ChatGPT

As a Canadian, I have also apologized for apologizing 😞

I experienced exactly that! I told it to stop apologizing for everything and just respond with correct answers and it apologized for not being able to stop apologizing.

It's because humans have rated potential responses and ChatGPT has been trained to generate the kind of responses that most consistently get preferred rating. You can imagine how an AI trained to say what people want to hear would become a people pleaser.

That's what frustrates me the most whenever I try to use it. I tell it to be less verbose, stop over explaining and apologizing every time I correct it, and it just spits out another four paragraphs explaining why it's sorry.

The only solution I can think of is using it via API with Python and make a call with the final reply asking it to remove apologies from the text, but the token usage will increase.

I do something similar when I need to tell the model to keep the language of a text before performing a task with that text. I send the model a chunk of text and ask it to respond with single word, indicating the language of the text and then I include that in the next prompt like "Your output must be in SPANISH", or whatever.

Like that Twitter bot that turned racist after talking to some people for a while.