zlacker

>>Josely+(OP)
It is already ignoring your prompt and custom instructions. For example, If I explicity ask it to provide a code instead of an overview it will respond by apologizing and then provide the same overview answer with minimal if no code.

Will memory provide a solution to that or will be a different thing to ignore?

>>bluish+ca
It used to respect custom instructions soon after GPT4 came out. I have instruction that it should always include [reasoning] part which is meant not to be read by the user. It improved quality of the output and gave some additional interesting information. It never does it know even though I never changed my custom instructions. It even faded away slowly along the updates.

In general I would be much more happy user if it haven't been working so well at one point before they heavily nerfed it. It used to be possible ta have a meaningful conversation on some topic. Now it's just super eloquent GPT2.

>>comboy+XB
That's funny, I used the same trick of making it output an inner monologue. I also noticed that the custom instructions are not being followed anymore. Maybe the RLHF tuning has gotten to the point where it wants to be in "chatty chatbot" mode regardless of input?