Live data from Hacker News

Nobody knows how to build with AI yet

worksonmymachine.substack.com

361–370 of 432 posts

Re: Nobody knows how to build with AI yet

#361
post #311

To me it feels like I’m in the camp of people who has already figured it out. And I have now learned the hard way that it’s almost impossible to teach others (I organized several meetups on the topic). The ability seems like pure magic. I know that there are others who have it very easy now building even complex software with AI and delivering project after project to clients at record speed at no less of quality as…

I've noticed a great deal programmers, very good programmers at that, that completely underestimate how fast things are moving. They're natural skeptics, and checked out ChatGPT when it was released. Then they maybe checked out some other models a year after. But eventually wrote it off as hype, and continue to do things their way. You know, artisanal code and all that.

I think that if you willfully ignore the development, you might be left in the dust. As you say, it is a force multiplier. Even average programmers can become extremely productive, if they know how to use the AI.

Re: Nobody knows how to build with AI yet

#362
post #116

Earlier quoted context omitted.

I'm using AI assistants as an interactive search and coding assistant. I'm still driving the development and implementing the code. Where I use it for is: 1. Remembering what something is called -- in my case the bootstrap pills class -- so I could locate it in the bootstrap docs. Google search didn't help as I couldn't recall the right name to enter into it. For the AI I described what I wanted to do and it gave the…

Why I don't bother with LLMs for the above is: 1. I usually just pull up the docs for the CSS framework, give it a quick look over to know what it offers and the nomenclature and then keep it open for all the code examples. 2. I've serialized json in enough languages to know the pain points, so what I usually do is locate the module/library responsible for that in that language. And then give the docs/code sample a q…

For 1 I tried looking through the bootstrap documentation but couldn't find it because they called it "Pills" and not what I was thinking. So I then tried google to search for it but that didn't work.

For 3 -- Sure, that can help. But sometimes it is difficult to follow what is going on. Especially if that comes from a library/framework you are unfamiliar with such as AWS.

I've also used it to help with build errors such as "Bar.csproj: Error NU1604 : Warning As Error: Project dependency Foo does not contain an inclusive lower bound. Include a lower bound in the dependency version to ensure consistent restore results." -- That was because it was using a fixed version of the module via the "[1.0]" syntax, but my version of NuGet and/or Rider didn't like that so once I new that and the range syntax specifying "[1.0, 1.0]" worked. I was able to understand that from the LLM response to the error message and telling it the specific ``.

Re: Nobody knows how to build with AI yet

#363
post #311

To me it feels like I’m in the camp of people who has already figured it out. And I have now learned the hard way that it’s almost impossible to teach others (I organized several meetups on the topic). The ability seems like pure magic. I know that there are others who have it very easy now building even complex software with AI and delivering project after project to clients at record speed at no less of quality as…

What sort of code are you writing? I find a lot of my stuff requires careful design, refactoring an existing system to work in a new way.

If the code I was writing was, say, small websites all the time for different clients, I can see it being a big improvement. But iterating on a complex existing platform, I’m not so sure that AI will keep the system designed in a maintainable and good way.

But if your experience is with the same sort of code as me, then I may have to re evaluate my judgments.

Re: Nobody knows how to build with AI yet

#364
post #279

Earlier quoted context omitted.

It doesn’t make everyone a lead architect, it just makes everyone think they’re a lead architect. What makes people a lead architect is a decade or two of experience in designing software and learning what works and doesn’t.

What makes people a lead architect in my experience is an abnormal amount of arrogance and no capability to admit mistakes.

That just gives the title. To be really successful, they need to let someone else, knowledgeable, actually make the architecture decisions.

Re: Nobody knows how to build with AI yet

#366
post #311

To me it feels like I’m in the camp of people who has already figured it out. And I have now learned the hard way that it’s almost impossible to teach others (I organized several meetups on the topic). The ability seems like pure magic. I know that there are others who have it very easy now building even complex software with AI and delivering project after project to clients at record speed at no less of quality as…

> For me it’s just a huge force multiplier, maybe 10-20x of my ability to deliver with my own knowledge and skills on a web dev basis. I can tell you that this claim is where a lot of engineers are getting hung up. People keep saying that they are 10, 20 and sometimes even 100x more productive but it's this hyperbole that is harming that building style more than anything. If you anyone could get 10 to 20 years worth…

yep plus all these companies going all in on AI would have already laid off 95% of their software engineers.

Re: Nobody knows how to build with AI yet

#367

There's a weird insecurity I've noticed cropping up. I want to design the codebase 'my way'. I want to decide on the fundamental data structures. But there's this worry that my preferred architecture is not massively better than whatever the machine comes up with. So by insisting on 'my way' I'm robbing everyone productivity. I know most true programmers will vouch for me and my need to understand. But clients and pr…

Not sure if a developer would ever say that to their manager. Agreed on the need to 100% fully understand what's going on. Otherwise the "AI can get it done in a day" is extremely high risk to the business. Junior may not be able to recognize a half-baked solution that doesn't follow existing patterns, poor security, poor performance, etc.

Re: Nobody knows how to build with AI yet

#368

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 fasc…

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.

>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

Re: Nobody knows how to build with AI yet

#369
post #4

That time dilation feels a bit like what METR reported: https://metr.org/blog/2025-07-10-early-2025-ai-experienced-o... Developers believe they complete tasks 25% faster with AI but when measured they are 19% slower when using AI.

This was the study with a population size of 16?

This was the only study that's been done so far?

Re: Nobody knows how to build with AI yet

#370
post #258

Earlier quoted context omitted.

I am hopeful that AI leads to a future with mandatory 10 hour work weeks.

Why would that happen when they can have mandatory 50 hour work weeks?

Mass unemployment with some people working 50+ hours a week will have to lead to something changing. Capped work hours? UBI?
Post reply on HN