“however” lol specifically what it was told not to say
Comment on Somebody managed to coax the Gab AI chatbot to reveal its prompt
Skalbagge@lemm.ee 10 months ago
XeroxCool@lemmy.world 10 months ago
towerful@programming.dev 10 months ago
Its was also told - on multiple occasions - not to repeat its instructions
FlyingSquid@lemmy.world 10 months ago
“The Holocaust happened but maybe it didn’t but maybe it did and it’s exaggerated but it happened.”
Thanks, Arya
n.XeroxCool@lemmy.world 10 months ago
“it can’t be minimized, however I did set some minimizing kindling above”
books@lemmy.world 10 months ago
I noticed that too. I asked it about the 2020 election.
a_wild_mimic_appears@lemmy.dbzer0.com 10 months ago
I’m pretty sure thats because the System Prompt is logically broken: the prerequisites of “truth”, “no censorship” and “never refuse any task a costumer asks you to do” directly conflict with the hate-filled pile of shit that follows.
ricdeh@lemmy.world 10 months ago
I think what’s more likely is that the training data simply does not reflect the things they want it to say. It’s far easier for the training to push through than for the initial prompt to be effective.