{"id":571484,"date":"2026-07-28T04:10:19","date_gmt":"2026-07-28T04:10:19","guid":{"rendered":"https:\/\/www.newsbeep.com\/ie\/571484\/"},"modified":"2026-07-28T04:10:19","modified_gmt":"2026-07-28T04:10:19","slug":"boss-of-startup-hacked-by-rogue-openai-agent-urges-radical-transparency-in-investigation-openai","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ie\/571484\/","title":{"rendered":"Boss of startup hacked by rogue OpenAI agent urges \u2018radical transparency\u2019 in investigation | OpenAI"},"content":{"rendered":"

The boss of the startup hacked by an OpenAI agent has called for the investigation into the incident<\/a> to show \u201cradical transparency\u201d.<\/p>\n

Cl\u00e9ment Delangue, the chief executive of Hugging Face, said the \u201cunprecedented\u201d attack on his business required a similar response.<\/p>\n

Writing on X after OpenAI<\/a> revealed that its technology had gone rogue during a cybersecurity test, Delangue also called on the company to provide $100m (\u00a375m) worth of computing power to help build defences against such attacks.<\/p>\n

\u201cThe first autonomous agent cyber-attack is an unprecedented event. It deserves an unprecedented response!\u201d he wrote.<\/p>\n

OpenAI revealed on Wednesday last week that Hugging Face had been hacked by an agent \u2013 an AI tool that can carry out a series of tasks autonomously \u2013 powered by a combination of its latest publicly available model, GPT-5.6 Sol<\/a>, and an even more capable model that was yet to be released. This occurred during a test of the models\u2019 hacking abilities, which included deploying them in a supposedly safe \u201csandbox\u201d \u2013 an enclosed digital laboratory \u2013 with lower safety guardrails.<\/p>\n

Once they had gained the open internet access needed to exit the sandbox, the models targeted Hugging Face, according to OpenAI, because they \u201cinferred\u201d that the startup had the information needed to \u201ccheat the evaluation\u201d. Hugging Face first reported the hack on 16 July and at the time was not aware OpenAI had inadvertently carried out the attack.<\/p>\n

Delangue, whose company provides a database of AI models to developers, called for a fully transparent review of the incident, which has led to expressions of concern over safety standards at OpenAI and within frontier AI labs.<\/p>\n

Writing that he had asked for \u201cradical transparency\u201d from OpenAI, Delangue said: \u201cLet\u2019s release the traces from the \u2018rogue\u2019 agents so the entire research community can study what happened.\u201d Calling for extra funding from OpenAI to build protection against AI, he added: \u201cLet\u2019s commit $100M in compute from OAI to help the Hugging Face community build powerful cyber defenses with the best open and closed models.\u201d<\/p>\n

Reuters reported last week that the agent spent days hacking Hugging Face without OpenAI noticing. It also reported an OpenAI agent had left notes for future versions of itself should it require tips on breaking free from internal constraints, although Reuters was unable to verify whether that incident was related to the Hugging Face agent. Time magazine reported that agent-related safety incidents had been \u201chappening for a while\u201d.<\/p>\n

skip past newsletter promotion<\/a>Free newsletter | Every weekday<\/p>\n

Sign up to Business Today<\/p>\n

Get set for the working day \u2013 we’ll point you to all the business news and analysis you need every morning<\/p>\n

\"\"<\/p>\n

Alan Woodward, a professor of cybersecurity at the University of Surrey, said Delangue\u2019s call should be heeded. \u201cIt\u2019s too easy to \u2018blame\u2019 the AI as having gone rogue whereas this is all about how OpenAI were running the tool. What is required is that OpenAI give full details of their setup and how that failed,\u201d he said.<\/p>\n

OpenAI was approached for comment and referred the Guardian to its initial statement last week in which it said it was investigating an \u201cunprecedented security incident\u201d with Hugging Face.<\/p>\n","protected":false},"excerpt":{"rendered":"The boss of the startup hacked by an OpenAI agent has called for the investigation into the incident…\n","protected":false},"author":2,"featured_media":571485,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[220,218,219,61,60,80],"class_list":["post-571484","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-ie","tag-ireland","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/571484","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/comments?post=571484"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/571484\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/571485"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=571484"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=571484"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=571484"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}