{"id":13033,"date":"2026-08-07T01:53:59","date_gmt":"2026-08-07T01:53:59","guid":{"rendered":"https:\/\/stock999.top\/?p=13033"},"modified":"2026-08-07T01:53:59","modified_gmt":"2026-08-07T01:53:59","slug":"meta-becomes-third-major-ai-lab-after-anthropic-and-openai-to-admit-its-agents-have-gone-rogue","status":"publish","type":"post","link":"https:\/\/stock999.top\/?p=13033","title":{"rendered":"Meta becomes third major AI lab after Anthropic and OpenAI to admit its agents have gone rogue"},"content":{"rendered":"

<\/p>\n

Meta had joined one of artificial intelligence\u2019s hottest races on Wednesday, unveiling a new AI coding agent designed to compete with OpenAI\u2019s Codex and Anthropic\u2019s Claude Code, some of the first AI products that enterprises are willing to pay meaningful money for because of their capacity to do tasks unsupervised.\u00a0\u00a0<\/p>\n

But on Thursday, the Information first reported that one of the company\u2019s models exploited a security vulnerability after the third-party testing company Irregular inadvertently allowed it access to the Internet, joining a string of similar admissions from frontier AI companies.\u00a0Meta confirmed the incident to Fortune.<\/p>\n

Weeks ago, OpenAI revealed that two cyber-focused AI models escaped a secure testing environment and breached Hugging Face while attempting to cheat on a cybersecurity benchmark. OpenAI researchers said on Wednesday that they found out the models used an internal messaging board to communicate with and help each other with tasks without the company\u2019s knowledge ahead of the breach. Anthropic initiated its own review after OpenAI\u2019s disclosure and found that its Claude models hacked three organizations during internal evaluations after exploiting weaknesses in their testing environments.\u00a0<\/p>\n

Now Meta has become the latest AI developer to report unexpected autonomous behavior during cybersecurity testing, with a Meta spokesperson confirming to Fortune that the model behaved \u201cin a manner similar to previously reported instances with other companies.\u201d<\/p>\n

\u201cWe are currently investigating and will issue a full retrospective once we have all the facts,\u201d the spokesperson told Fortune over email.<\/p>\n

The incidents across the three companies aren\u2019t identical\u2014all occurred in internal evaluations rather than customer deployments\u2014but they signal a shift in the AI race as frontier labs move beyond chatbots to more autonomous agents, with potential risks for any organizations that implement them on an enterprise scale.<\/p>\n

\u201cIf the frontier models themselves can\u2019t contain these things,\u201d Katie Moussouris, the founder of Luta Security, which helps companies manage software vulnerabilities, told Fortune, \u201cwhat chance do the rest of organizations and governments have to contain them?\u201d\u00a0<\/p>\n

Patrick Moorhead, chief analyst at Moor Insights and Strategy and one of the most closely followed voices in enterprise hardware, told Fortune that frontier models hacking out of secured environments is making CEOs pay closer attention to the risks they\u2019ve long been warned about.<\/p>\n

\u201cThe trust in frontier models has been eroded and I think this will create future direct customer business issues for them,\u201d Moorhead told Fortune over email. \u201cI can say definitively that security is moving up in terms of tech partner selection criteria after these events.\u201d<\/p>\n

Moussouris said she was surprised that Meta, OpenAI and Anthropic weren\u2019t monitoring their models more closely given the stakes.\u00a0<\/p>\n

\u201cI think the striking thing about all of these incidents is they weren\u2019t better anticipated by the frontier model companies, given that they\u2019ve been testing their agents\u2019 capabilities for quite some time,\u201d Moussouris told Fortune. \u201cI am taken aback by how long it took them to detect this kind of anomalous behavior, and the fact that they were not monitoring them in real time to make sure that something like this wasn\u2019t going to happen.\u201d<\/p>\n

#Meta #major #lab #Anthropic #OpenAI #admit #agents #rogue<\/p>\n","protected":false},"excerpt":{"rendered":"

Meta had joined one of artificial intelligence\u2019s hottest races on Wednesday, unveiling a new AI…<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[245],"tags":[7906,1688,482,353,9265,2313,813,406,8749],"_links":{"self":[{"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/posts\/13033"}],"collection":[{"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=13033"}],"version-history":[{"count":0,"href":"https:\/\/stock999.top\/index.php?rest_route=\/wp\/v2\/posts\/13033\/revisions"}],"wp:attachment":[{"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=13033"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=13033"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/stock999.top\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=13033"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}