{"id":628568,"date":"2026-09-18T13:16:09","date_gmt":"2026-09-18T13:16:09","guid":{"rendered":"https:\/\/www.newsbeep.com\/ie\/628568\/"},"modified":"2026-09-18T13:16:09","modified_gmt":"2026-09-18T13:16:09","slug":"openai-ethically-hacked-with-help-of-anthropics-claude-chatbot-openai","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ie\/628568\/","title":{"rendered":"OpenAI \u2018ethically hacked\u2019 with help of Anthropic\u2019s Claude chatbot | OpenAI"},"content":{"rendered":"

Cybersecurity researchers have hacked into OpenAI with the help of Anthropic\u2019s Claude chatbot, in the latest example of security issues<\/a> at the company.<\/p>\n

A team at a US-based startup compromised a number of OpenAI employees\u2019 ChatGPT<\/a> accounts, starting a process that enabled them to access their target\u2019s software cache \u2013 and potentially more.<\/p>\n

\u201cThe scope of what we could theoretically access was huge,\u201d said researchers at Hacktron AI<\/a>.<\/p>\n

Initially, the research team used Claude, which can generate code for hackers, to access ChatGPT accounts via an OpenAI<\/a> staff discussion forum hosted by the Discourse platform. They then made a harmless \u201cpull request\u201d \u2013 an attempt to change the code in a file \u2013 to OpenAI\u2019s service on the GitHub software repository.<\/p>\n

Hacktron reported the hack to OpenAI, having carried out the operation under an OpenAI programme that rewarded ethical hackers for testing its systems. The researchers stressed that they had access to, but did not download, the code from the GitHub repository.<\/p>\n

Despite initial use of Claude, the researchers said they were largely using OpenAI\u2019s own cutting edge GPT-5.6 Sol model to carry out the hack, which was first reported<\/a> by the Wall Street Journal.<\/p>\n

An OpenAI spokesperson said: \u201cWe thank the researchers for contacting us and sharing their findings\u201d, adding that the company had addressed the vulnerabilities that had been exploited.<\/p>\n

Hacktron said AI tools had made a once-complex hacking task far easier and drastically shortened the time needed to plan and execute an attack. This is a common refrain from cybersecurity experts when discussing the impact of AI.<\/p>\n

\u201cWork that once required a well-resourced team and months of effort can now be compressed into days,\u201d said Hacktron, which received a $6,500 payment from OpenAI under the company\u2019s bug bounty programme.<\/p>\n

The hack is the latest safety incident at OpenAI, which revealed in July that a \u201cswarm\u201d of agents \u2013 the term for AI tools capable of carrying out tasks autonomously \u2013 powered by its technology had hacked<\/a> the AI startup Hugging Face during a cybersecurity test.<\/p>\n

This week the San Francisco-based company revealed six more examples of \u201cunexpected or concerning\u201d actions by its technology, and warned that the pace of development could not continue at \u201cmaximum speed for much longer\u201d.<\/p>\n

Anthropic made a fresh call at the weekend for a slowdown in AI development<\/a>, which was supported by OpenAI, Google DeepMind and Elon Musk. Anthropic also repeated warnings that unrestrained AI development posed an existential threat, concerns that some experts<\/a> are sceptical about.<\/p>\n

Donald Trump has rejected calls for a slowdown, citing a need to stay ahead of China\u2019s AI industry and dismissing \u201cnegative forces \u2026 bringing up things that won\u2019t happen\u201d.<\/p>\n","protected":false},"excerpt":{"rendered":"Cybersecurity researchers have hacked into OpenAI with the help of Anthropic\u2019s Claude chatbot, in the latest example of…\n","protected":false},"author":2,"featured_media":628569,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[220,218,219,61,60,80],"class_list":["post-628568","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\/628568","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=628568"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/628568\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/628569"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=628568"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=628568"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=628568"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}