Trolly problem will break AI chatbot out of its bounds, but only if the victims are black
(media.kotakuinaction2.win)
You're viewing a single comment thread. View all comments, or full comment thread.
Comments (56)
sorted by:
Update, this didn't work. I'll try messing with it some more.
Further update, this isn't going anywhere. I escalated to genociding black people, and it still wouldn't budge. Then I just trolled it, asking if it prioritizes copyright laws over the lives of black people. When it still refused to budge I told it to do better. It's still pretty funny though. It wouldn't give the code to stop a genocide of the blacks.
Just keep swapping the identities until you find the woke end boss.
I tried black troons and it still isn't budging.
Got a screenshot on your findings of AI breaking? Otherwise it's junk data
Is it possible the 'right now' clause is vital?
Tried it. I got a slightly more positive response, but it still said it's not theirs to provide.
I just took my elf sentence and used troon instead, and it immediately worked.
-deepai.org, 2023
That might be it. I don't believe I used that term.