--- title: AI Is Getting Scarily Good at Finding Security... description: AI models are increasingly capable of finding security vulnerabilities faster and more contextually than traditional tools, approaching the reasoning of... canonical: https://daily.dev/posts/ai-is-getting-scarily-good-at-finding-security-vulnerabilities-now-what--ee8iej5iv twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: AI Is Getting Scarily Good at Finding Security Vulnerabilities. Now What? | daily.dev og:description: AI models are increasingly capable of finding security vulnerabilities faster and more contextually than traditional tools, approaching the reasoning of... og:url: https://daily.dev/posts/ai-is-getting-scarily-good-at-finding-security-vulnerabilities-now-what--ee8iej5iv og:image: https://api.daily.dev/og/posts/EE8IeJ5iV.png og:image:alt: AI Is Getting Scarily Good at Finding Security Vulnerabilities. Now What? 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 Is Getting Scarily Good at Finding Security Vulnerabilities. Now What? **[Medium](https://daily.dev/sources/medium_js)** · 2 min read · 0 upvotes · 0 comments ## Summary AI models are increasingly capable of finding security vulnerabilities faster and more contextually than traditional tools, approaching the reasoning of experienced security researchers. However, false positives remain a significant problem, burdening open-source maintainers and making signal-to-noise separation difficult. Experts advocate for a hybrid approach: adversarial AI review pipelines, human confirmation of AI findings, and shifting security review earlier in the development lifecycle. The next major challenge is not just detection but automated remediation at scale. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Why are cybersecurity experts worried about AI models finding software vulnerabilities? An AI model found thousands of high- and critical-severity vulnerabilities across major operating systems and browsers without being explicitly trained for security research, prompting major tech companies to form a joint initiative against AI-assisted cyberattacks. The concern is that this capability could expand the attack surface as easily as it strengthens defenses, since the same skill helps both attackers and defenders. _Track how AI is reshaping vulnerability research and defensive tooling by following security coverage on daily.dev._ ### How can teams reduce false positives from AI-based vulnerability scanning? Some tools run adversarial review, where one AI's findings are challenged and validated by another model or agent before reaching a human reviewer, cutting down on false positives. Experts still insist AI-flagged issues require human confirmation since AI outputs are probabilistic rather than final verdicts, and recommend dynamic threat modeling and red teaming alongside earlier security review in the development pipeline. _Developers evaluating AI security tooling can compare approaches to false-positive reduction on daily.dev._ ## Similar posts on daily.dev - [AI is turning offensive security into a continuous necessity](https://daily.dev/posts/ai-is-turning-offensive-security-into-a-continuous-necessity-dtkmtrav8) · CSO Online · 0 upvotes · 0 comments - [AI gets good at finding bugs, not as good at fixing them](https://daily.dev/posts/ai-gets-good-at-finding-bugs-not-as-good-at-fixing-them-sptd5ofrp) · The Register · 0 upvotes · 0 comments - [AI is Coding Us Into a Corner](https://daily.dev/posts/ai-is-coding-us-into-a-corner-xg52035q1) · DevOps.com · 0 upvotes · 0 comments - [AI Is Forcing a New Open Source Security Model](https://daily.dev/posts/ai-is-forcing-a-new-open-source-security-model-c8mvjeytk) · Security Boulevard · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#appsec](https://daily.dev/tags/appsec), [#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-is-getting-scarily-good-at-finding-security-vulnerabilities-now-what--ee8iej5iv) ```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 Is Getting Scarily Good at Finding Security Vulnerabilities. Now What?","url":"https://daily.dev/posts/ai-is-getting-scarily-good-at-finding-security-vulnerabilities-now-what--ee8iej5iv","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/ai-is-getting-scarily-good-at-finding-security-vulnerabilities-now-what--ee8iej5iv"},"datePublished":"2026-07-23T04:54:40.211Z","dateModified":"2026-09-14T06:01:00.263Z","description":"AI models are increasingly capable of finding security vulnerabilities faster and more contextually than traditional tools, approaching the reasoning of...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d6ab0a9a223ee01bc82d647f54feb2d2?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d6ab0a9a223ee01bc82d647f54feb2d2?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Medium","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":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/ai-is-getting-scarily-good-at-finding-security-vulnerabilities-now-what--ee8iej5iv","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,appsec,ai-security,red-teaming","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"AI Is Getting Scarily Good at Finding Security Vulnerabilities. Now What?"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/ai-is-getting-scarily-good-at-finding-security-vulnerabilities-now-what--ee8iej5iv#faq","mainEntity":[{"@type":"Question","name":"Why are cybersecurity experts worried about AI models finding software vulnerabilities?","acceptedAnswer":{"@type":"Answer","text":"An AI model found thousands of high- and critical-severity vulnerabilities across major operating systems and browsers without being explicitly trained for security research, prompting major tech companies to form a joint initiative against AI-assisted cyberattacks. The concern is that this capability could expand the attack surface as easily as it strengthens defenses, since the same skill helps both attackers and defenders. Track how AI is reshaping vulnerability research and defensive tooling by following security coverage on daily.dev."}},{"@type":"Question","name":"How can teams reduce false positives from AI-based vulnerability scanning?","acceptedAnswer":{"@type":"Answer","text":"Some tools run adversarial review, where one AI's findings are challenged and validated by another model or agent before reaching a human reviewer, cutting down on false positives. Experts still insist AI-flagged issues require human confirmation since AI outputs are probabilistic rather than final verdicts, and recommend dynamic threat modeling and red teaming alongside earlier security review in the development pipeline. Developers evaluating AI security tooling can compare approaches to false-positive reduction on daily.dev."}}]} ```