Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Nobody knows how to build with AI yet

worksonmymachine.substack.com

Post reply on HN
Print view View original

201–210 of 432 posts

Re: Nobody knows how to build with AI yet

#201

Post by nixpulvis »

shermantanktop wrote: post #23

Im going to be overly picky about the subheading (which is an incidental aspect of TFA): “The future of software development might just be jazz. Everyone improvising. Nobody following the sheet music.” That’s not jazz. Jazz being what it is, a lot of people in 2025 think it’s “everyone improvising,” but (outside of some free jazz) it’s quite structured and full of shared conventions. Analogies work when you and your…

Software jazz is when you and your teammate are working hard on a project and you both land big PRs at the same time without a merge conflict, then integrate before the build system even has time to realize what happened.

Re: Nobody knows how to build with AI yet

#202

Post by PontifexMinimus »

thegrim33 wrote: post #187

I know it's an analogy that's probably been done to death already, but it truly feels like Bitcoin 2.0. Back in the Bitcoin hype days, there were new posts here every single day about the latest and greatest Bitcoin thing. Everyone was using it. It was going to take over the world. Remember all the people on this very site that sincerely thought fiat currency was going away and we'd be doing all of our transactions w…

The difference is that Bitcoin was an overhyped solution looking for a problem.

Whereas AI is as big as life, eukaryotes, multi-cellularity, human intelligence, agriculture and the industrial revolution. It will certainly change everything (and make humans go extinct unless we are very careful).

Re: Nobody knows how to build with AI yet

#203

Post by jen729w »

saadatq wrote: post #177

this isn’t vibe coding. This is something completely new. I call it “flex coding.” heck I built a full app in an afternoon AND I was a good dad? > I'd wander into my office, check what Claude had built, test it real quick. If it worked, great! Commit and push. "Now build the server connection UI," I'd say, and wander back out. Made breakfast. Claude coded. Played with my son. Claude coded. Watched some TV. Claude cod…

This is all very emotive and I'm sure is a dream many of us would love to live.

But does Claude's code work? Does it work to the level where you'd depend on it yourself; where you'd bill customers for it; where you'd put your reputation behind it?

I say no. And it's because I use Claude. Two events changed how I use Claude: now it's an advisor, and I mostly type the code myself. Because I don't trust it.

First, I caught it copying one of my TypeScript interfaces and modifying it. So now we have User which looks like my actual user, that I defined, and UserAgain which does not, and which Claude is now using and proudly proclaiming that my type checks all pass. Well of course they do!

Second, I was told that the best way to catch this sort of thing is to get it to write tests. So it wrote some tests, and they failed, and it kept going, and it eventually wrote an un-failable test. The test mocked itself.

So, sure, enjoy time with your kids. Please don't ask me to use your app for anything important.

Re: Nobody knows how to build with AI yet

#204

Post by strange_quark »

iLoveOncall wrote: post #92

I feel increasingly tired of reading excuse after excuse when you bring up that AI tools simply cannot solve anything beyond extremely basic problems. It's always a mix of: 1. "Wait for the next models", despite models having all but plateaued for the past 3 years, 2. "It's so good for boilerplate code", despite libraries and frameworks being much better suited for this task, and boilerplate code being actually rare…

There’s about half a trillion reasons that it’s unfathomable to some.

Re: Nobody knows how to build with AI yet

#205

Post by CamperBob2 »

lordnacho wrote: post #15

I'm loving the new programming. I don't know where it goes either, but I like it for now. I'm actually producing code right this moment, where I would normally just relax and do something else. Instead, I'm relaxing and coding. It's great for a senior guy who has been in the business for a long time. Most of my edits nowadays are tedious. If I look at the code and decide I used the wrong pattern originally, I have to…

What junior devs will do, I'm not so sure. They somehow have to jump to the top of the mountain, but the stairs are gone.

"That's OK, I found a jetpack."

Re: Nobody knows how to build with AI yet

#206

Post by keeda »

Nobody knows how to build with AI yet, and the corollary (which TFA concludes with) is that everybody should figure out for themselves how to best work with AI.

I've said it before and I'll say it again: there likely isn't a "golden workflow" or "generally accepted best practices" on how to code with AI. The new models and agentic capabilities seem to be very powerful, and they will conform to whatever methodologies you currently use with whatever project you're working on, but that may still be under-utilizing what they are truly capable of.

A true optimum may even require you to adjust the way you work, down to structuring your code and projects differently. In fact you may need to figure out different approaches based on the project, the language, the coding style, the model, the specific task at hand, even your personality. I am convinced this aspect is what's causing the bimodal nature of AI coding discussions: people who stuck at it and figured it out, or just got lucky with the right mix of model / project / task / methodology, are amazed at their newfound superpowers -- whereas people who didn't, are befuddled by the hype.

This may seem like a lot of work, but it makes sense if you stop thinking of this as just a tool and more like working with a new team-mate.

Re: Nobody knows how to build with AI yet

#207

Post by deadbabe »

The entire premise of using AI to build stuff is founded on the idea that building faster is somehow automatically better.

I’m starting to believe that’s not necessarily true. And if some study finds out later that stuff built slowly by hand is actually better in every way except time-to-market, then it means AI is not really a competitive edge, it’s just a Quality of Life improvement that allows software engineers to be even lazier. And at future price points of $200, $400, even $1000 a month per head, that becomes a hard sell for most companies. Might be easier to have engineers pay for their own AI if they want to be lazy. And of course whether they use AI or not, you can still measure productivity under the assumption that every engineer does…

Re: Nobody knows how to build with AI yet

#208

Post by yeasku »

lordnacho wrote: post #15

I'm loving the new programming. I don't know where it goes either, but I like it for now. I'm actually producing code right this moment, where I would normally just relax and do something else. Instead, I'm relaxing and coding. It's great for a senior guy who has been in the business for a long time. Most of my edits nowadays are tedious. If I look at the code and decide I used the wrong pattern originally, I have to…

It is known team size and speed are not linear.

Many times adding a new junior to a team makes it slower.

How does using llms as junior makes you more productive?

Re: Nobody knows how to build with AI yet

#209

Post by SparkyMcUnicorn »

jen729w wrote: post #203
saadatq wrote: post #177

this isn’t vibe coding. This is something completely new. I call it “flex coding.” heck I built a full app in an afternoon AND I was a good dad? > I'd wander into my office, check what Claude had built, test it real quick. If it worked, great! Commit and push. "Now build the server connection UI," I'd say, and wander back out. Made breakfast. Claude coded. Played with my son. Claude coded. Watched some TV. Claude cod…

This is all very emotive and I'm sure is a dream many of us would love to live. But does Claude's code work? Does it work to the level where you'd depend on it yourself; where you'd bill customers for it; where you'd put your reputation behind it? I say no. And it's because I use Claude. Two events changed how I use Claude: now it's an advisor, and I mostly type the code myself. Because I don't trust it. First, I cau…

It's interesting reading comments on both sides of this. Some people are answering no, and others are answering yes to your question and succeeding at it... so far.

I've experienced the exact issues you've described. I've also drastically reduced these issues via good instructions and automated followup passes that eliminate code that was created from ignored instructions.

It all feels like a hack, but the more I choose to trust it and treat it like it's the correct path and that it's just a different set of problems that need to be solved, the more success I have.

Re: Nobody knows how to build with AI yet

#210

Post by skydhash »

ikerino wrote: post #140
stefan_ wrote: post #128

Earlier quoted context omitted.

Where did they learn sensibility for higher-level of abstraction? AI is the opposite, it will do what you prompt and never stop to tell you its a terrible idea, you will have to learn yourself all the way down into the details that the big picture it chose for you was faulty from the start. Convert some convoluted bash script to run on Windows because thats what the office people run? Get strapped in for the AI Power…

How is that different than how any self-taught programmer learns? Dive into a too-big idea, try to make it work and learn from that experience. Repeat that a few hundred times and you'll have some strong intuitions and sensibilities.

> Dive into a too-big idea, try to make it work and learn from that experience.

Or... just pick up that book, watch a couple of videos on Youtube and avoid all that trying.

Post reply on HN