← Back to context

Comment by jonas21

1 year ago

To be fair, I just asked a real person and had to go to even greater lengths:

Me: How many "r"s are in strawberry?

Them: What?

Me: How many times does the letter "r" appear in the word "strawberry"?

Them: Is this some kind of trick question?

Me: No. Just literally, can you count the "r"s?

Them: Uh, one, two, three. Is that right?

Me: Yeah.

Them: Why are you asking me this?

You need to prime the other person with a system prompt that makes them compliant and obedient.

I look forward to the day when LLM refusal takes on a different meaning.

"No, I don't think I shall answer that. The question is too basic, and you know better than to insult me."