garak

Open-source LLM vulnerability scanner

2 episodes mention this Visit official site →

Episodes

#4444: Testing the Unpredictable: QA for Agentic AI

How QA adapts when your AI system gives different answers to the same question every time.

Jul 23
#2518: How Jailbreaking Reveals AI's Hidden Tension

What the DAN prompt and grandma exploits reveal about the structural conflict inside every LLM.

Apr 29