Blog | Promptfoo

Archive5

Running LLMs locally with Ollama? These models often bypass cloud safety filters.

Open source models on HuggingFace often lack safety training.

Meet GOAT: our advanced multi-turn jailbreaking strategy that uses AI attackers to break AI defenders.

Attackers can poison RAG knowledge bases to manipulate AI responses.

Traditional fuzzing fails against LLMs.

RAG applications face unique security challenges beyond foundation models.

Prompt injections are the most critical LLM vulnerability.

When LLMs have too much power, they become dangerous.

Biased AI outputs can destroy trust and violate regulations.

Not all foundation models are created equal when it comes to security.