The world of immediate engineering is fascinating on varied ranges and there’s no scarcity of intelligent methods to nudge brokers like ChatGPT into producing particular sorts of responses. Methods like Chain-of-Thought (CoT), Instruction-Based mostly, N-shot, Few-shot, and even methods like Flattery/Position Task are the inspiration behind libraries stuffed with prompts aiming to fulfill each want.
On this article, I’ll delve into a method that, so far as my analysis reveals, is probably much less explored. Whereas I’ll tentatively label it as “new,” I’ll chorus from calling it “novel.” Given the blistering fee of innovation in immediate engineering and the benefit with which new strategies may be developed, it’s totally attainable that this method would possibly exist already in some type.
The essence of the approach goals to make ChatGPT function in a approach that simulates a program. A program, as we all know, contains a sequence of directions sometimes bundled into capabilities to carry out particular duties. In some methods, this method is an amalgam of Instruction-Based mostly and Position-Based mostly prompting strategies. However not like these approaches, it seeks to make the most of a repeatable and static framework of directions, permitting the output from one operate to tell one other and everything of the interplay to remain throughout the boundaries of this system. This modality ought to align properly with the prompt-completion mechanics in brokers like ChatGPT.
For instance the approach, 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 capabilities and options:
Work on New IdeaExpand on IdeaSummarize IdeaRetrieve IdeasContinue Engaged on Earlier IdeaToken/”Reminiscence” Utilization Statistics
To be clear we is not going to be asking ChatGPT to code the mini-app in any particular programming language and we are going to mirror this in our program parameters.