LLM Agents Are Now Finding Zero-Days: How AI is Autonomously Rewriting the Rules of...
LLM Agents Are Now Finding Zero-Days: How AI is Autonomously Rewriting the Rules of Vulnerability Research
Published: May 26, 2026 · ⏱️ 18 min read · Tags: security, llm, ai-agents, vulnerability-research, devops, cybersecurity
Table of Contents
The Day an AI Found a macOS Kernel CVE
What Is LLM Vulnerability Research? (Beyond Static Analysis)
AI shrinks zero-day exploit time from a year to a single day, heading toward one minute — Zero-Day Clock warns security window has collapsed
You Can’t Patch Your Way Out of This One
The AI Era Is Creating a Bug Hunting Arms Race
Project Glasswing identifies over 10,000 critical vulnerabilities in first month using AI
This Week In Security: AI Generated Reports, More AI Generated Reports, GitHub Chaos, And More Linux Vulnerabilities
Anthropic's Project Glasswing uncovers over 10,000 software vulnerabilities using AI
The AI that cracked Apple Silicon is only the beginning
Anthropic's Mythos AI model detects 23,000 vulnerabilities across 1,000 open source projects
Mythos and GPT-5.5 muscle out the competition
In recent weeks, we pointed Mythos and other security-focused LLMs at live code across critical parts of our infrastructure. We…
20 years' worth of screaming from security researchers, in graphs and numbers
GTIG says AI-powered hacking has moved well beyond phishing emails and chatbot tricks
Claude Mythos found thousands of vulnerabilities, exposing patching limits as AI-driven exploit discovery accelerates cyber risk.
Writing memory-safe code beats patching your way to safety
