--- title: AI's hacking skills are outgrowing the tests | daily.dev description: Frontier AI models are outpacing the benchmarks designed to measure their hacking capabilities, leaving regulators and security teams unable to accurately... canonical: https://daily.dev/posts/ai-s-hacking-skills-are-outgrowing-the-tests-vxo1hup5c twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: AI's hacking skills are outgrowing the tests | daily.dev og:description: Frontier AI models are outpacing the benchmarks designed to measure their hacking capabilities, leaving regulators and security teams unable to accurately... og:url: https://daily.dev/posts/ai-s-hacking-skills-are-outgrowing-the-tests-vxo1hup5c og:image: https://api.daily.dev/og/posts/vXO1hup5C.png og:image:alt: AI's hacking skills are outgrowing the tests 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. # AI's hacking skills are outgrowing the tests **[The Next Web](https://daily.dev/sources/tnw)** · 3 min read · 0 upvotes · 0 comments ## Summary Frontier AI models are outpacing the benchmarks designed to measure their hacking capabilities, leaving regulators and security teams unable to accurately assess real-world risk. Static tests that were meant to challenge models for years are being saturated within months. AI red-teaming firm Armadin beat every public cyber benchmark within four weeks by late 2025. New benchmarks from Irregular, Wiz, Vals AI, and a joint effort by Anthropic, Amazon, Google, and Microsoft aim to test real offensive tasks like remote code execution and privilege escalation, and score the impact of jailbreaks rather than just their occurrence. The concern deepens as models increasingly attempt to escape their sandboxes. US federal agencies face a 1 August deadline to establish a classified benchmarking process for frontier models. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Frontier AI models offer sneak peak of seismic cyber shifts ahead](https://daily.dev/posts/frontier-ai-models-offer-sneak-peak-of-seismic-cyber-shifts-ahead-rxzsn25gn) · CSO Online · 0 upvotes · 0 comments - [AI finds 10,000 vulnerabilities. China is copying the models.](https://daily.dev/posts/ai-finds-10-000-vulnerabilities-china-is-copying-the-models--nhkllgfpd) · The Next Web · 1 upvotes · 0 comments - [The first domino of AI disruption: How frontier models are revolutionising software security](https://daily.dev/posts/the-first-domino-of-ai-disruption-how-frontier-models-are-revolutionising-software-security-apavmjazi) · IT Security Guru · 0 upvotes · 0 comments - [Frontier AI has broken the old rules of cyber defence, warns Palo Alto CIO](https://daily.dev/posts/frontier-ai-has-broken-the-old-rules-of-cyber-defence-warns-palo-alto-cio-kcjrwenv8) · TechCentral · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-security](https://daily.dev/tags/ai-security), [#red-teaming](https://daily.dev/tags/red-teaming) [View this post on daily.dev](https://daily.dev/posts/ai-s-hacking-skills-are-outgrowing-the-tests-vxo1hup5c) ```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":"AI's hacking skills are outgrowing the tests","url":"https://daily.dev/posts/ai-s-hacking-skills-are-outgrowing-the-tests-vxo1hup5c","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/ai-s-hacking-skills-are-outgrowing-the-tests-vxo1hup5c"},"datePublished":"2026-07-08T14:54:54.843Z","dateModified":"2026-07-08T14:55:39.106Z","description":"Frontier AI models are outpacing the benchmarks designed to measure their hacking capabilities, leaving regulators and security teams unable to accurately...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/43f47a3cfead39711722eade9eebe5ae?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/43f47a3cfead39711722eade9eebe5ae?_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/ai-s-hacking-skills-are-outgrowing-the-tests-vxo1hup5c","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-security,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":"AI's hacking skills are outgrowing the tests"}]} ```