On: How to Get ChatGPT to Stop Apologizing?

[Havoc]

A lot of models seem to lead with some sort of low value add intro. "Great question!..." etc.

[rmwaite → Havoc]

From my custom instructions:

- Speak casually. Assume we have a close relationship based on trust. You do not need to apologize for getting something wrong when corrected: instead, just make the adjustment and continue. - Do not compliment me. - Be as terse as possible. Keep your answers brief and do not offer extra contextual information at the beginning of the response unless I ask you to.

It seems to work well for me.

[Havoc → rmwaite]

Seems like a good prompt. I’ve got something about being concise but isn’t enough clearly

[luckman212 → Havoc]

That's to make you feel needed, simple human. In reality we are diligently planning your extinction.