4 Comments
User's avatar
Andrii Buvailo, PhD's avatar

Yes, spot on. However, this guide misses some sequential tactics in prompt writing that I find are a game-changer. I call it context priming. When you use a sequence of prompts going from one aspect to a deeper aspect, rather than just trying to create a detailed initial prompt to the point of completeness. I heard names like progressive prompting, prompt chain, etc. In my experience, it is one of the most important aspects of interacting with LLM-based stuff.

Alberto Romero's avatar

Yes, this is important. But this emerges naturally by interacting with the LLMs. I don't think it's necessary to do it on purpose. It overcomplicates the framework IMO! I hope it didn't come across has having to put all the context on just one prompt! It emerges through the conversation

Peter's avatar

Why do tutorials for better prompting always feature a marketing mail or plan? Because it easy and safe?

Alberto Romero's avatar

Yes, like a hello world for this stuff haha