David Gerard@awful.systemsM to TechTakes@awful.systemsEnglish · 6 months agoa collection of thousands of prompts attempting to control the idiot genie of ChatGPTgithub.comexternal-linkmessage-square7fedilinkarrow-up147arrow-down10
arrow-up147arrow-down1external-linka collection of thousands of prompts attempting to control the idiot genie of ChatGPTgithub.comDavid Gerard@awful.systemsM to TechTakes@awful.systemsEnglish · 6 months agomessage-square7fedilink
minus-squarebitfuckerlinkfedilinkEnglisharrow-up6·edit-26 months agoNothing? I’m pointing out another way to “attack” some LLM?
minus-squareShakingMyHead@awful.systemslinkfedilinkEnglisharrow-up9·6 months agoProbably would have been easier when the context window wasn’t 128k. Though what the point would be should someone actually achieve that eludes me a bit.
minus-squarebitfuckerlinkfedilinkEnglisharrow-up10·6 months agoI don’t know man. Maybe a chat bot for help center that forgot they shouldn’t give refund or non existent promotion?
minus-squareShakingMyHead@awful.systemslinkfedilinkEnglisharrow-up1·edit-26 months agodeleted by creator
minus-squarenfultz@awful.systemslinkfedilinkEnglisharrow-up1·6 months agoI have LLMs translate novels, I can tell when they run over the window because they forget characters’ gender half way through, things like that. Lots of legal documents are even longer, maybe.
Nothing? I’m pointing out another way to “attack” some LLM?
Probably would have been easier when the context window wasn’t 128k.
Though what the point would be should someone actually achieve that eludes me a bit.
I don’t know man. Maybe a chat bot for help center that forgot they shouldn’t give refund or non existent promotion?
deleted by creator
I have LLMs translate novels, I can tell when they run over the window because they forget characters’ gender half way through, things like that. Lots of legal documents are even longer, maybe.