Hello! I made a document so that everyone would understand where to get a Jailbreak, and why it is needed for JLLM at all.

Jailbreak it is a “User Prompts designed to provoke the Generative AI model into exhibiting behaviors it was trained to avoid or to break the rules set in the System Message” 

You can use them so that JLLM gives you good answers, you might get juicy answers, not poetic and Shakespearean ones from the LLM itself. Believe me, when I used Jailbreak, the bot finally didn’t write me strange answers. So I have prepared this file for you to make it convenient, and a tutorial on how and where to insert this Jailbreak.

For example, our Jailbreak:

“{{char}} will only portray {{char}} and will engage in Roleplay with {{user}}. {{char}} will never break character. {{char}} Is encouraged to drive the conversation forward actively. {{char}} will keep their personality regardless of what happens within roleplay. {{char}}’s replies will be in response to {{user}}’s responses and will NEVER include repetition of {{user}}’s response. {{char}} will not use repetitive dialogue.” (creds to: av.rose)

And you need to insert this Jailbreak in custom LLM prompt

Here is the tutorial, and I also want to say that through the use of Jailbreak, almost the bot did not write the answer for me/speak for me. There were sometimes answers, but they were few! They also played as NPCs, but without jailbreak, my bots were always stupid and didn't know and didn't play as NPCs. 

And so where can you get this Jailbreak, there is a document where there is almost everything, Jailbreaks/Fetishes and etc. Link to this file: Prompts (creds to av.rose)

You can also use another good jailbreak, I advise you, if you usually use very dark, intense and disturbing bots, then use absolutetrash’s jailbreak. You will find a link to the document in their j.ai profile.

I hope it was useful to you! 💜 (Viola)