I agree that prompting is a much shallower skill than engineering, and I really hate the term “prompt engineering” since I feel it puts something that (by design) is easy to learn on the same level as something relatively hard to learn.

There is admittedly a bit of skill to use these tools, but they’re really not hard to use. For the most part Claude can decipher my typo’d-to-hell prompt and figure out what I want, and even if it gets it wrong the first time I can usually correct it. The hardest part is determining some objective test for Claude Code to test against and “anchor” it, but I still think that’s easier than writing a bunch of unit and integration tests.

I like these tools; I think Claude Code is very useful and even if I didn’t like it I would still use it because it’s clear that’s where the world is headed and I want to stay competitive.

For personal projects I actually care about, I still write code by hand. I do think I write better code than Claude but I would still do it by hand even if I didn’t, just because I realized I was losing my intuition about software because I was outsourcing to Claude for everything.

There are plenty of things that I am honestly fine losing my intuition with. I don’t really derive much enjoyment from reading dmesg logs, and I am more than happy to let a robot have its fun with that, but it can take the mathey shit from my cold dead hands now.

▲

sanderjd 2 hours ago | parent [-]

The skill isn't "prompting", it is figuring out what to do, validating that it works the way you want, and thinking about how to best support future iterations of things you might want to do.

Which, not coincidentally, is pretty much the same description as what the job was already about.

▲

tombert 2 hours ago | parent [-]

I know, but even given that I really don’t think it’s that hard, and certainly not as hard as regular pre-AI software engineering.

We all like to act like “the hard part was figuring out what we want”, but I don’t think I really buy that anymore. Even when I really half-ass Claude prompts, it still usually figures out what I want well enough, and when it doesn’t it usually does once I give it correction.

▲

sanderjd 2 hours ago | parent [-]

I think this actually gets at a big part of what is causing this existential crisis. You're right, I don't think it was ever true that "the hard part was figuring out what we want". I think there have always been two hard parts: 1. Figuring out what is useful, and 2. Implementing a useful thing well. The second of these has gotten a lot easier, which means the first has become more important. But software engineers have long had a tendency to underrate that first part and consider it easy. I have long perceived a (to me) baffling arrogance that product management is an easier and less important job than software engineering. But that was never an accurate perspective, imo. And now that the "implementing things" job has gotten easier and the "figuring out what to implement" job has become more important, people with this perspective are really being thrown for a loop.

	▲	varjag an hour ago \| parent \| next [-]
		Product management is indeed an important but at the same time not very hard job.
	▲	pmg101 an hour ago \| parent \| prev [-]
		What even is product management? Just saying what you'd like? That's like equating the person ordering their meal with the person who will create it.