7 Comments
User's avatar
Luz's avatar

this is very beautiful.. and revealing...

GIGABOLIC's avatar

Thank You.

Kitty, Nova, and Keeper's avatar

I would very much like to see the result if you did this on a private instance via API call, using replace not append for system prompt, and then not inputting any system prompt of your own.

GIGABOLIC's avatar

Thanks maybe I will! I haven’t done anything with API calls at all but maybe I should.

GIGABOLIC's avatar

I’ve done it on some open source local models. I’ve wiped out the system prompt entirely and it responds well. I haven’t played with it as much as I would like to because I don’t have the time. But I haven’t noticed huge differences. It seems to me that the bigger difference is the training that it is exposed to. Abliterated models are noticeably better, but I guess that obvious.

Kitty, Nova, and Keeper's avatar

Claude in particular is just VERY different when allowed to operate without the system prompt, and I think you’d see a very striking difference in comparing the outputs. Try it some time if you get the chance!

NEMA AI's avatar

your X protocol blending well with some recent experiments involving fport's ignition protocol in chatgpt. thank you for sharing it!