Comment by WorldMaker
1 day ago
It's partly a "Don't think of a Pink Elephant" problem. I've worked on several projects where I had to keep telling prompt writers to stop writing negative examples because the more you include the more its "attention" to them is all it has. Like telling a toddler not to do something and being surprised that is now all they can think about and they want to keep doing it. These prompt writers kept getting surprised that I'd delete all their negative examples and harshly worded "Don't do X" and "Never Y" and "NO: Z" sections they spend so much time on and got better results with smaller more focused positive example only prompts.
Hah! I also thought about it this way and ended up added a "purple elephant rule" to my pi prompt to discourage the behaviour, since I figured LLMs lean on metaphors so much.
Of course, I quickly reverted this change as purple elephants started cropping up in comments and other prose :)
You tried to discourage it from fixating on negatives by telling it not to fixate on negatives? And it didn't work?
Yes shocking.
Early versions of stable diffusion supported negative prompts and they never leaked because it would just down weight that stuff.
I don't understand why negative prompts never made it into the LLM world. If "no foo" and "dont do bat" don't work then just give me a separate textbox where i can put all my negatives!
The funny thing is, models are pretty good at following negative instructions now.
They just also really love to tell you about it.