The world of prompt engineering is fascinating on various levels and there’s no shortage of clever ways to nudge agents like ChatGPT into generating specific sorts of responses. Techniques like Chain-of-Thought (CoT), Instruction-Based, N-shot, Few-shot, and even tricks like Flattery/Role Project are the inspiration behind libraries filled with prompts aiming to satisfy every need.
In this text, I’ll delve into a method that, so far as my research shows, is potentially less explored. While I’ll tentatively label it as “latest,” I’ll refrain from calling it “novel.” Given the blistering rate of innovation in prompt engineering and the benefit with which latest methods could be developed, it’s entirely possible that this method might exist already in some form.
The essence of the technique goals to make ChatGPT operate in a way that simulates a program. A program, as we all know, comprises a sequence of instructions typically bundled into functions to perform specific tasks. In some ways, this method is an amalgam of Instruction-Based and Role-Based prompting techniques. But unlike those approaches, it seeks to utilize a repeatable and static framework of instructions, allowing the output from one function to tell one other and the whole lot of the interaction to remain throughout the boundaries of this system. This modality should align well with the prompt-completion mechanics in agents like ChatGPT.
For instance the technique, let’s specify the parameters for a mini-app inside ChatGPT4 designed to operate as an Interactive Innovator’s Workshop. Our mini-app will incorporate the next functions and features:
- Work on Latest Idea
- Expand on Idea
- Summarize Idea
- Retrieve Ideas
- Proceed Working on Previous Idea
- Token/”Memory” Usage Statistics
To be clear we won’t be asking ChatGPT to code the mini-app in any specific programming language and we’ll reflect this in our program parameters.