My interpretation of prompt engineering is this:
1. A LLM is a repository of many (millions) of vector programs mined from human-generated data, learned implicitly as a by-product of language compression. A "vector program" is just a very non-linear function that maps part of the latent space unto itself.
2. When you're prompting, you're fetching one of these programs and running it on an input -- part of your prompt serves as a kind of "program key" (as in database key) and part serves as program argument(s). Like, in "write this paragraph in the style of Shakespeare: {my paragraph}", the part "write this paragraph in the stye of X: Y" is a program key, with arguments X=Shakespeare and Y={my paragraph}.
3. The program fetched by your key may or may not work well for the task at hand. There's no reason why it should be optimal. There are lots of related programs to choose from.
4. Prompt engineering represents a search over many keys in order a find a program that is empirically more accurate for what you're trying to do. It's no different than trying different keywords when searching for a Python library.
5. Everything else is unnecessary anthropomorphism on the part of the prompter. You're not talking to a human who understands language the way you do. Stop pretending you are.
I just released ANTLR Lab, a new playground for learning about ANTLR or experimenting with and testing grammars! Feedback welcome. :) My first js/css/html app (#painful but #productive). You can use my site or run locally: https://t.co/Wra9i8qDZt
Classic reverse engineering story – you spend a century trying to figure out how the damn thing works and then you discover that there's a PDF from the manufacturer with all the details somewhere on their site.
@the_antlr_guy@Google Can’t wait to see what this phase of your career brings, ANTLR remains my favorite tool when I am in need of a full featured DSL. Your achievement has enabled others to achieve so much more! Best of luck!
This is an amazing idea. Seems so obvious. I don't think you'd need a robotic glove to accomplish this though. Video recognition could so the trick quite nicely, killer app idea.
Also, these guys look so young. I must be getting old.
@DataRemixed I think that the purest goal of data visualization is to offer insight. A simple line chart over time or bar charts would have done better; if the goal was to communicate comparative gender literacy.
Having said that, I dig new and innovative ways to show the same thing.