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

191–200 of 432 posts

Re: Nobody knows how to build with AI yet

#191

Post by scorpioxy »

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…

My feelings exactly. For a while I thought I was missing out and then I started learning how(and why) it works and I thought it was interesting but greatly over-hyped, exactly like bitcoin was.

I tried to follow the hype and generate an application but it took a lot of time and it did generate something but not something that works with many subtle bugs. Now it may be that I needed to prompt it better, but that response also feels similar to how Scrum is always "done wrong" when it doesn't work. The result started getting better when I got more and more detailed with my prompts and then I realized that I am about to start writing code as a prompt and I may as well write the code myself.

So I still think it's an interesting tool, and it will automate away certain industries but no where near what the advertising is implying.

Re: Nobody knows how to build with AI yet

#192

Post by baxter001 »

dustincoates wrote: post #168
nirvanatikku wrote: post #9

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…

Repl.it is so hit or miss for me, and that's that is so frustrating. Like, it can knock out something in minutes that would have taken me an afternoon. That's amazing. Then other times, I go to create something that is suggested _by them below the prompt box_ and it can't do it properly.

The fact that you think it was suggested _by_ them is I think where your mental model is misleading you.

LLMs can be thought of metaphorically as a process of decompression, if you can give it a compressed form for your scenario 1 it'll go great - you're actually doing a lot of mental work to arrive at that 'compressed' request, checking technical feasibility, thinking about interactions, hinting at solutions.

If you feed it back it's own suggestion it's no so guaranteed to work.

Re: Nobody knows how to build with AI yet

#193

Post by pessimizer »

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.

The self-taught programmer's idea was coded by someone who is no smarter than they are. It will never confuse them, because they understand how it was written. They will develop along with the projects they attempt.

The junior dev who has agents write a program for them may not understand the code well enough to really touch it at all. They will make the wrong suggestions to fix problems caused by inexperienced assumptions, and will make the problems worse.

i.e. it's because they're junior and not qualified to manage anybody yet.

The LLMs are being thought of as something to replace juniors, not to assist them. It makes sense to me.

Re: Nobody knows how to build with AI yet

#194

Post by lobf »

karel-3d wrote: post #142
esafak wrote: post #129

Earlier quoted context omitted.

Imagine a future where creating software is about the designing the UX, overseeing the architecture and quality assurance. Implementation is farmed out.

But the architecture is the important (and hard) part!!! Not the UX!

A customer doesn't care about architecture. They want a good UX.

Re: Nobody knows how to build with AI yet

#195

Post by 827a »

Flatcircle wrote: post #22

My theory on AI is it's the next iteration of google search, a better more conversational, base layer over all the information that exists on the internet. Of course some people will lose jobs just like what happened to several industries when search became ubiquitous. (newspapers, phone books, encyclopedias, travel agents) But IMHO this isn't the existential crisis people think it is. It's just a tool. Smart, clever…

Yeah; there's still a massive chasm between "I spent hours precisely defining my requirements for this greenfield application with no users and the AI one-shot it" and "million line twenty team enterprise SaaS hellscale with ninety-seven stakeholders per line of code".

The fact that AI can actually handle the former case is, to be clear, awesome; but not surprising. Low-code tools have been doing it for years. Retool, even back in 2018, was way more productive than any LLMs I've seen today, at the things Retool could do. But its relative skill at these things, to me, does not conclusively determine that it is on the path toward being able to autonomously handle the latter.

The english language is simply a less formal programming language. Its informality means it requires less skill to master, but also means it may require more volume to achieve desired outcomes. At some level of granularity, it is necessarily the case that programming in english begins to look like programming in javascript; just with capital letters, exclamation points, and threats to fire the AI instead of asserts and conditionals. Are we really saving time, and thus generating higher levels of productivity? Or, is its true benefit that it enables foray into languages and domains you might be unfamiliar with; unlocking software development for a wider range of people who couldn't muster it before? Its probably a bit of both.

Dario Amodei says we'll have the first billion dollar solo-company by 2026 [1]. I lean toward this not happening. I would put money on even $100M not happening, barring some level of hyperinflation which changes our established understanding of what a dollar even is. But, here's what I will say: hitting levels of revenue like this, with a human count so low that the input of the AI has to overwhelm the input from the humans, is the only way to prove to me that, actually, these things might be more than freakin awesome tools. Blog posts from people making greenfield apps named after a furrsona DJ isn't moving the needle for me on this issue.

[1] https://www.inc.com/ben-sherry/anthropic-ceo-dario-amodei-pr...

Re: Nobody knows how to build with AI yet

#196

Post by fragmede »

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…

peeThe difference is Bitcoin is a networked system. Bitcoin is useless if I use it and you/my landlord/stores/the taxman doesn't. If my pizza store doesn't take Bitcoin, I can't use my Bitcoin. Meanwhile, LLM assisted programming has value to its adherents without needing you/my landlord/stores/the taxman to even have heard of it. My time machine is just as good as yours, so I have no idea if OpenAI, specifically is going to be around in 10 years, but I can tell you that I'll still have deepseek-r1.ggml

Re: Nobody knows how to build with AI yet

#197

Post by helix400 »

asadotzler wrote: post #112

I seem to have missed the part where he successfully prompted for security, internationalizability, localizability, accessibility, usability, etc., etc. This is a core problem with amateurs pretending to be software producers. There are others, but this one is fundamental to acceptable commercial software and will absolutely derail vibe coded products from widespread adoption. And if you think these aspects of qualit…

Exactly.

>My four-document system? Spaghetti that happened to land in a pattern I could recognize. Tomorrow it might slide off the wall. That's fine. I'll throw more spaghetti.

Amazing that in July 2025 people still think you can scale development this way.

Re: Nobody knows how to build with AI yet

#198

Post by baby_souffle »

asadotzler wrote: post #112

I seem to have missed the part where he successfully prompted for security, internationalizability, localizability, accessibility, usability, etc., etc. This is a core problem with amateurs pretending to be software producers. There are others, but this one is fundamental to acceptable commercial software and will absolutely derail vibe coded products from widespread adoption. And if you think these aspects of qualit…

> And if you think these aspects .. , you've probably never done serious work in those spaces.

To be fair, a lot of commercial software clearly hasn't, either.

Re: Nobody knows how to build with AI yet

#199

Post by sarchertech »

paulgerhardt wrote: post #7
fmbb wrote: 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?

16 developers doing hundreds of tasks. And the effect size was big enough for the result to be statistically significant.

Re: Nobody knows how to build with AI yet

#200

Post by roxolotl »

nirvanatikku wrote: post #9

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.
Post reply on HN