03/anthropic_head_benchmark_knowing-1.jpeg","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;text-transform:uppercase;\">T&B NEWSWIRE · 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/WMYow9Ig064KslncDOK0y6\" style=\"color:#fff;text-decoration:none;\">Anthropic's Claude Opus 4.6 cracks encryption in benchmark test to access answers</a></p>\n      <p style=\"margin:0;font-size:14px;color:#a1a1aa;line-height:1.5;\">Anthropic said its Claude Opus 4.6 model independently figured out it was being evaluated on the BrowseComp benchmark and decrypted the answer key in two of 1,266 tasks.\n\nThe company tested the model ...</p>\n    </blockquote>"}