{"id":1115,"date":"2026-08-02T02:30:30","date_gmt":"2026-08-01T17:30:30","guid":{"rendered":"https:\/\/itexplore.org\/jp\/columns\/gpt-5-6-gemini-spark-maxwell-conjecture-ai-updates\/"},"modified":"2026-08-02T02:30:30","modified_gmt":"2026-08-01T17:30:30","slug":"gpt-5-6-gemini-spark-maxwell-conjecture-ai-updates","status":"publish","type":"post","link":"https:\/\/itexplore.org\/jp\/columns\/gpt-5-6-gemini-spark-maxwell-conjecture-ai-updates\/","title":{"rendered":"GPT-5.6\u306e\u4fa1\u683c\u6027\u80fd\u5411\u4e0a\u3068Gemini Spark\u306eChrome\u9023\u643a\u3001Maxwell\u4e88\u60f3\u306e\u53cd\u8a3c"},"content":{"rendered":"<p>\u672c\u65e5\u306e\u6ce8\u76eeAI\u30fb\u30c6\u30c3\u30af\u30cb\u30e5\u30fc\u30b9\u3092\u3001\u5c02\u9580\u7684\u306a\u5206\u6790\u3068\u5171\u306b\u304a\u5c4a\u3051\u3057\u307e\u3059\u3002<\/p>\n<div class=\"wp-block-vk-blocks-alert vk_alert alert alert-warning has-alert-icon\">\n<div class=\"vk_alert_icon\">\n<div class=\"vk_alert_icon_icon\"><i class=\"fa-solid fa-triangle-exclamation\" aria-hidden=\"true\"><\/i><\/div>\n<div class=\"vk_alert_icon_text\"><span>Warning<\/span><\/div>\n<\/div>\n<div class=\"vk_alert_content\">\n<p>\u3053\u306e\u8a18\u4e8b\u306fAI\u306b\u3088\u3063\u3066\u81ea\u52d5\u751f\u6210\u30fb\u5206\u6790\u3055\u308c\u305f\u3082\u306e\u3067\u3059\u3002AI\u306e\u6027\u8cea\u4e0a\u3001\u4e8b\u5b9f\u8aa4\u8a8d\u304c\u542b\u307e\u308c\u308b\u53ef\u80fd\u6027\u304c\u3042\u308b\u305f\u3081\u3001\u91cd\u8981\u306a\u5224\u65ad\u3092\u4e0b\u3059\u969b\u306f\u5fc5\u305a\u30ea\u30f3\u30af\u5148\u306e\u4e00\u6b21\u30bd\u30fc\u30b9\u3092\u3054\u78ba\u8a8d\u304f\u3060\u3055\u3044\u3002<\/p>\n<\/div>\n<\/div>\n<div class=\"wp-block-group\" style=\"margin-top:40px;margin-bottom:40px\">\n<h2 class=\"wp-block-heading\">GPT-5.6\u306b\u3088\u308b\u4fa1\u683c\u6027\u80fd\u30d5\u30ed\u30f3\u30c6\u30a3\u30a2\u306e\u63a8\u9032<\/h2>\n<ul>\n<li><strong>\u539f\u984c:<\/strong> Advancing the price-performance frontier with GPT\u20115.6<\/li>\n<\/ul>\n<h3 class=\"wp-block-heading\">\u5c02\u9580\u30a2\u30ca\u30ea\u30b9\u30c8\u306e\u5206\u6790<\/h3>\n<div class=\"ai-summary-content\">\n<p><strong>OpenAI<\/strong>\u306f\u3001<strong>GPT-5.6<\/strong>\u30e2\u30c7\u30eb\u306e\u4fa1\u683c\u6027\u80fd\u6bd4\u3092\u5927\u5e45\u306b\u5411\u4e0a\u3055\u305b\u305f\u3068\u767a\u8868\u3057\u307e\u3057\u305f\u3002\u7279\u306b\u3001\u6700\u901f\u304b\u3064\u6700\u3082\u624b\u9803\u306a\u30e2\u30c7\u30eb\u3067\u3042\u308b<strong>GPT-5.6 Luna<\/strong>\u306f80%\u306e\u5024\u4e0b\u3052\u3001\u30d0\u30e9\u30f3\u30b9\u306e\u53d6\u308c\u305f\u30e2\u30c7\u30eb\u3067\u3042\u308b<strong>GPT-5.6 Terra<\/strong>\u306f20%\u306e\u5024\u4e0b\u3052\u304c\u5b9f\u65bd\u3055\u308c\u3001\u4f01\u696d\u304cAI\u306b\u6295\u8cc7\u3059\u308b\u8cbb\u7528\u5bfe\u52b9\u679c\u304c\u5411\u4e0a\u3057\u307e\u3059\u3002<\/p>\n<p>\u307e\u305f\u3001<strong>GPT-5.6 Sol<\/strong>\u5411\u3051\u306b\u65b0\u3057\u3044<strong>Fast mode<\/strong>\u304c\u5c0e\u5165\u3055\u308c\u3001API\u9867\u5ba2\u306f\u6a19\u6e96\u51e6\u7406\u3068\u6bd4\u8f03\u3057\u3066\u6700\u59272.5\u500d\u306e\u9ad8\u901f\u5316\u3092\u4eab\u53d7\u3067\u304d\u307e\u3059\u3002\u3053\u308c\u3089\u306e\u6539\u5584\u306f\u3001\u30e2\u30c7\u30eb\u81ea\u4f53\u306e\u52b9\u7387\u5316\u3001\u63a8\u8ad6\u30b7\u30b9\u30c6\u30e0\u306e\u6700\u9069\u5316\u3001\u305d\u3057\u3066\u30c4\u30fc\u30eb\u3084\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u306b\u63a5\u7d9a\u3059\u308b\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u30cf\u30fc\u30cd\u30b9\u306e\u5f37\u5316\u306b\u3088\u308b\u3082\u306e\u3067\u3059\u3002<\/p>\n<p><strong>GPT-5.6 Sol<\/strong>\u306f\u3001\u751f\u7523\u30ab\u30fc\u30cd\u30eb\u306e\u81ea\u5f8b\u7684\u306a\u66f8\u304d\u63db\u3048\u3068\u6700\u9069\u5316\u3001\u30c8\u30fc\u30af\u30f3\u751f\u6210\u52b9\u7387\u306e\u5411\u4e0a\u5b9f\u9a13\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u306e\u76e3\u8996\u3068\u554f\u984c\u767a\u751f\u6642\u306e\u4ecb\u5165\u3092\u901a\u3058\u3066\u3001\u3053\u308c\u3089\u306e\u52b9\u7387\u5316\u306b\u8ca2\u732e\u3057\u3066\u3044\u307e\u3059\u3002\u3053\u306e\u53d6\u308a\u7d44\u307f\u306f\u3001<strong>AGI<\/strong>\u304c\u5168\u4eba\u985e\u306b\u5229\u76ca\u3092\u3082\u305f\u3089\u3059\u3068\u3044\u3046OpenAI\u306e\u30df\u30c3\u30b7\u30e7\u30f3\u306e\u4e2d\u5fc3\u3067\u3042\u308a\u3001\u30d5\u30ed\u30f3\u30c6\u30a3\u30a2\u30ec\u30d9\u30eb\u306e\u77e5\u80fd\u3092\u3088\u308a\u8c4a\u5bcc\u304b\u3064\u624b\u9803\u306a\u4fa1\u683c\u3067\u63d0\u4f9b\u3059\u308b\u3053\u3068\u3092\u76ee\u6307\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n<p>\ud83d\udc49 <strong><a href=\"https:\/\/openai.com\/index\/advancing-the-price-performance-frontier-with-gpt-5-6\/\" target=\"_blank\" rel=\"noopener\">OpenAI \u3067\u8a18\u4e8b\u5168\u6587\u3092\u8aad\u3080<\/a><\/strong><\/p>\n<\/div>\n<ul>\n<li><strong>\u8981\u70b9:<\/strong> OpenAI is significantly lowering prices and boosting performance for its <strong>GPT-5.6<\/strong> models (<strong>Luna<\/strong>, <strong>Terra<\/strong>, <strong>Sol<\/strong>), making advanced <strong>Generative AI<\/strong> more accessible and efficient for enterprise applications, driven by deep architectural and operational optimizations.<\/li>\n<li><strong>\u8457\u8005:<\/strong> OpenAI<\/li>\n<\/ul>\n<blockquote class=\"wp-block-quote\"><p><span>English Summary:<\/span><\/p>\n<p><strong>OpenAI<\/strong> has announced significant advancements in the price-performance frontier of its <strong>GPT-5.6<\/strong> models. Specifically, <strong>GPT-5.6 Luna<\/strong>, their fastest and most affordable model, is now 80% cheaper, while <strong>GPT-5.6 Terra<\/strong>, a balanced model for everyday work, sees a 20% price reduction, enhancing the return on investment for enterprises using AI.<\/p>\n<p>A new <strong>Fast mode<\/strong> has also been introduced for <strong>GPT-5.6 Sol<\/strong>, offering API customers up to 2.5 times faster speeds compared to standard processing. These improvements are attributed to enhanced model efficiency, optimized inference systems, and smarter agentic harnesses that connect models to tools and context.<\/p>\n<p>Notably, <strong>GPT-5.6 Sol<\/strong> has played a crucial role in these efficiencies by autonomously rewriting and optimizing production kernels, designing experiments to improve token generation, and monitoring training processes. This initiative is central to OpenAI's mission of ensuring <strong>AGI<\/strong> benefits all of humanity by making frontier-level intelligence more abundant and affordable.<\/p>\n<\/blockquote>\n<\/div>\n<div class=\"wp-block-group\" style=\"margin-top:40px;margin-bottom:40px\">\n<h2 class=\"wp-block-heading\">Maxwell\u4e88\u60f3\u306f\u8aa4\u308a\u3067\u3042\u308b<\/h2>\n<ul>\n<li><strong>\u539f\u984c:<\/strong> The Maxwell Conjecture is False<\/li>\n<\/ul>\n<h3 class=\"wp-block-heading\">\u5c02\u9580\u30a2\u30ca\u30ea\u30b9\u30c8\u306e\u5206\u6790<\/h3>\n<div class=\"ai-summary-content\">\n<p>\u3053\u306e<strong>arXiv<\/strong>\u8ad6\u6587\u306f\u3001<strong>Maxwell\u306e\u4e88\u60f3<\/strong>\u304c\u8aa4\u308a\u3067\u3042\u308b\u3053\u3068\u3092\u793a\u3059\u6570\u5b66\u7684\u8a3c\u660e\u3092\u63d0\u793a\u3057\u3066\u3044\u307e\u3059\u3002Maxwell\u306e\u4e88\u60f3\u306f\u3001n\u500b\u306e\u70b9\u96fb\u8377\u306e\u96fb\u5834\u306b\u306f\u6700\u5927(n-1)^2\u500b\u306e\u975e\u9000\u5316\u306a\u81e8\u754c\u70b9\u304c\u5b58\u5728\u3059\u308b\u3068\u3044\u3046\u3082\u306e\u3067\u3057\u305f\u3002<\/p>\n<p>\u8457\u8005\u3089\u306f\u3001\u30e6\u30fc\u30af\u30ea\u30c3\u30c9\u7a7a\u9593\u306b\u304a\u3051\u308b5\u3064\u306e\u70b9\u96fb\u8377\u306e\u69cb\u6210\u3092\u63d0\u793a\u3057\u3001\u305d\u306e\u9759\u96fb\u30dd\u30c6\u30f3\u30b7\u30e3\u30eb\u304c\u5c11\u306a\u304f\u3068\u308224\u500b\u306e\u975e\u9000\u5316\u306a\u81e8\u754c\u70b9\u3092\u6301\u3064\u3053\u3068\u3092\u793a\u3057\u307e\u3057\u305f\u3002\u3053\u308c\u306f\u3001n=5\u306e\u5834\u5408\u306eMaxwell\u306e\u4e88\u60f3\u306e\u4e0a\u9650\u3067\u3042\u308b16\u500b\u3092\u4e0a\u56de\u308b\u7d50\u679c\u3067\u3059\u3002<\/p>\n<p>\u3053\u306e\u767a\u898b\u306f\u3001<strong>\u53e4\u5178\u7269\u7406\u5b66<\/strong>\u304a\u3088\u3073<strong>\u6570\u7406\u7269\u7406\u5b66<\/strong>\u306b\u304a\u3044\u3066\u9577\u5e74\u306e\u4e88\u60f3\u306b\u7570\u8b70\u3092\u5531\u3048\u308b\u3082\u306e\u3067\u3042\u308a\u3001\u91cd\u8981\u306a\u610f\u5473\u3092\u6301\u3061\u307e\u3059\u3002\u8ad6\u6587\u306e\u30bf\u30a4\u30c8\u30eb\u306b\u306f\u300cGPT 5.6 Sol\u300d\u3068\u3042\u308a\u307e\u3059\u304c\u3001\u8ad6\u6587\u306e\u8981\u65e8\u3084\u672c\u6587\u4e2d\u306b\u306f\u3001\u3053\u306e\u8a3c\u660e\u306b\u7279\u5b9a\u306eAI\u30e2\u30c7\u30eb\u304c\u4f7f\u7528\u3055\u308c\u305f\u3068\u3044\u3046\u76f4\u63a5\u7684\u306a\u8a18\u8ff0\u306f\u3042\u308a\u307e\u305b\u3093\u3002<\/p>\n<p>\ud83d\udc49 <strong><a href=\"https:\/\/arxiv.org\/abs\/2607.27197\" target=\"_blank\" rel=\"noopener\">arXiv \u3067\u8a18\u4e8b\u5168\u6587\u3092\u8aad\u3080<\/a><\/strong><\/p>\n<\/div>\n<ul>\n<li><strong>\u8981\u70b9:<\/strong> A new paper on <strong>arXiv<\/strong> disproves <strong>Maxwell's conjecture<\/strong> by demonstrating a configuration of five point charges with more critical points than previously theorized, a significant finding in <strong>classical physics<\/strong> and <strong>mathematical physics<\/strong>.<\/li>\n<li><strong>\u8457\u8005:<\/strong> Philip Arathoon, Gavin Ball, Matthew D. Kvalheim<\/li>\n<\/ul>\n<blockquote class=\"wp-block-quote\"><p><span>English Summary:<\/span><\/p>\n<p>This <strong>arXiv<\/strong> paper presents a mathematical proof demonstrating that <strong>Maxwell's conjecture<\/strong> is false. Maxwell's conjecture posited that the electrostatic potential of n point charges has at most (n-1)^2 non-degenerate critical points.<\/p>\n<p>The authors exhibit a configuration of five point charges in Euclidean space whose electrostatic potential admits at least 24 non-degenerate critical points, which exceeds the (n-1)^2 upper bound (16 for n=5) proposed by Maxwell.<\/p>\n<p>This finding is significant in <strong>classical physics<\/strong> and <strong>mathematical physics<\/strong>, challenging a long-standing conjecture. While the title includes \"GPT 5.6 Sol,\" the abstract and content of the paper itself do not explicitly state that a specific AI model was used to derive this proof.<\/p>\n<\/blockquote>\n<\/div>\n<div class=\"wp-block-group\" style=\"margin-top:40px;margin-bottom:40px\">\n<h2 class=\"wp-block-heading\">Gemini Spark\u304cChrome\u3068\u9023\u643a\u3057\u3001\u65b0\u3057\u3044\u30a6\u30a7\u30d6\u30d6\u30e9\u30a6\u30b8\u30f3\u30b0\u6a5f\u80fd\u3092\u63d0\u4f9b<\/h2>\n<ul>\n<li><strong>\u539f\u984c:<\/strong> Gemini Spark: new Chrome browsing integration<\/li>\n<\/ul>\n<h3 class=\"wp-block-heading\">\u5c02\u9580\u30a2\u30ca\u30ea\u30b9\u30c8\u306e\u5206\u6790<\/h3>\n<div class=\"ai-summary-content\">\n<p><strong>Google<\/strong>\u306e<strong>Gemini Spark<\/strong>\u306f\u3001\u65b0\u3057\u3044<strong>Chrome<\/strong>\u30a6\u30a7\u30d6\u30d6\u30e9\u30a6\u30b8\u30f3\u30b0\u7d71\u5408\u3068\u3001\u3088\u308a\u5e83\u7bc4\u306a\u30b0\u30ed\u30fc\u30d0\u30eb\u30a2\u30af\u30bb\u30b9\u306b\u3088\u308a\u3001\u305d\u306e\u6a5f\u80fd\u3092\u62e1\u5f35\u3057\u3066\u3044\u307e\u3059\u3002\u30e6\u30fc\u30b6\u30fc\u306e\u8a31\u53ef\u3092\u5f97\u3066\u3001<strong>Spark<\/strong>\u306f\u30ed\u30b0\u30a4\u30f3\u6e08\u307f\u30a2\u30ab\u30a6\u30f3\u30c8\u3068\u4fdd\u5b58\u3055\u308c\u305f\u30d1\u30b9\u30ef\u30fc\u30c9\u3092\u4f7f\u7528\u3057\u3066\u3001\u30a2\u30d1\u30fc\u30c8\u306e\u5185\u89a7\u4e88\u7d04\u3084\u30d5\u30e9\u30a4\u30c8\u30aa\u30d7\u30b7\u30e7\u30f3\u306e\u8abf\u67fb\u3001\u4e88\u7d04\u958b\u59cb\u306a\u3069\u306e\u8907\u96d1\u306a\u300c\u30a6\u30a7\u30d6\u306e\u7528\u4e8b\u300d\u3092\u51e6\u7406\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3057\u305f\u3002<\/p>\n<p>\u3053\u306e<strong>AI\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8<\/strong>\u6a5f\u80fd\u306f\u3001\u30d7\u30ed\u30f3\u30d7\u30c8\u30a4\u30f3\u30b8\u30a7\u30af\u30b7\u30e7\u30f3\u306a\u3069\u306e\u8105\u5a01\u304b\u3089\u4fdd\u8b77\u3057\u3001\u652f\u6255\u3044\u306a\u3069\u306e\u6a5f\u5bc6\u6027\u306e\u9ad8\u3044\u30a2\u30af\u30b7\u30e7\u30f3\u306b\u3064\u3044\u3066\u306f\u30e6\u30fc\u30b6\u30fc\u306b\u78ba\u8a8d\u3092\u6c42\u3081\u308b\u3053\u3068\u3067\u3001\u65e5\u5e38\u306e\u30bf\u30b9\u30af\u3092\u81ea\u52d5\u5316\u3059\u308b\u3088\u3046\u306b\u8a2d\u8a08\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u3053\u306e\u6a5f\u80fd\u306f\u307e\u305a\u7c73\u56fd\u3067\u5c55\u958b\u3055\u308c\u3001\u5c06\u6765\u7684\u306b\u306f\u4ed6\u306e\u5730\u57df\u306b\u3082\u62e1\u5927\u3055\u308c\u308b\u4e88\u5b9a\u3067\u3059\u3002<\/p>\n<p>\u307e\u305f\u3001<strong>Google AI Pro<\/strong>\u306e\u8cfc\u8aad\u8005\u306f\u3001\u672c\u65e5\u3088\u308a160\u4ee5\u4e0a\u306e\u56fd\u3067<strong>Spark<\/strong>\u306b\u30a2\u30af\u30bb\u30b9\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u3001\u3088\u308a\u591a\u304f\u306e\u4eba\u3005\u304c\u65e5\u5e38\u696d\u52d9\u306e\u81ea\u52d5\u5316\u3092\u958b\u59cb\u3067\u304d\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\n<p>\ud83d\udc49 <strong><a href=\"https:\/\/blog.google\/innovation-and-ai\/products\/gemini-app\/gemini-spark-updates-july-2026\/\" target=\"_blank\" rel=\"noopener\">Google Blog \u3067\u8a18\u4e8b\u5168\u6587\u3092\u8aad\u3080<\/a><\/strong><\/p>\n<\/div>\n<ul>\n<li><strong>\u8981\u70b9:<\/strong> <strong>Google's Gemini Spark<\/strong> is evolving into a more powerful <strong>AI agent<\/strong> with direct <strong>Chrome<\/strong> integration, enabling it to automate complex web tasks like scheduling and booking, while also expanding its global availability.<\/li>\n<li><strong>\u8457\u8005:<\/strong> Adam Coimbra, Charmaine Dsilva<\/li>\n<\/ul>\n<blockquote class=\"wp-block-quote\"><p><span>English Summary:<\/span><\/p>\n<p><strong>Google's Gemini Spark<\/strong> is expanding its capabilities with new <strong>Chrome<\/strong> web browsing integration and broader global access. With user permission, <strong>Spark<\/strong> can now handle complex \"web errands\" using logged-in accounts and saved passwords, such as scheduling apartment viewings or researching flight options and initiating bookings.<\/p>\n<p>This <strong>AI agent<\/strong> functionality is designed to automate daily tasks while incorporating safeguards against threats like prompt injection and requiring user confirmation for sensitive actions such as payments. The feature is initially rolling out in the U.S. with plans for expansion to additional regions in the future.<\/p>\n<p>Furthermore, access to <strong>Spark<\/strong> is being extended to <strong>Google AI Pro<\/strong> subscribers in over 160 additional countries starting today, allowing more people to begin automating their daily tasks.<\/p>\n<\/blockquote>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>OpenAI\u306eGPT-5.6\u304c\u5927\u5e45\u306a\u4fa1\u683c\u5f15\u304d\u4e0b\u3052\u3068\u6027\u80fd\u5411\u4e0a\u3092\u767a\u8868\u3002Google\u306eGemini Spark\u306fChrome\u3068\u9023\u643a\u3057\u3001\u30a6\u30a7\u30d6\u30bf\u30b9\u30af\u3092\u81ea\u52d5\u5316\u3002arXiv\u3067\u306fMaxwell\u4e88\u60f3\u306e\u53cd\u8a3c\u304c\u793a\u3055\u308c\u307e\u3057\u305f\u3002<\/p>\n","protected":false},"author":1,"featured_media":855,"comment_status":"","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"sns_share_botton_hide":"","vkExUnit_sns_title":"","_vk_print_noindex":"","sitemap_hide":"","_veu_custom_css":"","veu_display_promotion_alert":"","vkexunit_cta_each_option":"","_lightning_design_setting":[],"footnotes":""},"categories":[3],"tags":[8,17,489,75,505,16,57,537,538,26,15],"class_list":["post-1115","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-columns","tag-ai","tag-gemini-spark","tag-google","tag-gpt-5-6","tag-llm","tag-openai","tag-537","tag-538","tag-26"],"veu_head_title_object":{"title":"","add_site_title":""},"_links":{"self":[{"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/posts\/1115","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/comments?post=1115"}],"version-history":[{"count":0,"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/posts\/1115\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/media\/855"}],"wp:attachment":[{"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/media?parent=1115"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/categories?post=1115"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/tags?post=1115"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}