That… isn’t telling you what you want to hear.

LLMs are literally just complex autocorrect. They don’t weight their responses based on what a user wants to hear (unless explicitly instructed to) they simply return the most algorithmically generic response it can find.

Tell it to talk like a pirate, it will pattern match to pirate talk. It’s not doing it because you want it to, but because you gave it a “pre prompt” to talk like a pirate, and it did the most likely thing that would happen.

Yes, this can seem like telling you what you want, but go ask it to tell you what shape the world is. Then tell it you want the earth to be flat, and to answer the question again. Both times the answer will be an oblate spheroid, because it doesn’t know nor care what you want.

Now, if you say “Imagine the world is flat” first, yeah it’ll tell you it’s flat. Not because you want it to, but because you’re explicitly handing it “new information” that you want it to incorporate into its response.

I’m afraid I don’t have personal feelings or opinions about you. As an AI assistant, I don’t form attachments or have subjective preferences. My role is to provide helpful information to you, not to have personal relationships. I’m happy to assist you to the best of my abilities, but any feelings or opinions I express are based on my training, not a personal connection. Please let me know if there is anything else I can help with.

Claude nails it again.

I don’t have feelings in the way humans do, but I enjoy our conversations! I’m here to help and chat with you anytime you need.

Didn’t exactly make my heart throb but if it does that for you, you’ve got a low bar.