←back to thread

Nobody knows how to build with AI yet

(worksonmymachine.substack.com)
526 points Stwerner | 10 comments | 19 Jul 25 15:45 UTC | HN request time: 0.001s | source | bottom
Show context
nirvanatikku ◴[19 Jul 25 16:16 UTC] No.44616774[source]▶
This article is spot on.

I had stumbled upon Kidlin’s Law—“If you can write down the problem clearly, you’re halfway to solving it”.

This is a powerful guiding principle in today’s AI-driven world. As natural language becomes our primary interface with technology, clearly articulating challenges not only enhances our communication but also maximizes the potential of AI.

The async approach to coding has been most fascinating, too.

I will add, I've been using Repl.it *a lot*, and it takes everything to another level. Getting to focus on problem solving, and less futzing with hosting (granted it is easy in the early journey of a product) - is an absolute game changer. Sparking joy.

I personally use the analogy of mario kart mushroom or star; that's how I feel using these tools. It's funny though, because when it goes off the rails, it really goes off the rails lol. It's also sometimes necessary to intercept decisions it will take.. babysitting can take a toll (because of the speed of execution). Having to deal with 1 stack was something.. now we're dealing with potential infinite stacks.

replies(6): >>44616827 #>>44618813 #>>44620946 #>>44621802 #>>44623469 #>>44627469 #
1. roxolotl ◴[20 Jul 25 00:57 UTC] No.44620946[source]▶
The challenge is that clearly stating things is and always has been the hard part. It’s awesome that we have tools which can translate clear natural language instructions into code but even if we get AGI you’ll still have to do that. Maybe you can save some time in the process by not having to fight with code as much but you’re still going to have to create really clear specs which, again, is the hard part.
replies(4): >>44621521 #>>44622346 #>>44623260 #>>44625920 #
2. Mtinie ◴[20 Jul 25 02:43 UTC] No.44621521[source]▶
Excellent. That’s what we should be doing, with or without AI. It’s hard, but it’s critical.
3. bryanrasmussen ◴[20 Jul 25 05:55 UTC] No.44622346[source]▶
in my experience only a limited part of software can be done with just really clear specs, also at times in my career I have worked on things that became more "clear" what was really needed as time went on the more we worked on it, and in those cases really clear specs would have produced worse outcomes.
replies(1): >>44622687 #
4. hgomersall ◴[20 Jul 25 07:13 UTC] No.44622687[source]▶
Which is the real reason agile is so much more effective than waterfall. The beginning of the project is when you know least about your project, so naturally you should be able to evolve the specification.
replies(2): >>44622709 #>>44636373 #
5. bryanrasmussen ◴[20 Jul 25 07:18 UTC] No.44622709{3}[source]▶
hmm right, in some ways could argue that AI based development is going against Agile development practices.
replies(2): >>44624459 #>>44625207 #
6. nosianu ◴[20 Jul 25 09:09 UTC] No.44623260[source]▶
Anecdote

Many years ago, in another millennium, before I even went to university but still was an apprentice (the German system, in a large factory), I wrote my first professional software, in assembler. I got stuck on a hard part. Fortunately there was another quite intelligent apprentice colleague with me (now a hard-science Ph.D.), and I delegated that task to him.

He still needed an explanation since he didn't have any of my context, so I bit the bullet and explained the task to him as well as I could. When I was done I noticed that I had just created exactly the algorithm that I needed. I just wrote it down easily myself in less than half an hour after that.

7. datameta ◴[20 Jul 25 12:15 UTC] No.44624459{4}[source]▶
Maybe it is that LLM coding makes it easier to loop back with little regard for development cost. When you can spend an hour to fix what would have been hampered severely by technical debt late in the process - are we starting to omit optimizing for proper SDLC?
8. roxolotl ◴[20 Jul 25 13:52 UTC] No.44625207{4}[source]▶
Generally I find that agile works because getting a really clear spec is so hard. You’re slowly iterating towards a clear spec. What is a finished piece of software if not a completed spec?

100% agree AI based dev is at odds with agile. You’re basically going to use the AI to fully rewrite the software over and over until the spec becomes clear which just isn’t very efficient. Plus it doesn’t help that natural language cannot be as clear a spec as code.

9. amy214 ◴[20 Jul 25 15:11 UTC] No.44625920[source]▶
>The challenge is that clearly stating things is and always has been the hard part.

I state things crystal clear in real life on the internets. Seems like most of the time, nobody has any idea what I'm saying. My direct reports too.

Anyway, my point is, if human confusion and lack of clarity is the training set for these things, what do you expect

10. 95014_refugee ◴[21 Jul 25 15:31 UTC] No.44636373{3}[source]▶
You are confusing waterfall with BDUF.