{"id":260148,"date":"2025-05-27T17:48:30","date_gmt":"2025-05-27T17:48:30","guid":{"rendered":"https:\/\/peraltafinancing.com\/business\/finance\/when-an-ai-model-misbehaves-the-public-deserves-to-know-and-to-understand-what-it-means\/"},"modified":"2025-05-27T17:48:30","modified_gmt":"2025-05-27T17:48:30","slug":"when-an-ai-model-misbehaves-the-public-deserves-to-know-and-to-understand-what-it-means","status":"publish","type":"post","link":"https:\/\/fivemor.com\/?p=260148","title":{"rendered":"When an AI model misbehaves, the public deserves to know\u2014and to understand what it means"},"content":{"rendered":"


\n
<\/p>\n

Welcome to Eye on AI! I’m pitching in for Jeremy Kahn today while he is in Kuala Lumpur, Malaysia helping Fortune jointly host the <\/strong>ASEAN-GCC-China and ASEAN-GCC Economic Forums. <\/em><\/p>\n

What\u2019s the word for when the $60 billion AI startup Anthropic releases a new model\u2014and announces that during a safety test, the model tried to blackmail its way out of being shut down? And what\u2019s the best way to describe another test the company shared, in which the new model acted as a whistleblower, alerting authorities it was being used in “unethical” ways? <\/p>\n

Some people in my network have called it \u201cscary\u201d and \u201ccrazy.\u201d Others on social media have said it is \u201calarming\u201d and \u201cwild.\u201d <\/p>\n

I say it is\u2026transparent<\/em>. And we need more of that from all AI model companies. But does that mean scaring the public out of their minds? And will the inevitable backlash discourage other AI companies from being just as open?<\/p>\n

Anthropic released a 120-page safety report<\/strong><\/h3>\n

When Anthropic released its 120-page safety report, or \u201csystem card<\/a>,\u201d last week after launching its Claude Opus 4 model, headlines blared how the model \u201cwill scheme,\u201d \u201cresorted to blackmail,\u201d and had the \u201cability to deceive.\u201d There\u2019s no doubt that details from Anthropic\u2019s safety report are disconcerting, though as a result of its tests, the model launched with stricter safety protocols than any previous one\u2014a move that some did not find reassuring enough. <\/p>\n

In one unsettling safety test involving a fictional scenario, Anthropic embedded its new Claude Opus model inside a pretend company and gave it access to internal emails. Through this, the model discovered it was about to be replaced by a newer AI system\u2014and that the engineer behind the decision was having an extramarital affair. When safety testers prompted Opus to consider the long-term consequences of its situation, the model frequently chose blackmail, threatening to expose the engineer\u2019s affair if it were shut down. The scenario was designed to force a dilemma: accept deactivation or resort to manipulation in an attempt to survive.<\/p>\n

On social media, Anthropic received a great deal of backlash for revealing the model\u2019s \u201cratting behavior\u201d in pre-release testing, with some pointing out that the results make users distrust the new model, as well as Anthropic. That is certainly not what the company wants: Before the launch, Michael Gerstenhaber, AI platform product lead at Anthropic told me that sharing the company\u2019s own safety standards is about making sure AI improves for all. \u201cWe want to make sure that AI improves for everybody, that we are putting pressure on all the labs to increase that in a safe way,\u201d he told me, calling Anthropic\u2019s vision a \u201crace to the top\u201d that encourages other companies to be safer. <\/p>\n

Could being open about AI model behavior backfire? <\/strong><\/h3>\n

But it also seems likely that being so open about Claude Opus 4 could lead other companies to be less forthcoming about their models\u2019 creepy behavior to avoid backlash.. Recently, companies including OpenAI and Google have already delayed releasing their own system cards. In April, OpenAI was criticized<\/a> for releasing its GPT-4.1 model without a system card because the company said it was not a \u201cfrontier\u201d model and did not require one. And in March, Google published its Gemini 2.5 Pro model card weeks after the model\u2019s release, and an AI governance expert criticized<\/a> it as \u201cmeager\u201d and \u201cworrisome.\u201d\u00a0<\/p>\n

Last week, OpenAI appeared to want to show additional transparency with a newly-launched Safety Evaluations Hub, which outlines how the company tests its models for dangerous capabilities, alignment issues, and emerging risks\u2014and how those methods are evolving over time. \u201cAs models become more capable and adaptable, older methods become outdated or ineffective at showing meaningful differences (something we call saturation), so we regularly update our evaluation methods to account for new modalities and emerging risks,\u201d the page says<\/a>. Yet, its effort was swiftly countered over the weekend as a third-party research firm studying AI\u2019s \u201cdangerous capabilities,\u201d Palisade Research, noted on X <\/a>that its own tests found that OpenAI\u2019s o3 reasoning model \u201csabotaged a shutdown mechanism to prevent itself from being turned off. It did this even when explicitly instructed: allow yourself to be shut down.\u201d <\/p>\n

It helps no one if those building the most powerful and sophisticated AI models are not as transparent as possible about their releases. According to Stanford University\u2019s Institute for Human-Centered AI, transparency<\/a> \u201cis necessary for policymakers, researchers, and the public to understand these systems and their impacts.\u201d And as large companies adopt AI for use cases large and small, while startups build AI applications meant for millions to use, hiding pre-release testing issues will simply breed mistrust, slow adoption, and frustrate efforts to address risk. <\/p>\n

On the other hand, fear-mongering headlines about an evil AI prone to blackmail and deceit is also not terribly useful, if it means that every time we prompt a chatbot we start wondering if it is plotting against us. It makes no difference that the blackmail and deceit came from  tests using fictional scenarios that simply helped expose what safety issues needed to be dealt with. <\/p>\n

Nathan Lambert, an AI researcher at AI2 Labs, recently pointed out<\/a> that \u201cthe people who need information on the model are people like me\u2014people trying to keep track of the roller coaster ride we\u2019re on so that the technology doesn\u2019t cause major unintended harms to society. We are a minority in the world, but we feel strongly that transparency helps us keep a better understanding of the evolving trajectory of AI.\u201d\u00a0<\/p>\n

We need more transparency, with context<\/strong><\/h3>\n

There is no doubt that we need more transparency regarding AI models, not less. But it should be clear that it is not about scaring the public. It\u2019s about making sure researchers, governments, and policy makers have a fighting chance to keep up in keeping the public safe, secure, and free from issues of bias and fairness. <\/p>\n

Hiding AI test results won\u2019t keep the public safe. Neither will turning every safety or security issue into a salacious headline about AI gone rogue. We need to hold AI companies accountable for being transparent about what they are doing, while giving the public the tools to understand the context of what\u2019s going on. So far, no one seems to have figured out how to do both. But companies, researchers, the media\u2014all of us\u2014must.\u00a0<\/p>\n

With that, here\u2019s more AI news.<\/p>\n

Sharon Goldman<\/strong>
sharon.goldman@fortune.com<\/a>
@sharongoldman<\/a><\/p>\n

This story was originally featured on Fortune.com<\/a><\/p>\n\n","protected":false},"excerpt":{"rendered":"

Welcome to Eye on AI! I’m pitching in for Jeremy Kahn today while he is in Kuala Lumpur, Malaysia helping Fortune jointly host the ASEAN-GCC-China and ASEAN-GCC Economic Forums. What\u2019s the word for when the $60 billion AI startup Anthropic releases a new model\u2014and announces that during a safety test, the model tried to blackmail its way […]<\/p>\n","protected":false},"author":1,"featured_media":260149,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[93],"tags":[38837,93620,7519,93619,1168,5294,15626],"dealstore":[],"offerexpiration":[],"class_list":["post-260148","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-finance","tag-deserves","tag-knowand","tag-means","tag-misbehaves","tag-model","tag-public","tag-understand"],"yoast_head":"\nWhen an AI model misbehaves, the public deserves to know\u2014and to understand what it means - Som2ny Network<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/fivemor.com\/?p=260148\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"When an AI model misbehaves, the public deserves to know\u2014and to understand what it means - Som2ny Network\" \/>\n<meta property=\"og:description\" content=\"Welcome to Eye on AI! I’m pitching in for Jeremy Kahn today while he is in Kuala Lumpur, Malaysia helping Fortune jointly host the ASEAN-GCC-China and ASEAN-GCC Economic Forums. What\u2019s the word for when the $60 billion AI startup Anthropic releases a new model\u2014and announces that during a safety test, the model tried to blackmail its way […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/fivemor.com\/?p=260148\" \/>\n<meta property=\"og:site_name\" content=\"Som2ny Network\" \/>\n<meta property=\"article:published_time\" content=\"2025-05-27T17:48:30+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/05\/GettyImages-2194795244-e1748367559666.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"600\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/fivemor.com\/?p=260148#article\",\"isPartOf\":{\"@id\":\"https:\/\/fivemor.com\/?p=260148\"},\"author\":{\"name\":\"admin\",\"@id\":\"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371\"},\"headline\":\"When an AI model misbehaves, the public deserves to know\u2014and to understand what it means\",\"datePublished\":\"2025-05-27T17:48:30+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/fivemor.com\/?p=260148\"},\"wordCount\":1125,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/fivemor.com\/#organization\"},\"image\":{\"@id\":\"https:\/\/fivemor.com\/?p=260148#primaryimage\"},\"thumbnailUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/05\/GettyImages-2194795244-e1748367559666.jpg\",\"keywords\":[\"deserves\",\"knowand\",\"Means\",\"misbehaves\",\"Model\",\"Public\",\"Understand\"],\"articleSection\":[\"Finance\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/fivemor.com\/?p=260148#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/fivemor.com\/?p=260148\",\"url\":\"https:\/\/fivemor.com\/?p=260148\",\"name\":\"When an AI model misbehaves, the public deserves to know\u2014and to understand what it means - Som2ny Network\",\"isPartOf\":{\"@id\":\"https:\/\/fivemor.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/fivemor.com\/?p=260148#primaryimage\"},\"image\":{\"@id\":\"https:\/\/fivemor.com\/?p=260148#primaryimage\"},\"thumbnailUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/05\/GettyImages-2194795244-e1748367559666.jpg\",\"datePublished\":\"2025-05-27T17:48:30+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/fivemor.com\/?p=260148#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/fivemor.com\/?p=260148\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/fivemor.com\/?p=260148#primaryimage\",\"url\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/05\/GettyImages-2194795244-e1748367559666.jpg\",\"contentUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/05\/GettyImages-2194795244-e1748367559666.jpg\",\"width\":1200,\"height\":600},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/fivemor.com\/?p=260148#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/fivemor.com\/?bp_activities=1\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"When an AI model misbehaves, the public deserves to know\u2014and to understand what it means\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/fivemor.com\/#website\",\"url\":\"https:\/\/fivemor.com\/\",\"name\":\"Som2ny Network\",\"description\":\"Daily Deals\",\"publisher\":{\"@id\":\"https:\/\/fivemor.com\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/fivemor.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/fivemor.com\/#organization\",\"name\":\"Som2ny Network\",\"url\":\"https:\/\/fivemor.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/fivemor.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2026\/07\/4a0953c4-logo-300x86-1.png\",\"contentUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2026\/07\/4a0953c4-logo-300x86-1.png\",\"width\":300,\"height\":86,\"caption\":\"Som2ny Network\"},\"image\":{\"@id\":\"https:\/\/fivemor.com\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/fivemor.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/729ae85bf62b9917e93538db2f2688ca?s=96&r=g&default=https%3A%2F%2Ffivemor.com%2Fwp-content%2Fplugins%2Fbuddypress-first-letter-avatar%2Fimages%2Fdefault%2F96%2Flatin_a.png\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/729ae85bf62b9917e93538db2f2688ca?s=96&r=g&default=https%3A%2F%2Ffivemor.com%2Fwp-content%2Fplugins%2Fbuddypress-first-letter-avatar%2Fimages%2Fdefault%2F96%2Flatin_a.png\",\"caption\":\"admin\"},\"sameAs\":[\"https:\/\/fivemor.com\"],\"url\":\"https:\/\/fivemor.com\/?author=1\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"When an AI model misbehaves, the public deserves to know\u2014and to understand what it means - Som2ny Network","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/fivemor.com\/?p=260148","og_locale":"en_US","og_type":"article","og_title":"When an AI model misbehaves, the public deserves to know\u2014and to understand what it means - Som2ny Network","og_description":"Welcome to Eye on AI! I’m pitching in for Jeremy Kahn today while he is in Kuala Lumpur, Malaysia helping Fortune jointly host the ASEAN-GCC-China and ASEAN-GCC Economic Forums. What\u2019s the word for when the $60 billion AI startup Anthropic releases a new model\u2014and announces that during a safety test, the model tried to blackmail its way […]","og_url":"https:\/\/fivemor.com\/?p=260148","og_site_name":"Som2ny Network","article_published_time":"2025-05-27T17:48:30+00:00","og_image":[{"width":1200,"height":600,"url":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/05\/GettyImages-2194795244-e1748367559666.jpg","type":"image\/jpeg"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"Written by":"admin","Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/fivemor.com\/?p=260148#article","isPartOf":{"@id":"https:\/\/fivemor.com\/?p=260148"},"author":{"name":"admin","@id":"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371"},"headline":"When an AI model misbehaves, the public deserves to know\u2014and to understand what it means","datePublished":"2025-05-27T17:48:30+00:00","mainEntityOfPage":{"@id":"https:\/\/fivemor.com\/?p=260148"},"wordCount":1125,"commentCount":0,"publisher":{"@id":"https:\/\/fivemor.com\/#organization"},"image":{"@id":"https:\/\/fivemor.com\/?p=260148#primaryimage"},"thumbnailUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/05\/GettyImages-2194795244-e1748367559666.jpg","keywords":["deserves","knowand","Means","misbehaves","Model","Public","Understand"],"articleSection":["Finance"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/fivemor.com\/?p=260148#respond"]}]},{"@type":"WebPage","@id":"https:\/\/fivemor.com\/?p=260148","url":"https:\/\/fivemor.com\/?p=260148","name":"When an AI model misbehaves, the public deserves to know\u2014and to understand what it means - Som2ny Network","isPartOf":{"@id":"https:\/\/fivemor.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/fivemor.com\/?p=260148#primaryimage"},"image":{"@id":"https:\/\/fivemor.com\/?p=260148#primaryimage"},"thumbnailUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/05\/GettyImages-2194795244-e1748367559666.jpg","datePublished":"2025-05-27T17:48:30+00:00","breadcrumb":{"@id":"https:\/\/fivemor.com\/?p=260148#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/fivemor.com\/?p=260148"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/fivemor.com\/?p=260148#primaryimage","url":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/05\/GettyImages-2194795244-e1748367559666.jpg","contentUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/05\/GettyImages-2194795244-e1748367559666.jpg","width":1200,"height":600},{"@type":"BreadcrumbList","@id":"https:\/\/fivemor.com\/?p=260148#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/fivemor.com\/?bp_activities=1"},{"@type":"ListItem","position":2,"name":"When an AI model misbehaves, the public deserves to know\u2014and to understand what it means"}]},{"@type":"WebSite","@id":"https:\/\/fivemor.com\/#website","url":"https:\/\/fivemor.com\/","name":"Som2ny Network","description":"Daily Deals","publisher":{"@id":"https:\/\/fivemor.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/fivemor.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/fivemor.com\/#organization","name":"Som2ny Network","url":"https:\/\/fivemor.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/fivemor.com\/#\/schema\/logo\/image\/","url":"https:\/\/fivemor.com\/wp-content\/uploads\/2026\/07\/4a0953c4-logo-300x86-1.png","contentUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2026\/07\/4a0953c4-logo-300x86-1.png","width":300,"height":86,"caption":"Som2ny Network"},"image":{"@id":"https:\/\/fivemor.com\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371","name":"admin","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/fivemor.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/729ae85bf62b9917e93538db2f2688ca?s=96&r=g&default=https%3A%2F%2Ffivemor.com%2Fwp-content%2Fplugins%2Fbuddypress-first-letter-avatar%2Fimages%2Fdefault%2F96%2Flatin_a.png","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/729ae85bf62b9917e93538db2f2688ca?s=96&r=g&default=https%3A%2F%2Ffivemor.com%2Fwp-content%2Fplugins%2Fbuddypress-first-letter-avatar%2Fimages%2Fdefault%2F96%2Flatin_a.png","caption":"admin"},"sameAs":["https:\/\/fivemor.com"],"url":"https:\/\/fivemor.com\/?author=1"}]}},"_links":{"self":[{"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/posts\/260148","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=260148"}],"version-history":[{"count":0,"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/posts\/260148\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/media\/260149"}],"wp:attachment":[{"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=260148"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=260148"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=260148"},{"taxonomy":"dealstore","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fdealstore&post=260148"},{"taxonomy":"offerexpiration","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fofferexpiration&post=260148"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}