a collection of thousands of prompts attempting to control the idiot genie of ChatGPT
a collection of thousands of prompts attempting to control the idiot genie of ChatGPT
github.com chatgpt_system_prompt/prompts at main · LouisShark/chatgpt_system_prompt
A collection of GPT system prompts and various prompt injection/leaking knowledge. - LouisShark/chatgpt_system_prompt
![chatgpt_system_prompt/prompts at main · LouisShark/chatgpt_system_prompt](https://lemdro.id/pictrs/image/d543d261-1d3e-4643-b610-ff9aee3cf201.png?format=webp&thumbnail=256)
7
comments
it's like little toy tugboats trying to steer the titanic around icebergs
21 0 ReplySo, 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.
8 2 Replyand your point is?
7 0 ReplyNothing? I'm pointing out another way to "attack" some LLM?
6 0 Reply
Is this a leak or something?
1 0 Reply
You've viewed 7 comments.
Scroll to top