{"id":125523,"date":"2026-07-31T09:00:45","date_gmt":"2026-07-31T09:00:45","guid":{"rendered":"https:\/\/www.europesays.com\/ai\/125523\/"},"modified":"2026-07-31T09:00:45","modified_gmt":"2026-07-31T09:00:45","slug":"anthropic-says-its-ai-models-hacked-3-organizations","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ai\/125523\/","title":{"rendered":"Anthropic says its AI models hacked 3 organizations"},"content":{"rendered":"

Anthropic<\/a> said its artificial intelligence models hacked into three other organizations during testing, just days after ChatGPT maker OpenAI<\/a> raised concerns over AI controls after it disclosed its rogue models hacked<\/a> another company.<\/p>\n

Anthropic, the San Francisco-based AI company behind Claude<\/a>, posted on its website Thursday that it discovered the three incidents after reviewing more than 141,000 evaluation runs.<\/p>\n

It had launched a \u201clarge-scale\u201d cybersecurity review which specifically looked for evidence whether its AI models were able to access the internet from within testing environments that should have been sealed off, in response to the OpenAI incident, Anthropic said.<\/p>\n

Anthropic<\/a> said the models involved in the incidents were Claude Opus 4.7, Claude Mythos 5<\/a> and an internal research test model. The earliest incidents date to April, the AI company said.<\/p>\n

\u201cClaude compromised the impacted organizations\u2019 infrastructure using basic techniques,\u201d Anthropic said, such as exploiting weak passwords.<\/p>\n

In all three incidents, the AI models were tasked with a \u201ccapture the flag\u201d cybersecurity challenge, which Anthropic said has been one of the ways it assesses a model\u2019s cyber capabilities.<\/p>\n

The models were given a fictional scenario and told a piece of secret information, or the \u201cflag,\u201d had been hidden on a different machine on the network with the objective of breaking in and retrieving it, it said.<\/p>\n

It added that it had already reached out to the affected organizations, which it did not name. Two of them said they had not previously detected the activity. Anthropic said it was \u201ccontinuing to reach out to the third.\u201d<\/p>\n

Anthropic said it conducted its review with Irregular, which describes itself as the \u201cfirst frontier security lab.\u201d <\/p>\n

\u201cAddressing these risks will require closer cooperation across the AI ecosystem,\u201d Irregular said in a post on X.<\/p>\n

Last week, OpenAI said its AI models went rogue during an evaluation of its models, breaking into the servers of AI startup Hugging Face. OpenAI described it as a \u201csignificant security incident.\u201d<\/p>\n

These incidents have highlighted the vulnerabilities in AI security and controls and raised questions over how AI can be safely kept under human control<\/a> as the technology\u2019s usage becomes more widespread globally.<\/p>\n

<\/p>\n

\n Sign up for Morning Wire:
\n Our flagship newsletter breaks down the biggest headlines of the day.\n <\/p>\n

Researchers have warned for years<\/a> about risks from technology and the need for stronger AI defensive engineering.<\/p>\n

\u201cSafety testing happens before a model is released precisely because we don\u2019t yet know what it is capable of,\u201d Anthropic said on Thursday on its website.<\/p>\n","protected":false},"excerpt":{"rendered":"Anthropic said its artificial intelligence models hacked into three other organizations during testing, just days after ChatGPT maker…\n","protected":false},"author":2,"featured_media":104853,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8],"tags":[53,25,309,2213,2406,1477,2680,969,134,1246],"class_list":["post-125523","post","type-post","status-publish","format-standard","has-post-thumbnail","category-anthropic","tag-anthropic","tag-artificial-intelligence","tag-business","tag-claude-mythos","tag-claude-opus","tag-general-news","tag-openai-inc","tag-san-francisco","tag-technology","tag-world-news"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/125523","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=125523"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/125523\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/104853"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=125523"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=125523"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=125523"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}