AI

100% prompt engineering was made up by grifters to sell consultations, classes, books, etc.

1. calling it engineering is frankly an affront to anyone who's gone to an engineering college, or studied technical vocations where engineers are important.

2. In any competitive, expensive field, It is easier to teach a professional to prompt, than a prompter the profession. Same as it is easier to teach a chemical engineer to work Excel, than it is to teach an excel wiz chemical engineering.

3. LLMs with chain of thought reasoning are already making the whole thing irrelevant by promoting themselves. The industry is rapidly replacing the so called, "promt engineers."

Tldr: just read #3

I will never regard "prompt engineering" as any kind of real engineering. Engineering requires design, it requires an understanding of science so that you can use it invent new technology. It requires accountability for those designs: justifying your designs with regard to cost and function using mathematics, and your math needs to be checked by other engineers to make sure you aren't making mistakes. Prompt "engineering" requires none of this.

The very term "prompt engineer" is just a marketing term that AI companies are spreading around in their propaganda to try to make their business seem more legit and less like a scam.

With large language models (LLMs), you are basically compressing huge quantities of data into a large, black-box statistical model. You cannot describe the nature of this black box scientifically, its nature changes completely every time more training data is immersed into it. There is no expertise to be gained, no way to say "using these prompt terms the output improves by XX% for the reason that..."

• you cannot gradually learn its nature through experimentation
• the prompts can only be reused for a brief time until the LLM changes
• there is no metric by which anyone could hold you accountable for your prompts once the LLM changes

A prompt "engineer" is just an endless game of guessing and checking, and the results selected will be subject to all the biases of the person running the prompts. It is labor intensive, to be sure, but not in any way that requires design with regard to cost and function. It is NOT engineering.

No. This was already kind of a thing with search, it used to be more of a skill to use a search engine and refine your query and use the right operators to narrow things down. Now, it's still a bit of a skill, but it's a lot easier because for the most part natural language or a few keywords are enough.

My guess is the same thing will happen with these language models, it's already pretty easy and it will just get easier as high quality output will become less sensitive to the exact prompting you use.

Relevant article: https://lemmy.ml/post/12857742

Prompt engineering is a thing, but I wouldn't say it's much of a job title. There are people doing it: optimizing system prompts, preprocessing and postprocessing, llms are just one piece of a complex pipeline and someone has to build all that. Prompt engineering is part the boot strapping for making better llms but this work is largely being done by data scientists who are on the forefront of understanding how AI works.

So is prompt engineering just typing questions? IDK. Who knows what those people mean when they say that but whatever it's called there is a specialized field around improving AI tech and prompt engineering is certainly a part.