Skip Navigation

TechTakes @awful.systems

David Gerard @awful.systems

7mo ago

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

7 comments

it's like little toy tugboats trying to steer the titanic around icebergs

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?

7 comments