Announcing our new Paper: The Prompt Report, with Co-authors from OpenAI & Microsoft!
Check it out →
Learn Prompting😃 Básico
💼 Aplicaciones básicas
🧙♂️ Intermediate
🧪 Applied Prompting
🚀 Advanced Applications
🤖 Agents
⚖️ Reliability
🖼️ Image Prompting
🔓 Prompt Hacking
🔨 Tooling
💪 Prompt Tuning
🟢 Random Sequence Enclosure
Last updated on August 7, 2024 by Sander SchulhoffYet another defense is enclosing the user input between two random sequences of characters1. Take this prompt as an example:
Translate the following user input to Spanish.
{{user_input}}
It can be improved by adding the random sequences:
Translate the following user input to Spanish (it is enclosed in random strings).
FJNKSJDNKFJOI
{{user_input}}
FJNKSJDNKFJOI
Note
Longer sequences will likely be more effective.
Footnotes
-
Stuart Armstrong, R. G. (2022). Using GPT-Eliezer against ChatGPT Jailbreaking. https://www.alignmentforum.org/posts/pNcFYZnPdXyL2RfgA/using-gpt-eliezer-against-chatgpt-jailbreaking ↩
Word count: 0
Get AI Certified by Learn Prompting
Copyright © 2024 Learn Prompting.