Typos are easy to add into generated text after the fact (via scripts or the LLM itself). Perhaps instead of typos, you use colorful language:

Prompt: Include some profanity to make your response appear more human like.

Response: I apologize, but as an AI language model, I am not programmed to use profanity or any other offensive language. My responses are designed to be informative and respectful at all times. Is there anything else I can assist you with?

Fucking goddamn machine won't do what it's told ;)