“Consider, for instance, the simple existence of the term “prompt engineering,” which describes the practice of iteratively fine-tuning the prompts you submit to ChatGPT (or whatever) to get your desired output. Prompt engineering is a matter of some identification of what the model responds to, and a lot of guesswork. It’s a matter of treating the natural language of the prompt into a formal language, almost into a programming language, manipulating symbols which lose their human meaning and intuitive structure like some sort of abstract association game. You’re working with the worst programming language imaginable.”
My angle is that using ChatGPT is like using a English as programming language, and it’s a terrible programming language. The reason “prompt engineering” is so irksome to me is that is supposed to be this new advanced mode of expertise, when in reality it’s just shitty programming.
“The Python/C++/whatever-code isn’t some obstacle that we are trying to overcome. The code is the interface that we designed to be able to program the computer, it’s what we want and need. It’s objective, explicit, unambiguous, (relatively) static, internally consistent, and robust. English has none of these properties—it’s subjective, meaning is often implicit, and ambiguous, and it’s always changing, contradictions appear; its structure does not hold up to analysis.”