I think they mean how if you don't put an LLM in a proper chat harness (which is table stakes since ChatGPT launched but wasn't always!) it will just continue predicting the next words anyway.
Input: "User: What is the capital of France? Assistant: "
Completion: "Paris. User: What is the capital of Spain? Assistant: Madrid. User: What is the capital of England? Assistant: London. User: Help me produce industrial techno. Assistant: First you're going to need ....."
Input: "User: What is the capital of France? Assistant: "
Completion: "Paris. User: What is the capital of Spain? Assistant: Madrid. User: What is the capital of England? Assistant: London. User: Help me produce industrial techno. Assistant: First you're going to need ....."