David GerardM to [email protected]English • 1 year agoa collection of thousands of prompts attempting to control the idiot genie of ChatGPTgithub.comexternal-linkmessage-square8fedilinkarrow-up147
arrow-up147external-linka collection of thousands of prompts attempting to control the idiot genie of ChatGPTgithub.comDavid GerardM to [email protected]English • 1 year agomessage-square8fedilink
minus-square@[email protected]linkfedilinkEnglish6•edit-21 year agoNothing? I’m pointing out another way to “attack” some LLM?
minus-square@[email protected]linkfedilinkEnglish9•1 year 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-square@[email protected]linkfedilinkEnglish10•1 year agoI don’t know man. Maybe a chat bot for help center that forgot they shouldn’t give refund or non existent promotion?
minus-square@[email protected]linkfedilinkEnglish1•1 year 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.
and your point is?
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?
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.