--- title: OpenAI built GPT-Red to hack its own AI, and hid it description: OpenAI has developed GPT-Red, an automated AI red-teaming model trained to attack its own AI systems to find and patch vulnerabilities before release. Using a... canonical: https://daily.dev/posts/openai-built-gpt-red-to-hack-its-own-ai-and-hid-it-56mlz7tpz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: OpenAI built GPT-Red to hack its own AI, and hid it | daily.dev og:description: OpenAI has developed GPT-Red, an automated AI red-teaming model trained to attack its own AI systems to find and patch vulnerabilities before release. Using a... og:url: https://daily.dev/posts/openai-built-gpt-red-to-hack-its-own-ai-and-hid-it-56mlz7tpz og:image: https://api.daily.dev/og/posts/56MLZ7TpZ.png og:image:alt: OpenAI built GPT-Red to hack its own AI, and hid it og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # OpenAI built GPT-Red to hack its own AI, and hid it **[The Next Web](https://daily.dev/sources/tnw)** · 3 min read · 0 upvotes · 0 comments ## Summary OpenAI has developed GPT-Red, an automated AI red-teaming model trained to attack its own AI systems to find and patch vulnerabilities before release. Using a self-play training loop against defender models, GPT-Red discovered a novel attack class called 'fake chain of thought' that plants false information in a model's working memory. In tests, it cracked over 90% of attacks against older GPT-5 but only 23% against the newly hardened GPT-5.6, and outperformed human red-teamers 84% to 13%. OpenAI used GPT-Red to harden GPT-5.6 against prompt injection but will not release the model publicly due to its offensive capabilities. GPT-Red still has limitations, including weakness against multi-turn attacks and image-embedded instructions. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#llm](https://daily.dev/tags/llm), [#openai](https://daily.dev/tags/openai), [#ai-security](https://daily.dev/tags/ai-security), [#prompt-injection](https://daily.dev/tags/prompt-injection), [#red-teaming](https://daily.dev/tags/red-teaming) [View this post on daily.dev](https://daily.dev/posts/openai-built-gpt-red-to-hack-its-own-ai-and-hid-it-56mlz7tpz) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"OpenAI built GPT-Red to hack its own AI, and hid it","url":"https://daily.dev/posts/openai-built-gpt-red-to-hack-its-own-ai-and-hid-it-56mlz7tpz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/openai-built-gpt-red-to-hack-its-own-ai-and-hid-it-56mlz7tpz"},"datePublished":"2026-07-15T22:18:46.748Z","dateModified":"2026-07-16T02:25:57.635Z","description":"OpenAI has developed GPT-Red, an automated AI red-teaming model trained to attack its own AI systems to find and patch vulnerabilities before release. Using a...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/66b72644557726dc2517f9cb5b5fcfb8?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/66b72644557726dc2517f9cb5b5fcfb8?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The Next Web","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The Next Web","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/tnw","url":"https://daily.dev/sources/tnw"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/openai-built-gpt-red-to-hack-its-own-ai-and-hid-it-56mlz7tpz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,openai,ai-security,prompt-injection,red-teaming","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The Next Web","item":"https://daily.dev/sources/tnw"},{"@type":"ListItem","position":3,"name":"OpenAI built GPT-Red to hack its own AI, and hid it"}]} ```