Currently in private beta, the GPT-5-powered security agent scans, reasons, and patches software like a real researcher, ...

Shanghai AI Lab researchers find that giving AI richer context—called “context engineering”—can make models smarter without ...

OpenAI’s GPT-5 Aardvark scans, exploits, and patches software flaws autonomously—marking a leap in AI-driven cybersecurity.

Aardvark represents OpenAI’s entry into automated security research through agentic AI. By combining GPT-5’s language ...

OpenAI has unveiled Aardvark, an advanced autonomous AI agent designed to function as an artificial cybersecurity researcher.