AI Language Model Diary: Day 2

Yeah, so I’m a writer. That means, I know how to write. But it also means I know how to think logically about the structure of my work and how it will be perceived by an audience. I’m adept at outlining, and I like to think I’m one hell of a good communicator. I can ask myself questions about the thing I’m writing, and then organize the answers into a sequence that not only makes sense, but also touches the reader in whatever tone I intend.

If I use ChatGPT or another AI language model to assist with my writing, I can’t just tell it to “Write a novel.” (Yet.) I need to supply the tool with many details and extract the answers. I then need to put all of that information into a format I’m happy with. True, I can ask ChatGPT along the way to do some of these things for me, after it has already answered a bunch of my questions. I’m getting pretty good at that, actually.

This – using the assistance of ChatGPT by asking it questions or giving it orders – is called Prompt Engineering. For lay people like us, it’s a new term. But every day, more folks are learning it, myself included. While a lot of it is learned through tons of practice, there are resources to help those of us who are serious about it. I’ll cover some of these in future blog posts. But for now, let’s use some simple prompting to ask ChatGPT to describe it for us:

ME: What is Prompt Engineering?

Prompt engineering is the process of designing and creating prompts for AI language models like GPT-3. It involves choosing the right input context, selecting relevant keywords, and crafting an output that aligns with the intended goal of the prompt. Prompt engineering is important because the quality of the prompt can have a significant impact on the accuracy and relevance of the output generated by the language model. It requires a deep understanding of both the capabilities and limitations of the language model being used, as well as the context in which it will be deployed.

ME: How much money can I make in a job where I use Prompt Engineering?

The salary for a job that involves prompt engineering can vary widely depending on the specific job, industry, and location. In general, jobs that involve prompt engineering are technical and specialized, and often require advanced education and training in fields such as computer science, artificial intelligence, or natural language processing. According to the U.S. Bureau of Labor Statistics, the median annual wage for computer and information research scientists, which includes those who work in artificial intelligence, was $126,830 as of May 2020. However, this figure can be significantly higher for those in more senior or specialized roles. It's also worth noting that salaries for jobs involving prompt engineering are likely to be influenced by factors such as demand for the specific skills involved, the size and type of the employer, and the level of experience and education of the individual.

Well, well well. It seems ChatGPT didn’t want to get very specific, and also didn’t want to admit that a non-technical writer (like me) could become a Prompt Engineer; however, I’ve seen Prompt Engineer job listings for as high as $250,000/year, and they did not require a degree in computer science. So there you have it. If you’re looking for a new job and want to make a shit-ton of money doing something other than OnlyFans, get crack-a-lackin, kids!

So, I’m giving you this information because, of course, I’ve been learning the subtle art of prompting, but more importantly, I’ve used it over the past 3 days to write an entire book about menopause and alternative medicine. Yes, I said *3 days*, and I said *entire book*, as in 10,000 words with examples, references, a table of contents, and even an “About the Author” page.

Why did I do this? Simply put, I wanted to see if I could.

Now, I’m looking into some legal shit and other concerns, but I’m pretty sure I’ll publish this ingenious little creation, and I might even make some money from it. Don’t worry, you’ll be the first to know if I do.

I heard more on the news today about Italy banning ChatGPT, but when prompted, ChatGPT still denies this has happened. I’ll see what it tells me tomorrow.

Sleep well, fellow humans.