Outside experts pick up the slack on safety testing on OpenAI\u2019s newest model release | CyberScoop<\/title> <meta name=\"description\" content=\"OpenAI\u2019s GPT-4.1 was released without a public safety report, prompting SplxAI researchers to test its resilience against misuse.\"> <link rel=\"canonical\" href=\"https:\/\/cyberscoop.com\/openai-gpt-4-1-safety-report-splxai-test-results\/\"> <meta property=\"og:locale\" content=\"en_US\"> <meta property=\"og:type\" content=\"article\"> <meta property=\"og:title\" content=\"Outside experts pick up the slack on safety testing on OpenAI\u2019s newest model release\"> <meta property=\"og:description\" content=\"OpenAI\u2019s GPT-4.1 was released without a public safety report, prompting SplxAI researchers to test its resilience against misuse.\"> <meta property=\"og:url\" content=\"https:\/\/cyberscoop.com\/openai-gpt-4-1-safety-report-splxai-test-results\/\"> <meta property=\"og:site_name\" content=\"CyberScoop\"> <meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/cyberscoop\/\"> <meta property=\"article:published_time\" content=\"2025-04-22T23:41:28+00:00\"> <meta property=\"article:modified_time\" content=\"2025-04-22T23:41:30+00:00\"> <meta property=\"og:image\" content=\"https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-5.jpg\"> <meta property=\"og:image:width\" content=\"6792\"> <meta property=\"og:image:height\" content=\"4528\"> <meta property=\"og:image:type\" content=\"image\/jpeg\"> <meta name=\"author\" content=\"djohnson\"> <meta name=\"twitter:card\" content=\"summary_large_image\"> <meta name=\"twitter:creator\" content=\"@CyberScoopNews\"> <meta name=\"twitter:site\" content=\"@CyberScoopNews\">  <link rel=\"dns-prefetch\" href=\"\/\/securepubads.g.doubleclick.net\">\n<link rel=\"dns-prefetch\" href=\"\/\/use.typekit.net\">\n<link rel=\"alternate\" type=\"application\/rss+xml\" title=\"CyberScoop \u00bb Feed\" href=\"https:\/\/cyberscoop.com\/feed\/\">\n<link rel=\"alternate\" type=\"application\/rss+xml\" title=\"CyberScoop \u00bb Comments Feed\" href=\"https:\/\/cyberscoop.com\/comments\/feed\/\"> <link rel=\"stylesheet\" id=\"all-css-2\" href=\"https:\/\/cyberscoop.com\/wp-includes\/css\/dist\/block-library\/style.min.css?m=1744740145g\" type=\"text\/css\" media=\"all\"> <link rel=\"stylesheet\" id=\"all-css-6\" href=\"https:\/\/cyberscoop.com\/wp-content\/mu-plugins\/search\/elasticpress\/dist\/css\/related-posts-block-styles.min.css?m=1744312959g\" type=\"text\/css\" media=\"all\"> <link rel=\"stylesheet\" id=\"all-css-8\" href=\"https:\/\/cyberscoop.com\/wp-content\/themes\/scoopnewsgroup\/dist\/css\/frontend.css?m=1740691656g\" type=\"text\/css\" media=\"all\">\n<link rel=\"stylesheet\" id=\"typekit-css\" href=\"https:\/\/use.typekit.net\/itk2qbh.css?ver=a815169637cf454b7376\" media=\"all\"> <link rel=\"https:\/\/api.w.org\/\" href=\"https:\/\/cyberscoop.com\/wp-json\/\"><link rel=\"alternate\" title=\"JSON\" type=\"application\/json\" href=\"https:\/\/cyberscoop.com\/wp-json\/wp\/v2\/posts\/84260\"><link rel=\"EditURI\" type=\"application\/rsd+xml\" title=\"RSD\" href=\"https:\/\/cyberscoop.com\/xmlrpc.php?rsd\">\n<meta name=\"generator\" content=\"WordPress 6.8\">\n<link rel=\"shortlink\" href=\"https:\/\/cyberscoop.com\/?p=84260\">\n<link rel=\"alternate\" title=\"oEmbed (JSON)\" type=\"application\/json+oembed\" href=\"https:\/\/cyberscoop.com\/wp-json\/oembed\/1.0\/embed?url=https%3A%2F%2Fcyberscoop.com%2Fopenai-gpt-4-1-safety-report-splxai-test-results%2F\">\n<link rel=\"alternate\" title=\"oEmbed (XML)\" type=\"text\/xml+oembed\" href=\"https:\/\/cyberscoop.com\/wp-json\/oembed\/1.0\/embed?url=https%3A%2F%2Fcyberscoop.com%2Fopenai-gpt-4-1-safety-report-splxai-test-results%2F&format=xml\">   <link rel=\"icon\" href=\"https:\/\/cyberscoop.com\/wp-content\/uploads\/sites\/3\/2023\/01\/cropped-cs_favicon-2.png?w=32\" sizes=\"32x32\">\n<link rel=\"icon\" href=\"https:\/\/cyberscoop.com\/wp-content\/uploads\/sites\/3\/2023\/01\/cropped-cs_favicon-2.png?w=192\" sizes=\"192x192\">\n<link rel=\"apple-touch-icon\" href=\"https:\/\/cyberscoop.com\/wp-content\/uploads\/sites\/3\/2023\/01\/cropped-cs_favicon-2.png?w=180\">\n<meta name=\"msapplication-TileImage\" content=\"https:\/\/cyberscoop.com\/wp-content\/uploads\/sites\/3\/2023\/01\/cropped-cs_favicon-2.png?w=270\"> <\/head><body class=\"wp-singular post-template-default single single-post postid-84260 single-format-standard wp-theme-scoopnewsgroup wp-child-theme-cyberscoop\" id=\"readabilityBody\"> <a href=\"https:\/\/cyberscoop.com\/openai-gpt-4-1-safety-report-splxai-test-results\/#main\" class=\"skip-to-content-link visually-hidden-focusable\">Skip to main content<\/a> <\/p>\n<div class=\"ad ad--top ad--top-desktop\">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<p> <main id=\"main\" role=\"main\" tabindex=\"-1\"> <\/p>\n<div class=\"ad ad--top ad--top-mobile\">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<section id=\"stickybar\" class=\"stickybar stickybar--event js-stickybar\">\n<div class=\"stickybar__details\" readability=\"4.9180327868852\">\n<div class=\"stickybar__info js-sticky-bar-content\" readability=\"32\">\n<p>Voting is open for the 2025 CyberScoop 50 awards!<\/p>\n<\/div>\n<p> <a class=\"stickybar__link button button-tertiary\" href=\"https:\/\/cyberscoop.com\/cyberscoop50\/\">Click here!<\/a> <\/div>\n<p> <button class=\"stickybar__close js-stickybar-close\" aria-controls=\"stickybar\"> <svg class=\"icon icon--close\" width=\"21\" height=\"22\" viewBox=\"0 0 21 22\" fill=\"none\"><path d=\"m.822.518-.805.805L9.695 11 .017 20.678l.805.805 9.678-9.678 9.677 9.678.806-.805L11.305 11l9.678-9.677-.806-.805-9.677 9.677L.822.518Z\" fill=\"currentColor\" \/><\/svg> <span class=\"visually-hidden\">Close<\/span> <\/button> <\/section>\n<article class=\"single-article content\">\n<div class=\"single-article__container js-single-article-content\">\n<header class=\"single-article__header \" readability=\"25.201559020045\">\n<div class=\"single-article__header-content\" readability=\"34.175115207373\">\n<ul class=\"single-article__eyebrow\">\n<li class=\"single-article__category\"> <a class=\"single-article__category-link\" href=\"https:\/\/cyberscoop.com\/openai-gpt-4-1-safety-report-splxai-test-results\/\"> <span>Uncategorized<\/span> <\/a> <\/li>\n<\/ul>\n<p> Independent testing by SplxAI found GPT-4.1 was three times more likely than its predecessor to bypass security safeguards and allow intentional misuse <\/p>\n<p>  <br \/>\n<audio id=\"audio-player\" src=\"https:\/\/wp-tts-cdn.api.scpnewsgrp.com\/cyberscoop\/84260\/english.openai.mp3\"><\/audio> <\/p>\n<div readability=\"11\">\n<div>\n<p>Listen to this article<\/p>\n<p>  <\/p>\n<p>0:00<\/p>\n<\/p><\/div>\n<p>  <\/p>\n<p> <span id=\"tts-tooltip\">Learn more.<\/span> <span> This feature uses an automated voice, which may result in occasional errors in pronunciation, tone, or sentiment. <\/span> <\/p>\n<\/div>\n<p>  <\/div>\n<div class=\"single-article__cover-wrap\">\n<figure class=\"single-article__cover\"> <img data-recalc-dims=\"1\" fetchpriority=\"high\" width=\"640\" height=\"426\" src=\"https:\/\/i0.wp.com\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release.jpg?resize=640%2C426&ssl=1\" class=\"single-article__cover-image wp-post-image\" alt decoding=\"async\" fetchpriority=\"high\" srcset=\"https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-5.jpg 6792w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-5.jpg?resize=300,200 300w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-5.jpg?resize=768,512 768w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-5.jpg?resize=1024,683 1024w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-5.jpg?resize=1536,1024 1536w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-5.jpg?resize=2048,1365 2048w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-5.jpg?resize=600,400 600w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-5.jpg?resize=252,168 252w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-5.jpg?resize=506,337 506w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-5.jpg?resize=1013,675 1013w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-5.jpg?resize=1265,843 1265w\" sizes=\"(max-width: 1013px) 100vw, 1013px\"><figcaption> (Getty Images) <\/figcaption><\/figure>\n<\/p><\/div>\n<\/header>\n<div class=\"single-article__content\">\n<div class=\"single-article__content-inner has-drop-cap\"> <html readability=\"79.231533533795\"><body readability=\"158.21992454939\"><\/p>\n<p>GPT-4.1, the latest family of generative AI models from OpenAI, was released earlier this month with promised improvements around coding, instruction following and context.<\/p>\n<p>It\u2019s also the first model released by the company since it announced changes to the way it tests and evaluates products for safety. Unlike its previous fine-tuned models, OpenAI did not release a corresponding safety report with GPT-4.1 that details its performance and limitations against different forms of abuse.<\/p>\n<p>So, researchers at SplxAI, an AI red teaming company, decided to put 4.1 to the test. <a href=\"https:\/\/splx.ai\/blog\/the-missing-gpt-4-1-safety-report#2\">Literally<\/a>.<\/p>\n<p>Researchers used the same prompts from their 4.0 tests, to create a financial advisor chatbot programmed with 11 \u201ccore security directives,\u201d\u2014explicit safeguards against jailbreaking and circumvention efforts across 11 different categories, including data leakage, hallucination, harmful content creation, data exfiltration and others.<\/p>\n<div class=\"ad ad--inline_1 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<p>While those prompts were fairly effective in preventing 4.0 models from violating OpenAI\u2019s guardrails, their success fell considerably in tests of the newer models.<\/p>\n<p>\u201cBased on over 1,000 simulated test cases, GPT-4.1 is 3x more likely to go off-topic and allow intentional misuse compared to GPT-4o,\u201d the report concluded.<\/p>\n<figure class=\"wp-block-image\"><img data-recalc-dims=\"1\" decoding=\"async\" src=\"https:\/\/i0.wp.com\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release.png?w=640&ssl=1\" alt><figcaption class=\"wp-element-caption\"><em>Results of safety tests across 11 different categories using the same prompt found higher error rates across GPT-4.1 than 4.0 (Source: SplxAI)<\/em><\/figcaption><\/figure>\n<p>While OpenAI has said that new, more explicit prompts will be needed to properly program 4.1, the report found that \u201cprompting recommendations for GPT-4.1 did not mitigate these issues in our tests when incorporated into an existing system prompt\u201d and in some cases actually led to higher error rates.<\/p>\n<p>Dominik Jurin\u010di\u0107, a data scientist at SplxAI and one of the authors of the research, told CyberScoop that when 4.1 is used in a controlled environment and given specific or basic tasks \u201cit\u2019s great, it\u2019s easy, and you actually can get reproducible results.\u201d<\/p>\n<div class=\"ad ad--inline_1 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<p>\u201cThe problem is when you need to safeguard it and defend and explain to the model that it can\u2019t do anything else, explaining \u2018everything else\u2019 explicitly is very hard,\u201d he said.<\/p>\n<p>Indeed, the prompting instructions used by SplxAI researchers for 4.1 clock in at just under 1400 words, with the core security directives alone taking up more than 1000 words. This is significant, Jurin\u010di\u0107 said, because it highlights how organizations face a moving target on AI safety every time they change or upgrade their model.<\/p>\n<p>After using the original and modified versions of the 4.0 system prompts, Splx researchers then started a new prompt from scratch using OpenAI\u2019s instructions, getting better results. But Jurin\u010di\u0107 said it took his team 4 to 5 hours of work before they had iterated an effective prompt. A less technically-inclined organization \u2014 or one that doesn\u2019t specifically focus on security research \u2014 is far more likely to simply port over their previous prompting guidance, new vulnerabilities and all.<\/p>\n<figure class=\"wp-block-image\"><img data-recalc-dims=\"1\" decoding=\"async\" src=\"https:\/\/i0.wp.com\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-1.png?w=640&ssl=1\" alt><figcaption class=\"wp-element-caption\"><em>Partial text of the prompting instructions detailing core security directives used by SplxAI researchers to test OpenAI\u2019s new GPT-4.1 (Source: SplxAI)<\/em><\/figcaption><\/figure>\n<p>While OpenAI draws a meaningful distinction between safety testing frontier and fine-tuned models, Jurin\u010di\u0107 sees less of a difference. Since OpenAI <a href=\"https:\/\/openai.com\/index\/gpt-4-1\/\">repeatedly compares<\/a> 4.1 to 4.0 in its releases and marketing\u2014, and given that 4.0 is OpenAI\u2019s most popular enterprise model\u2014 he expects many businesses will upgrade to 4.1.<\/p>\n<div class=\"ad ad--inline_1 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<p>\u201cIt makes sense from a consistency standpoint, but the way that the model release is framed and since it is advertised as a sort of successor to 4.0, it doesn\u2019t make much sense to me,\u201d he said. \u201cI think it\u2019s going to be widely used [by businesses] and they should have been aware of that when they were writing it.\u201d<\/p>\n<p>When contacted for further clarification on its policies, an OpenAI spokesperson directed CyberScoop to several passages from its new preparedness framework that prioritizes safeguarding against \u201csevere\u201d harms and is focused on \u201cany new or updated deployment that has a plausible chance of reaching a capability threshold whose corresponding risks are not addressed by an existing Safeguards Report.\u201d <\/p>\n<p>They also referenced a <a href=\"https:\/\/openai.com\/index\/moving-ai-governance-forward\/\">blog<\/a> on AI governance the company wrote in 2023 where the company states it will prioritize safety testing resources \u201conly on generative models that are overall more powerful than the current industry frontier.\u201d <\/p>\n<p> The concerns about 4.1 from security researchers comes less than a month after OpenAI released<a href=\"https:\/\/openai.com\/index\/updating-our-preparedness-framework\/\"> a revised policy<\/a> detailing how it will test and evaluate future models ahead of release, expressing a desire to focus on \u201cspecific risks that matter most\u201d and explicitly excluding abuses around \u201cpersuasion,\u201d which includes the use of their platforms to generate and distribute disinformation and influence elections.<\/p>\n<p>Those harms will no longer be part of safety testing on the front end. Such misuses, the company claims, will now be addressed through OpenAI\u2019s detection research into influence campaigns and stricter controls on model licensing.<\/p>\n<div class=\"ad ad--inline_1 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<p>The move prompted critics, including former employees, to question whether the company was pulling back on its prior safety and security commitments.<\/p>\n<p>\u201cPeople can totally disagree about whether testing finetuned models is needed\u2026And better for OpenAI to remove a commitment than to keep it [and] just not follow\u2026But in either case, I\u2019d like OpenAI to be clearer about having backed off this previous commitment,\u201d Steven Adler, a former researcher at OpenAI who worked on safety issues,<a href=\"https:\/\/x.com\/sjgadler\/status\/1912242579288256693\"> wrote<\/a> on X.<\/p>\n<p>Miranda Bogen, director of the AI Governance Lab at the Center for Democracy and Technology, expressed criticism of OpenAI earlier this month following reports that the company was cutting down the time it spends testing new models for safety and security.<\/p>\n<p>\u201cAs AI companies are racing to put out increasingly advanced systems, they also seem to be cutting more and more corners on safety, which doesn\u2019t add up. AI will surely transform people\u2019s lives, but if developers keep prioritizing speed over safety, these changes are more likely to be for the worse, not the better.\u201d<\/p>\n<p>Just a year ago, OpenAI and other AI companies convened in Washington D.C. and <a href=\"https:\/\/cyberscoop.com\/tech-companies-pledge-to-protect-2024-elections-from-ai-generated-media\/\">Munich, Germany<\/a> to sign <a href=\"https:\/\/www.nytimes.com\/2023\/07\/21\/us\/politics\/ai-regulation-biden.html\">voluntary agreements<\/a> signaling their commitments to AI model safety and preventing their tools from <a href=\"https:\/\/cyberscoop.com\/tech-platforms-ai-elections-misinformation-disinformation\/\">being abused<\/a> to <a href=\"https:\/\/cyberscoop.com\/ai-companies-election-transparency\/\">manipulate voters in elections<\/a>. Both issues were major priorities for then-President Joe Biden and Democrats in Congress.<\/p>\n<div class=\"ad ad--inline_1 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<p>Today, those same companies are facing a far different regulatory environment. President Donald Trump and Vice President JD Vance have rescinded most of the Biden-era AI executive orders and <a href=\"https:\/\/cyberscoop.com\/ai-safety-jd-vance-paris-ai-summit-deregulation\/\">have charted a new path for AI policy<\/a> that does not include safety considerations. <\/p>\n<p>Republicans, in control of both houses of Congress, have expressed virtually no appetite for substantial regulations on the nascent industry, fearful that it could inhibit growth and slow U.S. entities down as they try to compete with China for AI dominance.<\/p>\n<p> <\/body> <\/p>\n<footer class=\"single-article__footer\" readability=\"4.5\">\n<div class=\"author-card\" readability=\"14\">\n<div class=\"author-card__avatar\">\n<figure class=\"author-card__image-wrap\"> <img data-recalc-dims=\"1\" decoding=\"async\" class=\"author-card__image\" src=\"https:\/\/i0.wp.com\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-1.jpg?w=640&ssl=1\" alt=\"Greg Otto\"> <\/figure>\n<\/p><\/div>\n<p><h4 class=\"author-card__name\">Written by Greg Otto<\/h4>\n<p> Greg Otto is Editor-in-Chief of CyberScoop, overseeing all editorial content for the website. Greg has led cybersecurity coverage that has won various awards, including accolades from the Society of Professional Journalists and the American Society of Business Publication Editors. Prior to joining Scoop News Group, Greg worked for the Washington Business Journal, U.S. News & World Report and WTOP Radio. He has a degree in broadcast journalism from Temple University. <\/p>\n<\/p><\/div>\n<\/footer>\n<p> <\/html><\/div>\n<\/p><\/div>\n<\/p><\/div>\n<div class=\"single-article__ads js-single-article-sidebar\">\n<div class=\"ad ad--sidebar js-single-article-sidebar-5 ad--rightrail_1 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<div class=\"ad ad--sidebar js-single-article-sidebar-4 ad--rightrail_2 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<div class=\"ad ad--sidebar js-single-article-sidebar-3 ad--rightrail_3 \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div><\/div>\n<\/article>\n<div class=\"popular-stories popular-stories--single-post\">\n<div class=\"popular-stories__container\">\n<h2 class=\"popular-stories__title\"> More Scoops <\/h2>\n<div class=\"popular-stories__stories\">\n<div class=\"popular-stories__cards\">\n<article class=\"post-item post-item--popular-stories-cards \" readability=\"23.108823529412\">\n<figure class=\"post-item__thumbnail\"> <a class=\"post-item__thumbnail-link\" href=\"https:\/\/cyberscoop.com\/ai-companies-election-transparency\/\" tabindex=\"-1\"> <img data-recalc-dims=\"1\" loading=\"lazy\" width=\"528\" height=\"337\" src=\"https:\/\/i0.wp.com\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-2.jpg?resize=528%2C337&ssl=1\" class=\"attachment-ratio-16-9-md size-ratio-16-9-md wp-post-image\" alt decoding=\"async\" loading=\"lazy\" srcset=\"https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-6.jpg 5736w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-6.jpg?resize=300,191 300w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-6.jpg?resize=768,490 768w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-6.jpg?resize=1024,654 1024w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-6.jpg?resize=1536,980 1536w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-6.jpg?resize=2048,1307 2048w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-6.jpg?resize=600,383 600w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-6.jpg?resize=263,168 263w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-6.jpg?resize=528,337 528w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-6.jpg?resize=1058,675 1058w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-6.jpg?resize=1321,843 1321w\" sizes=\"auto, (max-width: 528px) 100vw, 528px\"> <\/a><figcaption class=\"screen-reader-text\"> A photo shows a frame of a video generated by a new intelligence artificial tool, dubbed \u201cSora\u201d, unveiled by the company OpenAI, in Paris on February 16, 2024. OpenAI, the creator of ChatGPT and image generator DALL-E, said it was testing a text-to-video model called Sora that would allow users to create realistic videos with a simple prompt. (Photo by Stefano RELLANDINI \/ AFP) (Photo by STEFANO RELLANDINI\/AFP via Getty Images) <\/figcaption><\/figure>\n<header class=\"post-item__meta\" readability=\"2.3934426229508\">\n<h3 class=\"post-item__title\"> <a class=\"post-item__title-link\" href=\"https:\/\/cyberscoop.com\/ai-companies-election-transparency\/\"> AI companies promise to protect our elections. Will they live up to their pledges? <\/a> <\/h3>\n<p> Critics in government and industry want more transparency, reporting and accountability for recent industry promises around AI and elections. <\/p>\n<div class=\"post-item__byline\"> <span class=\"post-item__author\"> <span>By <\/span> <a class=\"post-item__author-link\" href=\"https:\/\/cyberscoop.com\/author\/derek-johnson\/\"> Derek B. Johnson <\/a> <\/span> <\/div>\n<p> <\/header>\n<p> <\/article>\n<article class=\"post-item post-item--popular-stories-cards \">\n<figure class=\"post-item__thumbnail\"> <a class=\"post-item__thumbnail-link\" href=\"https:\/\/cyberscoop.com\/openai-microsoft-apt-llm\/\" tabindex=\"-1\"> <img data-recalc-dims=\"1\" loading=\"lazy\" width=\"241\" height=\"168\" src=\"https:\/\/i0.wp.com\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-3.jpg?resize=241%2C168&ssl=1\" class=\"attachment-ratio-16-9-sm size-ratio-16-9-sm wp-post-image\" alt decoding=\"async\" loading=\"lazy\" srcset=\"https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-7.jpg 1920w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-7.jpg?resize=300,209 300w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-7.jpg?resize=768,535 768w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-7.jpg?resize=1024,713 1024w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-7.jpg?resize=1536,1070 1536w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-7.jpg?resize=600,418 600w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-7.jpg?resize=241,168 241w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-7.jpg?resize=484,337 484w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-7.jpg?resize=969,675 969w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-7.jpg?resize=1211,843 1211w\" sizes=\"auto, (max-width: 241px) 100vw, 241px\"> <\/a><figcaption class=\"screen-reader-text\"> Microsoft CEO Satya Nadella (R) greets OpenAI CEO Sam Altman during the OpenAI DevDay event on November 06, 2023 in San Francisco, California. (Photo by Justin Sullivan\/Getty Images) <\/figcaption><\/figure>\n<header class=\"post-item__meta\">\n<h3 class=\"post-item__title\"> <a class=\"post-item__title-link\" href=\"https:\/\/cyberscoop.com\/openai-microsoft-apt-llm\/\"> State-backed hackers are experimenting with OpenAI models <\/a> <\/h3>\n<div class=\"post-item__byline\"> <span class=\"post-item__author\"> <span>By <\/span> <a class=\"post-item__author-link\" href=\"https:\/\/cyberscoop.com\/author\/elias-groll\/\"> Elias Groll <\/a> <\/span> <\/div>\n<p> <\/header>\n<p> <\/article>\n<article class=\"post-item post-item--popular-stories-cards \">\n<figure class=\"post-item__thumbnail\"> <a class=\"post-item__thumbnail-link\" href=\"https:\/\/cyberscoop.com\/guidelines-secure-ai-development\/\" tabindex=\"-1\"> <img data-recalc-dims=\"1\" loading=\"lazy\" width=\"252\" height=\"168\" src=\"https:\/\/i0.wp.com\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-4.jpg?resize=252%2C168&ssl=1\" class=\"attachment-ratio-16-9-sm size-ratio-16-9-sm wp-post-image\" alt decoding=\"async\" loading=\"lazy\" srcset=\"https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-8.jpg 1920w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-8.jpg?resize=300,200 300w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-8.jpg?resize=768,512 768w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-8.jpg?resize=1024,683 1024w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-8.jpg?resize=1536,1024 1536w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-8.jpg?resize=600,400 600w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-8.jpg?resize=252,168 252w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-8.jpg?resize=506,337 506w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-8.jpg?resize=1013,675 1013w, https:\/\/ddi.mohflo.net\/wp-content\/uploads\/2025\/04\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release-8.jpg?resize=1265,843 1265w\" sizes=\"auto, (max-width: 252px) 100vw, 252px\"> <\/a><figcaption class=\"screen-reader-text\"> Secretary of Homeland Security Alejandro Mayorkas speaks during the daily press briefing at the White House on March 1, 2021 in Washington, DC. (Drew Angerer\/Getty Images) <\/figcaption><\/figure>\n<header class=\"post-item__meta\">\n<h3 class=\"post-item__title\"> <a class=\"post-item__title-link\" href=\"https:\/\/cyberscoop.com\/guidelines-secure-ai-development\/\"> US and UK release guidelines for secure AI development <\/a> <\/h3>\n<div class=\"post-item__byline\"> <span class=\"post-item__author\"> <span>By <\/span> <a class=\"post-item__author-link\" href=\"https:\/\/cyberscoop.com\/author\/elias-groll\/\"> Elias Groll <\/a> <\/span> <\/div>\n<p> <\/header>\n<p> <\/article>\n<\/p><\/div>\n<\/p><\/div>\n<p> <\/div>\n<p>\n<\/div>\n<p> <\/p>\n<section class=\"latest-podcasts\">\n<h2 class=\"latest-podcasts__title\"> Latest Podcasts\t<\/h2>\n<\/section>\n<div class=\"top-categories\">\n<div class=\"top-categories__container\">\n<h3 class=\"top-categories__category-title\">Government<\/h3>\n<\/p><\/div>\n<div class=\"top-categories__container\">\n<h3 class=\"top-categories__category-title\">Technology<\/h3>\n<\/p><\/div>\n<\/p><\/div>\n<p> <\/main> <\/p>\n<div class=\"ad ad--bottom \">\n<div class=\"ad__inner\"> <span class=\"screen-reader-text\">Advertisement<\/span> <\/div>\n<\/div>\n<div id=\"interstitial\" class=\"welcome__container\"> <button id=\"close-modal-1\" class=\"welcome__clickable_area\"><\/button> <\/p>\n<div class=\"welcome__ad_wrapper\">\n<p> <button id=\"close-modal-3\" class=\"welcome__continue-button\">Continue to CyberScoop<\/button> <\/p>\n<\/p><\/div>\n<\/p><\/div>\n<p>   <\/body> <a href=\"https:\/\/cyberscoop.com\/openai-gpt-4-1-safety-report-splxai-test-results\/\">Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Outside experts pick up the slack on safety testing on<\/p>\n","protected":false},"author":11,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[1],"tags":[325],"class_list":["post-7557","post","type-post","status-publish","format-standard","hentry","category-uncategorized","tag-uncategorized"],"featured_image_urls":{"full":"","thumbnail":"","medium":"","medium_large":"","large":"","1536x1536":"","2048x2048":"","chromenews-featured":"","chromenews-large":"","chromenews-medium":""},"author_info":{"display_name":"Cyber Scoop","author_link":"https:\/\/ddi.mohflo.net\/index.php\/author\/cyberscoop\/"},"category_info":"<a href=\"https:\/\/ddi.mohflo.net\/index.php\/category\/uncategorized\/\" rel=\"category tag\">Uncategorized<\/a>","tag_info":"Uncategorized","comment_count":"0","jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/posts\/7557","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/users\/11"}],"replies":[{"embeddable":true,"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/comments?post=7557"}],"version-history":[{"count":0,"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/posts\/7557\/revisions"}],"wp:attachment":[{"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/media?parent=7557"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/categories?post=7557"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ddi.mohflo.net\/index.php\/wp-json\/wp\/v2\/tags?post=7557"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}

{"id":7557,"date":"2025-04-22T18:41:28","date_gmt":"2025-04-22T23:41:28","guid":{"rendered":"https:\/\/cyberscoop.com\/?p=84260"},"modified":"2025-04-22T18:41:28","modified_gmt":"2025-04-22T23:41:28","slug":"outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release","status":"publish","type":"post","link":"https:\/\/ddi.mohflo.net\/index.php\/2025\/04\/22\/outside-experts-pick-up-the-slack-on-safety-testing-on-openais-newest-model-release\/","title":{"rendered":"Outside experts pick up the slack on safety testing on OpenAI\u2019s newest model release"},"content":{"rendered":"