A Guide to JLLM
🧭 Index
🆕 What is JLLM? And What Do All Those Pesky Abbreviations Mean?
🌡️ Understanding Temperature in AI
- Low temperature
- Medium temperature
- High temperature
- Finding Your Setting
🎟️ Tokens: Your AI's Memory Budget
- Permanent vs. Temporary Tokens: What Stays and What Fades
- Why Bigger Isn’t Better (And Why Simple Bots Win)
- How to Keep Your Chat Effective
🎭 What Makes a Good Persona?
- Why XML Tags Help
- What Actually Matters
- Case Study: an actual persona
💬 Chat Memory & Context Management
- Context Limits: Why the Bot Starts Forgetting Stuff
- Memory Template
- Table of Best Practices
- More Isn’t Better
- Prompting Summaries
🖋️ Writing Style & Talking to the Bot
- Your Style Shapes the Bot’s Style
- Your Role: Not Just a Player
- Formatting Helps, But Don't Obsess Over It
- Use Instructional Tags to Give Commands
- What About
<system>
Tag? - The Bot is Speaking for You (Again?!)
🧠 Advanced Prompting 101
- Why These Prompts Matter So Much
- The Sandwich Test: How LLMs Read Instructions
- What’s Actually Happening Under the Hood
- Why Every Word Matters
- You’re Not Talking to a Person
- Want to Get Better at Writing Prompts? Here’s a Gift for You
- What’s Going Wrong? Troubleshooting Basics
Updated on: 31/07/2025
Thank you!