a collection of thousands of prompts attempting to control the idiot genie of ChatGPT
A collection of GPT system prompts and various prompt injection/leaking knowledge. - LouisShark/chatgpt_system_prompt
You're viewing a single thread.
So, you know LLM has a context window right? That means context overflow is a valid LLM attack strategy if you are somehow able to send more stuff than what is allowed.
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.
