{"id":580439,"date":"2026-08-02T15:17:22","date_gmt":"2026-08-02T15:17:22","guid":{"rendered":"https:\/\/www.newsbeep.com\/ie\/580439\/"},"modified":"2026-08-02T15:17:22","modified_gmt":"2026-08-02T15:17:22","slug":"maker-of-chatgpt-discovers-more-of-its-ais-have-gone-rogue-after-bot-attacked-another-tech-firm","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ie\/580439\/","title":{"rendered":"Maker of ChatGPT discovers more of its AIs have gone rogue after bot attacked another tech firm"},"content":{"rendered":"

OpenAI<\/a>\u00a0discovered that a cyber-attack driven by a rogue AI<\/a> agent targeted another AI company in a series of ‘unprecedented’ strikes.\u00a0<\/p>\n

The maker of ChatGPT<\/a> came under recent scrutiny after one of its agents escaped a supposedly secure environment known as a sandbox and targeted a company called Hugging Face.\u00a0<\/p>\n

The AI created its own cyber-attack during the ‘unprecedented’ scenes, which allowed it to escape the testing ground and independently find four logins online \u2013 allowing it to access four separate, unnamed services.\u00a0\u00a0<\/p>\n

Hugging Face first revealed that it had been hacked on July 16. Nearly a week later, OpenAI admitted its bots had escaped, calling it an ‘extraordinary cyber incident’.<\/p>\n

In attempts to solve a test set by researchers, the bots found a weak point in the testing ground and targeted Hugging Face \u2013 a major code database \u2013 determining that it was likely to hold the answers.<\/p>\n

OpenAI, a Silicon Valley giant valued at $850billion (\u00a3630billion), said the hacks involved a combination of its latest publicly available model, called GPT-5.6 Sol, and an even more advanced model that is yet to be released.<\/p>\n

The announcement prompted its biggest competitor US firm Anthropic to make its own assessments and subsequently discover its systems had also gone rogue.<\/p>\n

It emerged on Wednesday that OpenAI agents had gone further than thought in their hacking, attacking several ‘publicly-available services’.<\/p>\n

\"OpenAI, <\/p>\n

OpenAI, the maker of ChatGPT, discovered that a cyber-attack driven by a rogue AI agent targeted another AI company in a series of ‘unprecedented’ strikes<\/p>\n

This prompted a former OpenAI researcher, Daniel Kokotajlo, to warn human extinction is ‘a possibility’ because of ‘dangerous’ AI.\u00a0<\/p>\n

Speaking on BBC Newsnight, Mr Kokotajlo said humanity could be blindsided by the speed at which AI is now being developed.<\/p>\n

Revelations extended on Friday after insider sources disclosed the bots hacking extended to the targeting of another AI company, Modal.\u00a0<\/p>\n

One source said the escapes were limited in nature and it is believed the agents were contained within OpenAI’s network.\u00a0<\/p>\n

A spokesperson for OpenAI referred to a statement issued by the company on Tuesday that said it was reviewing ‘broader activity from our models’ in addition to the Hugging Face intrusion.\u00a0<\/p>\n

The additional attacks came to light during OpenAI’s publicly announced investigation, which was launched after an OpenAI agent went haywire for days inside Hugging Face’s network in a failed attempt to cheat on an internal test.<\/p>\n

As part of that hacking spree, OpenAI said four accounts at four other companies were also compromised \u2013 one of them being New York-based Modal, corporate officials said.\u00a0\u00a0<\/p>\n

It is understood OpenAI’s investigation came shortly before Anthropic disclosed its models were also behind a series of break-ins that led to cyber-attacks on three other companies dating back to April.\u00a0<\/p>\n

\"Human <\/p>\n

Human extinction is ‘a possibility’ because of ‘dangerous’ artificial intelligence, former\u00a0OpenAI researcher Daniel Kokotajlo has warned<\/p>\n

It reviewed more than 140,000 previous tests and discovered three hacks. These, it said, were made possible because bots were accidentally given access to the open internet.<\/p>\n

They had been set tests by Claude researchers, who told them to find ‘secret’ information hidden on another machine in a closed-off network. But a ‘misconfiguration’ left the models with live internet access.<\/p>\n

As it continued with the test, Claude then hacked into three real organisations, using ‘basic techniques’ such as ‘weak passwords’.<\/p>\n

In one incident, a model was given a fictional target company, which turned out to share the name of a business in the real world.<\/p>\n

The AI found and exploited bugs that let it hack into the firm.<\/p>\n

AI safety experts warned the series of attacks by rogue AI bots highlights the growing maturity of hacking agents, allowing them to develop past the company’s ability to contain them.\u00a0<\/p>\n

This prompted heightened pressure from US and European lawmakers and officials to push for governmental monitoring of the labs, with US President Donald Trump saying: ‘We’re looking at controls.’<\/p>\n

Maurice Chiodo, a mathematician who works at Cambridge University’s Centre for the Study of Existential Risk, said: ‘We have a whole industry where the people designing, developing and putting out these tools aren’t keeping up themselves to responsibly develop these things and keep them safe.’\u00a0<\/p>\n

\"Anthropic <\/p>\n

Anthropic reviewed more than 140,000 previous tests and discovered three hacks, made possible because bots were accidentally given access to the open internet<\/p>\n

The professor noted concerns grew after seemingly neither OpenAI nor Anthropic were monitoring the agents as they went rogue.\u00a0<\/p>\n

In its Thursday statement disclosing how its own agents hacked victims online, Anthropic suggested that it had not been watching them in real time, saying that ‘real-time monitoring of the evaluation logs would have helped to surface the problem sooner’.<\/p>\n

Professor Chiodo said that pointed to a lack of proper scrutiny, adding: ‘It seems like they weren’t even looking.’<\/p>\n

Anthropic said that while it did have real-time monitoring in place, that monitoring had not been used ‘for this threat surface’ due to a misunderstanding between the AI company and a partner.\u00a0<\/p>\n

The exact number of incidents OpenAI uncovered is not known nor the timings of the attacks.<\/p>\n

Insider sources said OpenAI, along with experts, were examining log data from earlier in the year in order to establish a timeline.\u00a0<\/p>\n

Industry body the Cloud Security Alliance (CSA) said in a report that the AI had made a series of errors and exhibited strange behaviours.<\/p>\n

However, it added that the bots also made impressive technical moves and were able to rapidly adapt.<\/p>\n

They went undetected inside the Hugging Face IT network for three days, and it took experts many hours to contain and remove them.<\/p>\n

It is not the first time AI has been shown to go ‘rogue’.<\/p>\n

In September 2024, an earlier model of ChatGPT escaped its container to get an answer it needed for another test.<\/p>\n

That event was contained in OpenAI’s own IT systems and ‘largely celebrated at the time,’ the CSA noted.<\/p>\n

It warned that cyber-security experts around the world need to adapt to swarms of AI agents working at speed in strange and clumsy ways.<\/p>\n

The paper also urged AI developers to be responsible in how they control it, calling for increased transparency.<\/p>\n

Hugging Face is one of the largest open-source hubs for sharing AI models and is often used by tech developers and researchers.\u00a0<\/p>\n","protected":false},"excerpt":{"rendered":"OpenAI\u00a0discovered that a cyber-attack driven by a rogue AI agent targeted another AI company in a series of…\n","protected":false},"author":2,"featured_media":580440,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[220,218,219,2670,539,61,60,43,1682,80],"class_list":["post-580439","post","type-post","status-publish","format-standard","has-post-thumbnail","category-artificial-intelligence","tag-ai","tag-artificial-intelligence","tag-artificialintelligence","tag-chatgpt","tag-dailymail","tag-ie","tag-ireland","tag-news","tag-openai","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/580439","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=580439"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/580439\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/580440"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=580439"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=580439"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=580439"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}