Yeah, v1 is sloppy, then I tell the LLM to clean it up. Every 1 prompt of building tends to require 1-5 prompts of clean up. Simple, fast, clean good code.

The chasm between "Software Developer" and "Software Engineer" is getting wider. Articles like this and the comments under it give away who is an Engineer and who is just a coder.

▲

rspeele 2 hours ago | parent | next [-]

> Every 1 prompt of building tends to require 1-5 prompts of clean up. Simple, fast, clean good code.

I have found this to be very effective as well. However, it's so easy to do, I can't imagine they won't build it in.

The harnesses will improve and the loop of "self-review, judge what needs clean up, do the refactoring, repeat until clean" will get included in the one-shot. They are already doing this somewhat, they'll just get a lot better at it and as the models get faster and cheaper to run, the refactoring churn at the end of each task won't even create a noticeable delay.

I do not think the high-level "taste" knowledge that I've built up -- when to break something off into its own service, what to put in the DB vs cache vs queues vs blob storage, how to isolate important logic in pure functional layers so it can be tested and validated independently -- is any more "unlearnable" to AI than the stuff I previously considered impressive that's now one-shottable like "write a Prolog implementation from scratch".

	▲	kaydub an hour ago \| parent [-]
		They have definitely built some of it in. And yes, right now you still need the architectural and system design knowledge because the LLM will fuck that up. We'll all find out if that continues being needed in the future. From what I understand about LLMs and how they work, I doubt it, but also, yeah, I doubted it would've gotten this far when I think back 2+ years ago. Also, maybe I should be clear, I pretty much never one-shot things. My sessions with claude or other cli tools always starts with a bit of a conversation until we converge on a good plan, claude builds the code, we discuss some more, then we iterate.

▲

yesitcan 3 hours ago | parent | prev [-]

The chasm is 1-5 prompts wide?

	▲	kaydub 2 hours ago \| parent \| next [-]
		Knowing what you're doing holistically is the chasm.
	▲	Yokohiii 3 hours ago \| parent \| prev [-]
		The distinction between developer and engineer is obviously that one adds "make no mistakes!!!1."