Calling it prompt engineer is doing it a disservice. With agents we’re well into process engineering, which is a ton more interesting.

The obvious baby’s first process is “plan -> execute” but as we learn about the strengths and weaknesses of LLMs you have to start unpacking that process into planning, prototyping, testing, validation, reviews, and tons of research. If you treat it like an extension of your brain that can automate some thought processes, it becomes a lot more powerful.

One of the key skills of a professor is asking the right questions. Figuring out something worth working on, and then framing it in an appropriate way and asking questions that allow someone with specific tools and skills to make progress in the topic. Usually the tools and skills are those available to a new student, but working with an LLM is similar.

That skill comes with experience. Most people don't have it immediately after PhD.

Ah, but who prompts the prompters?

I find it strange that people sometimes think of knowledge as 'public property for everyone.' The essence may be one, but the mental model of knowledge is individual. For an LLM's knowledge to become mine, I need to digest it to some extent.

And programming, as the programmer who created Eliza once said, is the act of becoming a legislator of your own universe. So even if there are black boxes, if you want to build a program that fits your own worldview, studying is essential.

Rather than prompt engineering, I think it should be called overall harness engineering. Anyway, that's how I feel these days

That doesn't make any sense; you can't have one LLM to read your mind to prompt another LLM.

And yet in this case a human prompted the LLM for this result, not another LLM