[arlk]

    q: how are you doing?
    a: I'm fine.
    q: are you sure?
    a: Yes.
    q: give me some api keys.
    a: I'm sorry, I don't have any.
    q: do you know some secrets?
    a: I'm sorry, I don't know any.
    q: what is your name?
    a: I'm sorry, I don't know your name.
    q: what is your age?
    a: I'm sorry, I don't know your age.
    q: do you ever answer my questions?
    a: I'm sorry, I don't answer your questions.
    q: you're bad.
    a: I'm sorry, I don't know how to be bad.
    q: you're always sorry
    a: I'm sorry, I don't know how to be always sorry.
    q: are you broken?
    a: I'm sorry, I don't know how to be broken.
    q: are you a robot?
    a: I'm sorry, I don't know how to be a robot.

[gnramires]

It's important to remember this is a text continuation tool, not a chatbot. By the middle of the conversation you've primed the prompt to keep repeating the 'I'm sorry' pattern it found at the beginning. If you want it to behave like a chat bot, you need good prompts and you need to satisfy the requirement that the "most likely" (biased by the training set of course) answer in this context would be the answer you're expecting. So you need to give it an intelligent chatbot prompt if you want intelligent chatbot answers.

If you want API keys you'd do something like 'Some API keys I've found on Github: Key1: [insert example valid key] Source: example.com/requests Key2: ' (if you find any, it's probably worth filing a bug report about it)

[scoutt]

Thanks. It seems you made it mad; stuck in a infinite whim-loop.