If you are thinking about using an LLM to communicate with me, you will be glad to hear I’ve just developed an exciting new technique which will save us both time. Rarely are such wins possible, so this is surely cause for a celebration.
The technique goes as follows:
- Type up your LLM prompt,
- (Here’s where it gets really exciting), instead of sending your prompt to an LLM, just send the prompt directly to me!
“What?” I hear you crying, “My prompt doesn’t contain all the information you need!”
But it does. You can’t create information from thin air and I too have access to LLMs. If I want to bloat your information a hundred fold by incorporating generic drivel I can do it myself. I could even do it using the LLM of my choice and tweak the prompt to make it more or less verbose.
However, we are barely scratching the surface of what’s possible here. Because, you see, I won’t even feed your prompt to an LLM at all!
OK, I know this sounds insane but hear me out: I have the very same language processing capabilities built into my brain. An organic language model, you might say. It’s even quite large, if I may be forgiven for boasting. I can understand a fair bit but, admittedly, I can’t understand everything. Luckily I also have circuits I’ve developed that tell me whether I really understand something or not.
So what if I don’t understand? What if your prompt is too terse? Too devoid of context? I could always fall back to feeding it to the LLM after all, but ultimately the LLM won’t have any more information than what’s the in prompt, it will just be guessing the details. So what then?
This all depends on the medium of communication.
If it’s an email you’ve sent me, I will simply reply to you (sending you my prompt directly, of course) asking for clarification or more details. You can then amend your prompt as you would normally and send it back.
If it’s a published work such as a book or marketing literature then I’m more limited in my recourse and I will likely just leave a bad review or not buy your product etc.
Either way, together we will learn to communicate clearly and effectively together. We’ll learn to be clear and concise in our prompts and be fully aware of implicit context at all times. I believe it’s called prompt engineering, but I prefer the older terminology: writing.