{"id":58610,"date":"2025-04-30T14:35:00","date_gmt":"2025-04-30T14:35:00","guid":{"rendered":"http:\/\/f2772638-a090-48e5-85d2-aa9d35cc4a4e"},"modified":"2025-04-30T14:35:00","modified_gmt":"2025-04-30T14:35:00","slug":"openai-recalls-gpt-4o-update-for-being-too-agreeable","status":"publish","type":"post","link":"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/","title":{"rendered":"OpenAI recalls GPT-4o update for being too agreeable"},"content":{"rendered":"<figure class=\"c-shortcodeImage u-clearfix c-shortcodeImage-large\">\n<div class=\"c-shortcodeImage_imageContainer\">\n<div class=\"c-shortcodeImage_image\"><picture class=\"c-cmsImage c-cmsImage_loaded\"><source media=\"(max-width: 767px)\" srcset=\"https:\/\/www.zdnet.com\/a\/img\/resize\/d80ddeb718dba5f3f7ec5051d38451d114b3d0fe\/2025\/04\/30\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\/gettyimages-2210029399.jpg?auto=webp&amp;width=768\" alt=\"OpenAI\"><source media=\"(max-width: 1023px)\" srcset=\"https:\/\/www.zdnet.com\/a\/img\/resize\/b90587cb67b1942659520edb5ac22be5a832d138\/2025\/04\/30\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\/gettyimages-2210029399.jpg?auto=webp&amp;width=1024\" alt=\"OpenAI\"><source media=\"(max-width: 1440px)\" srcset=\"https:\/\/www.zdnet.com\/a\/img\/resize\/73ea29d36f15045b547f071df53f0acf24759605\/2025\/04\/30\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\/gettyimages-2210029399.jpg?auto=webp&amp;width=1280\" alt=\"OpenAI\"><img decoding=\"async\" src=\"https:\/\/www.zdnet.com\/a\/img\/resize\/73ea29d36f15045b547f071df53f0acf24759605\/2025\/04\/30\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\/gettyimages-2210029399.jpg?auto=webp&amp;width=1280\" alt=\"OpenAI\" width=\"1280\" height=\"852.7186663922618\" fetchpriority=\"low\"><\/picture><\/div>\n<p> <!----><\/div><figcaption> <span class=\"c-shortcodeImage_credit g-outer-spacing-top-xsmall u-block\">Didem Mente\/Anadolu via Getty Images<\/span><\/figcaption><\/figure>\n<p>Late last week, OpenAI updated <a href=\"https:\/\/www.zdnet.com\/article\/how-to-use-chatgpt-a-beginners-guide-to-the-most-popular-ai-chatbot\/\">GPT-4o<\/a>, the primary model behind its popular chatbot, ChatGPT. But it is already being recalled.<\/p>\n<p><strong>Also:&nbsp;<\/strong><a href=\"https:\/\/www.zdnet.com\/article\/anthropic-finds-alarming-emerging-trends-in-claude-misuse-report\/\"><strong>Anthropic finds alarming &#8217;emerging trends&#8217; in Claude misuse report<\/strong><\/a><\/p>\n<p>On Tuesday, CEO Sam Altman announced <a href=\"https:\/\/x.com\/sama\/status\/1917291637962858735\" target=\"_blank\" rel=\"noopener nofollow\" class=\"c-regularLink\">via an X post<\/a> that OpenAI &#8220;started rolling back&#8221; the update due to user complaints about its responses. In some examples, reacting to somewhat ridiculous test prompts, ChatGPT encouraged <a href=\"https:\/\/x.com\/ai_for_success\/status\/1916556522571604264\" target=\"_blank\" rel=\"noopener nofollow\" class=\"c-regularLink\">risky medical choices<\/a>, <a href=\"https:\/\/x.com\/thinkbuildnext\/status\/1916250081579217243\" target=\"_blank\" rel=\"noopener nofollow\" class=\"c-regularLink\">rude and antisocial behavior<\/a>, and <a href=\"https:\/\/x.com\/fabianstelzer\/status\/1916372374091423984\" target=\"_blank\" rel=\"noopener nofollow\" class=\"c-regularLink\">valued a toaster over animal life<\/a>. <\/p>\n<p>(Disclosure: Ziff Davis, ZDNET&#8217;s parent company, filed an April 2025 lawsuit against OpenAI, alleging it infringed Ziff Davis copyrights in training and operating its AI systems.)<\/p>\n<h2>Overly flattering<\/h2>\n<p>&#8220;The update we removed was overly flattering or agreeable &#8212; often described as sycophantic,&#8221; OpenAI said <a href=\"https:\/\/openai.com\/index\/sycophancy-in-gpt-4o\/\" target=\"_blank\" rel=\"noopener nofollow\" class=\"c-regularLink\">in a blog<\/a> about the issue. Sycophancy in AI models can occur when <a href=\"https:\/\/arxiv.org\/abs\/2310.13548\" target=\"_blank\" rel=\"noopener nofollow\" class=\"c-regularLink\">human feedback is used to train them<\/a>, specifically in fine-tuning. The company explained the update had intended to &#8220;improv[e] the model&#8217;s default personality to make it feel more intuitive and effective across a variety of tasks.&#8221; <\/p>\n<p><strong>Also: <a href=\"https:\/\/www.zdnet.com\/article\/anthropic-mapped-claudes-morality-heres-what-the-chatbot-values-and-doesnt\/\">Anthropic mapped Claude&#8217;s morality. Here&#8217;s what the chatbot values (and doesn&#8217;t)<\/a><\/strong><\/p>\n<p>However, OpenAI admitted it had &#8220;focused too much on short-term feedback, and did not fully account for how users&#8217; interactions with ChatGPT evolve over time.&#8221; This led to GPT-4o responding in &#8220;overly supportive but disingenuous&#8221; ways. <\/p>\n<p>Sources inside OpenAI <a href=\"https:\/\/www.zdnet.com\/article\/openai-used-to-test-its-ai-models-for-months-now-its-days-why-that-matters\/\">recently reported<\/a> that the company has shrunk its safety testing timelines for new models. It is unclear how much direct impact that had here, or whether changes to testing occurred before or after the GPT-4o update was in progress. <\/p>\n<p><strong>Also: <a href=\"https:\/\/www.zdnet.com\/article\/the-dead-giveaway-that-chatgpt-wrote-your-content-and-how-to-work-around-it\/\">The dead giveaway that ChatGPT wrote your content &#8211; and how to work around it<\/a><\/strong><\/p>\n<p>Beyond being uncomfortable to interact with, sycophancy can be dangerous if chatbots blindly encourage users&#8217; hateful or violent opinions or desired actions &#8212; some of which they would usually disengage with based on OpenAI&#8217;s <a href=\"https:\/\/model-spec.openai.com\/2025-04-11.html\" target=\"_blank\" rel=\"noopener nofollow\" class=\"c-regularLink\">guardrails<\/a>. In the blog, OpenAI focused primarily on sycophancy&#8217;s impact on user satisfaction rather than potential safety issues. <\/p>\n<p><!----><\/p>\n<h2>Update reversed<\/h2>\n<p>In his post, Altman noted that the update is completely reversed for free-tier ChatGPT users, and that OpenAI would update the model again for <a href=\"https:\/\/www.zdnet.com\/article\/is-chatgpt-plus-worth-your-20-heres-how-it-compares-to-free-and-pro-plans\/\">paid users<\/a> once the reversal concluded. <\/p>\n<p>&#8220;[W]e&#8217;re working on additional fixes to model personality and will share more in the coming days,&#8221; he added. In its blog, OpenAI explained that this includes &#8220;refining core training techniques and system prompts,&#8221; adding personalization features for greater user control, and reevaluating how it weighs feedback for user satisfaction. <\/p>\n<p><strong>Also: <a href=\"https:\/\/www.zdnet.com\/article\/a-few-secretive-ai-companies-could-crush-free-society-researchers-warn\/\">A few secretive AI companies could crush free society, researchers warn<\/a><\/strong><\/p>\n<p>Moving forward, &#8220;users will be able to give real-time feedback to directly influence their interactions and choose from multiple default personalities,&#8221; the company added. <\/p>\n<p><em>Get the morning&#8217;s top stories in your inbox each day with our <\/em><a href=\"https:\/\/www.zdnet.com\/newsletters\/\"><strong><em>Tech Today newsletter.<\/em><\/strong><\/a><\/p>\n<div id=\"pinbox-f2772638-a090-48e5-85d2-aa9d35cc4a4e\" class=\"c-shortcodePinbox-carousel\">\n<div class=\"c-listingCarouselHorizontal\">\n<h4 class=\"c-sectionHeading\">Artificial Intelligence<\/h4>\n<p> <!----> <span class=\"c-listingCarouselHorizontal_loadingIndicator\"><\/span> <\/div>\n<\/div>\n<p>READ MORE <a href=\"https:\/\/www.zdnet.com\/article\/gpt-4o-update-gets-recalled-by-openai-for-being-too-agreeable\/\">HERE<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Users complained GPT-4o was too &#8216;sycophantic.&#8217; Here&#8217;s why and what happens now.READ MORE HERE&#8230;<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"colormag_page_layout":"default_layout","footnotes":""},"categories":[62],"tags":[],"class_list":["post-58610","post","type-post","status-publish","format-standard","hentry","category-zdnet-security"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.1 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>OpenAI recalls GPT-4o update for being too agreeable 2026 | ThreatsHub Cybersecurity News<\/title>\n<meta name=\"description\" content=\"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security &amp; Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"OpenAI recalls GPT-4o update for being too agreeable 2026 | ThreatsHub Cybersecurity News\" \/>\n<meta property=\"og:description\" content=\"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security &amp; Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/\" \/>\n<meta property=\"og:site_name\" content=\"ThreatsHub Cybersecurity News\" \/>\n<meta property=\"article:published_time\" content=\"2025-04-30T14:35:00+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.zdnet.com\/a\/img\/resize\/73ea29d36f15045b547f071df53f0acf24759605\/2025\/04\/30\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\/gettyimages-2210029399.jpg?auto=webp&amp;width=1280\" \/>\n<meta name=\"author\" content=\"TH Author\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@threatshub\" \/>\n<meta name=\"twitter:site\" content=\"@threatshub\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"TH Author\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/openai-recalls-gpt-4o-update-for-being-too-agreeable\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/openai-recalls-gpt-4o-update-for-being-too-agreeable\\\/\"},\"author\":{\"name\":\"TH Author\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#\\\/schema\\\/person\\\/12e0a8671ff89a863584f193e7062476\"},\"headline\":\"OpenAI recalls GPT-4o update for being too agreeable\",\"datePublished\":\"2025-04-30T14:35:00+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/openai-recalls-gpt-4o-update-for-being-too-agreeable\\\/\"},\"wordCount\":496,\"publisher\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/openai-recalls-gpt-4o-update-for-being-too-agreeable\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.zdnet.com\\\/a\\\/img\\\/resize\\\/73ea29d36f15045b547f071df53f0acf24759605\\\/2025\\\/04\\\/30\\\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\\\/gettyimages-2210029399.jpg?auto=webp&amp;width=1280\",\"articleSection\":[\"ZDNet | Security\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/openai-recalls-gpt-4o-update-for-being-too-agreeable\\\/\",\"url\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/openai-recalls-gpt-4o-update-for-being-too-agreeable\\\/\",\"name\":\"OpenAI recalls GPT-4o update for being too agreeable 2026 | ThreatsHub Cybersecurity News\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/openai-recalls-gpt-4o-update-for-being-too-agreeable\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/openai-recalls-gpt-4o-update-for-being-too-agreeable\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.zdnet.com\\\/a\\\/img\\\/resize\\\/73ea29d36f15045b547f071df53f0acf24759605\\\/2025\\\/04\\\/30\\\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\\\/gettyimages-2210029399.jpg?auto=webp&amp;width=1280\",\"datePublished\":\"2025-04-30T14:35:00+00:00\",\"description\":\"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/openai-recalls-gpt-4o-update-for-being-too-agreeable\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/openai-recalls-gpt-4o-update-for-being-too-agreeable\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/openai-recalls-gpt-4o-update-for-being-too-agreeable\\\/#primaryimage\",\"url\":\"https:\\\/\\\/www.zdnet.com\\\/a\\\/img\\\/resize\\\/73ea29d36f15045b547f071df53f0acf24759605\\\/2025\\\/04\\\/30\\\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\\\/gettyimages-2210029399.jpg?auto=webp&amp;width=1280\",\"contentUrl\":\"https:\\\/\\\/www.zdnet.com\\\/a\\\/img\\\/resize\\\/73ea29d36f15045b547f071df53f0acf24759605\\\/2025\\\/04\\\/30\\\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\\\/gettyimages-2210029399.jpg?auto=webp&amp;width=1280\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/openai-recalls-gpt-4o-update-for-being-too-agreeable\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"OpenAI recalls GPT-4o update for being too agreeable\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#website\",\"url\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/\",\"name\":\"ThreatsHub Cybersecurity News\",\"description\":\"%%focuskw%% Threat Intel \u2013 Threat Intel Services \u2013 CyberIntelligence \u2013 Cyber Threat Intelligence - Threat Intelligence Feeds - Threat Intelligence Reports - CyberSecurity Report \u2013 Cyber Security PDF \u2013 Cybersecurity Trends - Cloud Sandbox \u2013- Threat IntelligencePortal \u2013 Incident Response \u2013 Threat Hunting \u2013 IOC - Yara - Security Operations Center \u2013 SecurityOperation Center \u2013 Security SOC \u2013 SOC Services - Advanced Threat - Threat Detection - TargetedAttack \u2013 APT \u2013 Anti-APT \u2013 Advanced Protection \u2013 Cyber Security Services \u2013 Cybersecurity Services -Threat Intelligence Platform\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#organization\"},\"alternateName\":\"Threatshub.org\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#organization\",\"name\":\"ThreatsHub.org\",\"alternateName\":\"Threatshub.org\",\"url\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/wp-content\\\/uploads\\\/2025\\\/05\\\/Threatshub_Favicon1.jpg\",\"contentUrl\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/wp-content\\\/uploads\\\/2025\\\/05\\\/Threatshub_Favicon1.jpg\",\"width\":432,\"height\":435,\"caption\":\"ThreatsHub.org\"},\"image\":{\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/threatshub\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.threatshub.org\\\/blog\\\/#\\\/schema\\\/person\\\/12e0a8671ff89a863584f193e7062476\",\"name\":\"TH Author\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g\",\"caption\":\"TH Author\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"OpenAI recalls GPT-4o update for being too agreeable 2026 | ThreatsHub Cybersecurity News","description":"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.","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:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/","og_locale":"en_US","og_type":"article","og_title":"OpenAI recalls GPT-4o update for being too agreeable 2026 | ThreatsHub Cybersecurity News","og_description":"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.","og_url":"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/","og_site_name":"ThreatsHub Cybersecurity News","article_published_time":"2025-04-30T14:35:00+00:00","og_image":[{"url":"https:\/\/www.zdnet.com\/a\/img\/resize\/73ea29d36f15045b547f071df53f0acf24759605\/2025\/04\/30\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\/gettyimages-2210029399.jpg?auto=webp&amp;width=1280","type":"","width":"","height":""}],"author":"TH Author","twitter_card":"summary_large_image","twitter_creator":"@threatshub","twitter_site":"@threatshub","twitter_misc":{"Written by":"TH Author","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/#article","isPartOf":{"@id":"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/"},"author":{"name":"TH Author","@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/person\/12e0a8671ff89a863584f193e7062476"},"headline":"OpenAI recalls GPT-4o update for being too agreeable","datePublished":"2025-04-30T14:35:00+00:00","mainEntityOfPage":{"@id":"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/"},"wordCount":496,"publisher":{"@id":"https:\/\/www.threatshub.org\/blog\/#organization"},"image":{"@id":"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/#primaryimage"},"thumbnailUrl":"https:\/\/www.zdnet.com\/a\/img\/resize\/73ea29d36f15045b547f071df53f0acf24759605\/2025\/04\/30\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\/gettyimages-2210029399.jpg?auto=webp&amp;width=1280","articleSection":["ZDNet | Security"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/","url":"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/","name":"OpenAI recalls GPT-4o update for being too agreeable 2026 | ThreatsHub Cybersecurity News","isPartOf":{"@id":"https:\/\/www.threatshub.org\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/#primaryimage"},"image":{"@id":"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/#primaryimage"},"thumbnailUrl":"https:\/\/www.zdnet.com\/a\/img\/resize\/73ea29d36f15045b547f071df53f0acf24759605\/2025\/04\/30\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\/gettyimages-2210029399.jpg?auto=webp&amp;width=1280","datePublished":"2025-04-30T14:35:00+00:00","description":"ThreatsHub Cybersecurity News | ThreatsHub.org | Cloud Security & Cyber Threats Analysis Hub. 100% Free OSINT Threat Intelligent and Cybersecurity News.","breadcrumb":{"@id":"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/#primaryimage","url":"https:\/\/www.zdnet.com\/a\/img\/resize\/73ea29d36f15045b547f071df53f0acf24759605\/2025\/04\/30\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\/gettyimages-2210029399.jpg?auto=webp&amp;width=1280","contentUrl":"https:\/\/www.zdnet.com\/a\/img\/resize\/73ea29d36f15045b547f071df53f0acf24759605\/2025\/04\/30\/b3c19b73-adc2-41cb-afe8-bdc170c484d7\/gettyimages-2210029399.jpg?auto=webp&amp;width=1280"},{"@type":"BreadcrumbList","@id":"https:\/\/www.threatshub.org\/blog\/openai-recalls-gpt-4o-update-for-being-too-agreeable\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.threatshub.org\/blog\/"},{"@type":"ListItem","position":2,"name":"OpenAI recalls GPT-4o update for being too agreeable"}]},{"@type":"WebSite","@id":"https:\/\/www.threatshub.org\/blog\/#website","url":"https:\/\/www.threatshub.org\/blog\/","name":"ThreatsHub Cybersecurity News","description":"%%focuskw%% Threat Intel \u2013 Threat Intel Services \u2013 CyberIntelligence \u2013 Cyber Threat Intelligence - Threat Intelligence Feeds - Threat Intelligence Reports - CyberSecurity Report \u2013 Cyber Security PDF \u2013 Cybersecurity Trends - Cloud Sandbox \u2013- Threat IntelligencePortal \u2013 Incident Response \u2013 Threat Hunting \u2013 IOC - Yara - Security Operations Center \u2013 SecurityOperation Center \u2013 Security SOC \u2013 SOC Services - Advanced Threat - Threat Detection - TargetedAttack \u2013 APT \u2013 Anti-APT \u2013 Advanced Protection \u2013 Cyber Security Services \u2013 Cybersecurity Services -Threat Intelligence Platform","publisher":{"@id":"https:\/\/www.threatshub.org\/blog\/#organization"},"alternateName":"Threatshub.org","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.threatshub.org\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.threatshub.org\/blog\/#organization","name":"ThreatsHub.org","alternateName":"Threatshub.org","url":"https:\/\/www.threatshub.org\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.threatshub.org\/blog\/coredata\/uploads\/2025\/05\/Threatshub_Favicon1.jpg","contentUrl":"https:\/\/www.threatshub.org\/blog\/coredata\/uploads\/2025\/05\/Threatshub_Favicon1.jpg","width":432,"height":435,"caption":"ThreatsHub.org"},"image":{"@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/threatshub"]},{"@type":"Person","@id":"https:\/\/www.threatshub.org\/blog\/#\/schema\/person\/12e0a8671ff89a863584f193e7062476","name":"TH Author","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/066276f086d5155df79c850206a779ad368418a844da0182ce43f9cd5b506c3d?s=96&d=mm&r=g","caption":"TH Author"}}]}},"_links":{"self":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/posts\/58610","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/comments?post=58610"}],"version-history":[{"count":0,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/posts\/58610\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/media?parent=58610"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/categories?post=58610"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.threatshub.org\/blog\/wp-json\/wp\/v2\/tags?post=58610"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}