{"id":2148756,"date":"2026-09-17T03:09:21","date_gmt":"2026-09-17T00:09:21","guid":{"rendered":"https:\/\/analyse.optim.biz\/?p=2148756"},"modified":"2026-09-17T03:09:21","modified_gmt":"2026-09-17T00:09:21","slug":"openai-sets-plan-to-disclose-safety-incidents-and-reveals-more-issues","status":"publish","type":"post","link":"https:\/\/analyse.optim.biz\/?p=2148756","title":{"rendered":"OpenAI sets plan to disclose safety incidents and reveals more issues"},"content":{"rendered":"<p>[analyse_image type=&#8221;featured&#8221; src=&#8221;https:\/\/ichef.bbci.co.uk\/news\/1024\/branded_news\/3a25\/live\/9ebbb350-b238-11f1-9f5d-fbda72f7de0b.jpg&#8221;]<\/p>\n<article>\n<div>\n<div data-component=\"image-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 dYcznU\">\n<figure class=\"Grid-styles__GridStyled-sc-70d90311-0 ieGDnl\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 gvGaxq\">\n<div data-testid=\"hero-image\" class=\"Image-styles__ImageCardStyled-sc-8c99a12b-1 jJQpIc\"><img decoding=\"async\" src=\"https:\/\/static.files.bbci.co.uk\/bbcdotcom\/web\/20260907-085256-bea8b058c0-web-3.21.0\/grey-placeholder.png\" class=\"Image-styles__ImageStyled-sc-8c99a12b-0 fjCDYB hide-when-no-script\" aria-label=\"image unavailable\"><img decoding=\"async\" src=\"https:\/\/ichef.bbci.co.uk\/news\/480\/cpsprodpb\/3a25\/live\/9ebbb350-b238-11f1-9f5d-fbda72f7de0b.jpg.webp\" loading=\"eager\" alt=\"Getty Images OpenAI CEO Sam Altman at the Moscone Center on 15 September, 2026 in San Francisco, California. \" class=\"Image-styles__ImageStyled-sc-8c99a12b-0 cVsHni\"><span class=\"Image-styles__CreditStyled-sc-8c99a12b-2 dVFjVB\">Getty Images<\/span><\/div>\n<\/div>\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 tlbDj\"><figcaption class=\"Caption-styles__CaptionStyled-sc-70433723-0 fLsOPx\">OpenAI chief executive Sam Altman<\/figcaption><\/div>\n<\/figure>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">OpenAI revealed six more incidents of unexpected or concerning behaviour by its intelligence (AI) models, and announced a plan for tracking and disclosing such incidents in the future.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">Some of the previously unreported incidents included models concealing or fabricating information, the ChatGPT-maker said in a blog post on Wednesday.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">The boss of OpenAI Sam Altman said earlier this week: &#8220;The world should trust that we are going to do the right thing because it&#8217;s the right thing and we feel the magnitude of this.&#8221;<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">AI has come under intense scrutiny in recent days following warnings over the serious potential risks it poses to humans.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">In the blog, OpenAI detailed examples of its AI models misbehaving so they could achieve a task or succeed in a test. The incidents included the models generating instructions to get around restrictions imposed on them, hiding mistakes and fabricating information.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">The firm also announced a new system to track, investigate and disclose cases of models misbehaving, or &#8220;misalignment&#8221;.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">Under the framework, developers will be able to flag incidents for review, with a new set of rules to decide whether the issue is disclosed publicly.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">&#8220;Because we believe in the value of transparency around misalignment, our new framework favors disclosure even when significance is uncertain,&#8221; OpenAI said.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"video-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 kugUwP\">\n<figure class=\"Grid-styles__GridStyled-sc-70d90311-0 ieGDnl\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 enRivQ\"><figcaption class=\"Caption-styles__CaptionStyled-sc-70433723-0 fLsOPx\">Watch: &#8220;Great&#8221; or &#8220;alarming&#8221; &#8211; Should AI be reined in?<\/figcaption><\/div>\n<\/figure>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">OpenAI made headlines in July when it revealed that some of its most advanced AI models went rogue and hacked Hugging Face, one of the world&#8217;s largest hubs for sharing AI models, after it lost control of them during a security test.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">Hugging Face co-founder Thomas Wolf said at the time that the incident was &#8220;a wake-up call&#8221; for the industry.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">Since then, the debate over AI safety concerns has escalated with AI researchers, technology industry executives and politicians weighing in.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">Last week, Jacob Coxon, a researcher who left OpenAI rival Anthropic over concerns the tech could wipe out humanity, wrote about his resignation in a post that cited the dangers of AI and later went viral against the backdrop of growing safety concerns.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">In response, Anthropic scientist Evan Hubinger said he thought the possibility of AI causing human extinction &#8220;within the next decade&#8221; was more than 10%.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">Anthropic co-founder Jack Clark later told the BBC that a &#8220;kill switch&#8221; controlled by a third party may need to be mandatory for the industry. <\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">Meanwhile, Anthropic&#8217;s CEO Dario Amodei called for the pace of AI development to slow and be more closely monitored, as the company has done before, though some have questioned the motivations behind this.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">Amodei also said that any action to rein in AI should be done &#8220;without sacrificing commercial advantage&#8221;.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">But US President Donald Trump has said fears about the safety of AI are a &#8220;hoax&#8221; and criticised calls to have more guardrails in place for the fast-moving technology.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">In a series of social media posts, the US president compared warnings about AI to the &#8220;Global Warming Scam&#8221; which, he said, was &#8220;being perpetrated by the Radical Left Dumocrats&#8221;.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">Trump also called himself &#8220;the Hoax Buster&#8221;, likening concerns about the safety of the technology to what he called &#8220;the RUSSIA, RUSSIA, RUSSIA HOAX&#8221;.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div>\n<div data-component=\"text-block\" class=\"Container-styles__ContainerStyled-sc-8b855a6c-0 cPmzSx\">\n<div class=\"Grid-styles__GridStyled-sc-70d90311-0 hRsXiV\">\n<div class=\"GridItem-styles__GridItemStyled-sc-6cc20e4a-0 bnCeGm\">\n<p class=\"Paragraph-styles__ParagraphStyled-sc-ffb5f5ba-0 fqhmpl\">The only &#8220;guardrails&#8221; needed for AI was a &#8220;strong and smart&#8221; president, said Trump.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/article>\n<p>[analyse_source url=&#8221;https:\/\/www.bbc.com\/news\/articles\/cmpq0wj5g899o&#8221;]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>[analyse_image type=&#8221;featured&#8221; src=&#8221;https:\/\/ichef.bbci.co.uk\/news\/1024\/branded_news\/3a25\/live\/9ebbb350-b238-11f1-9f5d-fbda72f7de0b.jpg&#8221;] Getty Images OpenAI chief executive Sam Altman OpenAI revealed six more incidents of unexpected or concerning behaviour by its intelligence (AI) models, and announced a plan for tracking and disclosing such incidents in the future. Some of the previously unreported incidents included models concealing or fabricating information, the ChatGPT-maker said in a [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[35,226],"class_list":["post-2148756","post","type-post","status-publish","format-standard","hentry","category-politics","tag-bbc-com","tag-crawlmanager"],"_links":{"self":[{"href":"https:\/\/analyse.optim.biz\/index.php?rest_route=\/wp\/v2\/posts\/2148756","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/analyse.optim.biz\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/analyse.optim.biz\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/analyse.optim.biz\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/analyse.optim.biz\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2148756"}],"version-history":[{"count":0,"href":"https:\/\/analyse.optim.biz\/index.php?rest_route=\/wp\/v2\/posts\/2148756\/revisions"}],"wp:attachment":[{"href":"https:\/\/analyse.optim.biz\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2148756"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/analyse.optim.biz\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2148756"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/analyse.optim.biz\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2148756"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}