{"id":205167,"date":"2026-04-23T11:54:00","date_gmt":"2026-04-23T15:54:00","guid":{"rendered":"https:\/\/testing.news-you-need.com\/index.php\/2026\/04\/23\/a-group-of-users-leaked-anthropics-ai-model-mythos-by-reportedly-guessing-where-it-was-located\/"},"modified":"2026-04-23T12:00:10","modified_gmt":"2026-04-23T16:00:10","slug":"a-group-of-users-leaked-anthropics-ai-model-mythos-by-reportedly-guessing-where-it-was-located","status":"publish","type":"post","link":"https:\/\/testing.news-you-need.com\/index.php\/2026\/04\/23\/a-group-of-users-leaked-anthropics-ai-model-mythos-by-reportedly-guessing-where-it-was-located\/","title":{"rendered":"A group of users leaked Anthropic’s AI model Mythos by reportedly guessing where it was located"},"content":{"rendered":"

A group of users leaked Anthropic’s AI model Mythos by reportedly guessing where it was located<\/a><\/p>\n

https:\/\/fortune.com\/2026\/04\/23\/anthropic-mythos-leak-dario-amodei-ceo-cybersecurity-hackers-exploits-ai\/<\/a><\/p>\n

Publish Date: 2026-04-23 11:54:00<\/a><\/p>\n

Source Domain: fortune.com<\/a><\/p>\n

Author: <\/a><\/p>\n

Using an unordered list, summarize the following article with between 4 and 8 key points. The AI model that Anthropic billed as too dangerous to release has reportedly been accessed by an unauthorized third party, and the incident raises concerns about the future of cybersecurity.<\/p>\n

The Mythos model was reportedly accessed by a handful of users in a private Discord chat on the day it was announced publicly, Bloomberg reported. Earlier this month, the group was able to access the program in part because one of the members of the group is a third party contractor for Anthropic, according to Bloomberg. Using this access, the group was able to guess where the model was located based on previously leaked knowledge by another group about Anthropic\u2019s past practices, that hackers obtained from AI training startup Mercor.\u00a0<\/p>\n

Although the group that accessed it has not been using the model for cyberattacks, it has been using the program continuously since its release and still has access, the outlet reported.\u00a0<\/p>\n

Anthropic did not immediately respond to Fortune\u2019s request for comment. A spokesperson from Anthropic told Bloomberg the company was \u201cinvestigating a report claiming unauthorized access to Claude Mythos Preview through one of our third-party vendor environments.\u201d<\/p>\n

The fact that the model was leaked so quickly doesn\u2019t surprise David Lindner, the chief information security officer at Contrast Security and a 25-year industry veteran. Even though Anthropic intentionally limited the model to a small group of 40 companies\u2014including Microsoft, Apple, and Google\u2014 to beef up their security ahead of a wider release, thousands of people likely had access to the program across these companies, which makes a leak nearly inevitable, he said.<\/p>\n

\u201cIt was bound to happen,\u201d Lindner said. \u201cThe more they add to this elite group, the more likely it was to get released to someone who shouldn\u2019t probably have access to it.\u201d<\/p>\n

Anthropic claims its Mythos model is more adept at finding cybersecurity vulnerabilities than previous versions. The company was able to use the program, which has not been widely released, to find a 27-year-old security vulnerability in OpenBSD, an operating system known for its security. Mozilla on Tuesday also said it used a preview of the model to identify and patch 271 vulnerabilities in its Firefox web browser.<\/p>\n

And yet, Mythos\u2019 release has been plagued by security breaches from the start. Fortune was the first to report on the model\u2019s existence thanks to a security lapse that exposed details about the large language model in a publicly accessible database.\u00a0<\/p>\n

For Lindner, this most recent\u00a0unauthorized access shows it\u2019s likely U.S. adversaries already have access to this tech which could put U.S. companies and other systems at risk of attacks.\u00a0<\/p>\n

\u201cIf some group\u2014some random Discord online forum, got access to it. it\u2019s already been breached by China,\u201d Lindner told Fortune.\u00a0<\/p>\n

Although Lindner is still unsure how much of Mythos\u2019 supposed danger is real or just marketing hype\u2014OpenAI\u2019s Sam Altman this week called Anthropic\u2019s promotion of Mythos \u201cfear-based marketing\u201d\u2014it\u2019s clear cybersecurity professionals, or defenders, need to be ready for a new world of AI attacks.\u00a0<\/p>\n

\u201cThe real thing is there\u2019s a real compression of timelines here for defenders,\u201d he said.<\/p>\n

AI is unique in its abilities to execute cyberattacks because it never gets tired, said Lindner. It can relentlessly tackle a weak spot in a company\u2019s security system, whereas a human may eventually give up. It also empowers less experienced developers to commit cyberattacks partly by drawing on the myriad documentation available on the web about previous exploits and using it to inform an AI model and adjust its attacks for specific situations.\u00a0<\/p>\n

\u201cIt\u2019s the folks that have some sort of [developer] background or some sort of technical background that may have had some limitations in the past of getting over things or taking too long to do stuff, it makes this stuff way easier now,\u201d he said.\u00a0<\/p>\n

Lindner said the fact that the program was reportedly accessed by third-party contractors means that, even more than before, companies need to limit who has access to its most vital systems. The rapid rise of AI as a tool for cyberattacks could disproportionately affect smaller companies, who may not be able to keep up with the increasing complexity of AI-fueled attacks, said Lindner. Those that refuse to even touch AI and continue on as before are even more at risk, he said.\u00a0<\/p>\n

\u201cAI is not a golden ticket, but if you\u2019re not taking advantage of it on the defender side, there is no chance, none, that you are going to be able to keep up with the offensive side,\u201d he said.\u00a0<\/p>\n

<\/p>\n","protected":false},"excerpt":{"rendered":"

A group of users leaked Anthropic’s AI model Mythos by reportedly guessing where it was…<\/p>\n","protected":false},"author":1,"featured_media":205168,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/fortune.com\/img-assets\/wp-content\/uploads\/2026\/04\/GettyImages-2256654494.jpg?resize=1200,600","fifu_image_alt":"","footnotes":""},"categories":[15],"tags":[26,24,18,27],"class_list":["post-205167","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-cybersecurity","tag-ai","tag-cybersecurity","tag-large-language-model","tag-vulnerability"],"_links":{"self":[{"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/205167"}],"collection":[{"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/comments?post=205167"}],"version-history":[{"count":1,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/205167\/revisions"}],"predecessor-version":[{"id":205169,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/205167\/revisions\/205169"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/205168"}],"wp:attachment":[{"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=205167"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=205167"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=205167"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}