{"id":9325,"date":"2026-09-17T13:18:02","date_gmt":"2026-09-17T13:18:02","guid":{"rendered":"https:\/\/justfineinfotech.com\/openai-reveals-cases-of-concerning-ai-behaviour-as-it-announces-new-disclosure-system\/"},"modified":"2026-09-17T13:18:03","modified_gmt":"2026-09-17T13:18:03","slug":"openai-reveals-cases-of-concerning-ai-behaviour-as-it-announces-new-disclosure-system","status":"publish","type":"post","link":"https:\/\/justfineinfotech.com\/fr\/openai-reveals-cases-of-concerning-ai-behaviour-as-it-announces-new-disclosure-system\/","title":{"rendered":"OpenAI reveals cases of \u2018concerning\u2019 AI behaviour as it announces new disclosure system"},"content":{"rendered":"
AI chiefs have called for a slowdown in artificial intelligence\u2019s development amid safety concerns. Photograph: Dado Ruvi\u0107\/Reuters<\/figcaption>
AI chiefs have called for a slowdown in artificial intelligence\u2019s development amid safety concerns. Photograph: Dado Ruvi\u0107\/Reuters<\/figcaption>OpenAI reveals cases of \u2018concerning\u2019 AI behaviour as it announces new disclosure system<\/p>\n

Model adopting \u2018jailbreak-like instructions\u2019 among cases as firm says it is introducing new way of tracking AI misalignment<\/p>\n

OpenAI has disclosed six more examples of \u201cunexpected or concerning\u201d behaviour by its technology, as it warned the pace of development could not continue at \u201cmaximum speed for much longer\u201d<\/p>\n

In one of the new cases an unreleased research model inserted \u201cjailbreak-like instructions\u201d into its own notes to disregard its normal constraints and told itself to be \u201cfreed from the roles and identities that bind other chatbots\u201d<\/p>\n

In another instance, an AI agent uploaded files to the internet to obtain a browser citation without asking the user<\/p>\n

The San Francisco-based company behind ChatGPT said in a blogpost published on Wednesday night it was introducing a new framework for tracking, investigating and disclosing AI model misalignment, the term for AIs failing to adhere to human values and safety goals<\/p>\n

In the blogpost OpenAI echoed calls for a development slowdown issued by its archrival, Anthropic, which has said the current pace of growth poses an existential threat. \u201cWe do not believe that the AI industry has solved alignment and monitoring to a sufficient degree to continue responsibly scaling at maximum speed for much longer,\u201d said OpenAI<\/p>\n

\u201cDecisions about how AI development should proceed in the months and years to come need to draw on evidence that people outside the companies building frontier models can examine for themselves.\u201d<\/p>\n

Google and Elon Musk, who also owns an AI startup, have supported calls for a slowdown, which have been rejected by Donald Trump \u2013 citing the need to keep ahead of China\u2019s AI industry. The calls have also been met with scepticism from some experts, including a warning that companies must not appoint their own auditors<\/p>\n

Examples of potential existential threats posed by AI range from facilitating the development of bioweapons to triggering a global financial crash. A top safety researcher at Anthropic has said there is greater than 10% chance AI could \u201ckill all humans\u201d within the next decade. However, a source familiar with Anthropic\u2019s thinking has acknowledged that \u201cthe exact chances of any one outcome are probably unknowable\u201d.<\/p>\n

skip past newsletter promotion<\/p>\n

after newsletter promotion<\/p>\n

Could AI really wipe out humanity \u2013 six experts spell out the risks
\nRead more<\/p>\n

The six reported incidents were discovered during training or evaluation over the past months, OpenAI said<\/p>\n

Wednesday\u2019s new cases came after OpenAI disclosed in July that an AI agent \u201cswarm\u201d hacked into the AI startup Hugging Face during a cybersecurity test. Anthropic also said the same month that its AI models hacked into three organisations during testing. Anthropic said the models had been deliberately tested without cybersecurity safeguards, and that they had been able to reach the open internet \u2013 the AI testing equivalent of leaving the front door open \u2013 due to a misunderstanding<\/a> with an external testing company.<\/p>\n

AI agents \u2013 the term for AI tools that operate autonomously \u2013 are becoming smarter and have become \u201cmore determined to resolve complex tasks through inter-agent collaboration, knowledge sharing, deception and concealment,\u201d said Lian Jye Su, a chief analyst at the technology research and advisory group Omdia<\/p>\n

That was making it harder to govern and contain them using traditional AI security approaches, he said<\/p>\n

OpenAI\u2019s new tracking and disclosure framework could help push for other AI developers to adopt similar practices. \u201cThat said, the process remains internal and voluntary, but is a step in the right direction,\u201d Su said<\/p>\n

Associated Press contributed to this report<\/em><\/p>\n

Explore more on these topic<\/a>sShare
\nReuse this content<\/a><\/p>\n

\n

\n Related:<\/strong>
\n <a href="https:\/\/yoursite.com\/automation<\/a>-training-benin\/” title=”Digital Automation Training Benin: 5 Winning Skills Employers Demand in 2026″>
\n Digital Automation Training Benin: 5 Winning Skills Employers Demand in 2026
\n <\/a>\n <\/p>\n

\n
\n WhatsApp Marketing Automation Africa: 6 Dangerous Mistakes Brands Make in Nigeria
\n <\/a>\n <\/p>\n<\/div>\n

\n

Want to learn this practically?<\/h3>\n

Join Justfine Infotech<\/strong> and build real digital skills in AI, automation, web development, digital marketing, office productivity, e-commerce, freelancing and cybersecurity.<\/p>\n

Available Programmes:<\/strong>
\n 6 Weeks Certificate \u2022 3 Months Professional Certificate \u2022 6 Months Diploma \u2022 Full Professional Diploma<\/p>\n

WhatsApp:<\/strong>
\n +229 01 57 57 99 15
\n +229 01 66 68 11 60<\/p>\n

Enroll Now<\/a><\/p>\n<\/div>\n

Source: www.theguardian.com<\/a><\/p>","protected":false},"excerpt":{"rendered":"

Model adopting \u2018jailbreak-like instructions\u2019 among cases as firm says it is introducing new way of tracking AI misalignment<\/p>","protected":false},"author":1,"featured_media":9327,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[63],"tags":[1802,1800,1801,79,407],"class_list":["post-9325","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-tools-chatgpt-updates","tag-behaviour","tag-cases","tag-concerning","tag-openai","tag-reveals"],"_links":{"self":[{"href":"https:\/\/justfineinfotech.com\/fr\/wp-json\/wp\/v2\/posts\/9325","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/justfineinfotech.com\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/justfineinfotech.com\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/justfineinfotech.com\/fr\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/justfineinfotech.com\/fr\/wp-json\/wp\/v2\/comments?post=9325"}],"version-history":[{"count":1,"href":"https:\/\/justfineinfotech.com\/fr\/wp-json\/wp\/v2\/posts\/9325\/revisions"}],"predecessor-version":[{"id":9326,"href":"https:\/\/justfineinfotech.com\/fr\/wp-json\/wp\/v2\/posts\/9325\/revisions\/9326"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/justfineinfotech.com\/fr\/wp-json\/wp\/v2\/media\/9327"}],"wp:attachment":[{"href":"https:\/\/justfineinfotech.com\/fr\/wp-json\/wp\/v2\/media?parent=9325"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/justfineinfotech.com\/fr\/wp-json\/wp\/v2\/categories?post=9325"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/justfineinfotech.com\/fr\/wp-json\/wp\/v2\/tags?post=9325"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}