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

Has the cost of building software dropped 90%?

martinalderson.com

Post reply on HN
Print view View original

521–530 of 744 posts

Re: Has the cost of building software dropped 90%?

#521

Post by mrwrong »

adriand wrote: post #515
r_lee wrote: post #507

Earlier quoted context omitted.

These posts like the one OP made is why I'm losing my mind. Like, is there truly an agentic way to go 10x or is there some catch? At this point while I'm not thrilled about the idea of just "vibe coding" all the time, I'm fine with facing reality. But I keep having the same experience as you, or rather leaning more on that supercharged Google/SO replacement or just a "can you quickly make this boring func here that d…

> Like, is there truly an agentic way to go 10x or is there some catch? Yes. I think it’s practice. I know this sounds ridiculous, but I feel like I have reached a kind of mind meld state with my AI tooling, specifically Claude Code. I am not really consciously aware of having learned anything related to these processes, but I have been all in on this since ChatGPT, and I honestly think my brain has been rewired in a…

> Yes, I know this sounds ridiculous and over-the-top.

in that case you should come with more data. tell us how you measured your productivity improvement. all you've said here is that it makes you feel good

Re: Has the cost of building software dropped 90%?

#522

Post by bonzini »

r_lee wrote: post #507
tangotaylor wrote: post #498

> Engineers need to really lean in to the change in my opinion. I tried leaning in. I really tried. I'm not a web developer or game developer (more robotics, embedded systems). I tried vibe coding web apps and games. They were pretty boring. I got frustrated that I couldn't change little things. I remember getting frustrated that my game character kept getting stuck on imaginary walls and kept asking Cursor to fix it…

These posts like the one OP made is why I'm losing my mind. Like, is there truly an agentic way to go 10x or is there some catch? At this point while I'm not thrilled about the idea of just "vibe coding" all the time, I'm fine with facing reality. But I keep having the same experience as you, or rather leaning more on that supercharged Google/SO replacement or just a "can you quickly make this boring func here that d…

I did find some benefit in lowering the cost of exploratory work, but that's it—certainly worth 20€/month, but not the price of any of the "ultimate" plans.

For example today I had to write a simple state machine (for a parser that I was rewriting so I had all the testcases already). I asked Claude Code to write the state machine for me and stopped it before it tried compiling and testing.

Some of the code (of course including all the boilerplate) worked, some made no sense. It saved a few minutes and overall the code it produced was a decent first approximation, but waiting for it to "reason" through the fixes would have made no sense, at least to me. The time savings mostly came from avoiding the initial "type the boilerplate and make it compile" part.

When completing the refactoring there were a few other steps like where using AI was useful. But overall the LLM did maybe 10% of the work and saved optimistically 20-30 minutes over a morning.

Assuming I have similar savings once a week, which is again very optimistic... That's a 2% reduction or less.

Re: Has the cost of building software dropped 90%?

#523

Post by bonzini »

Jean-Papoulos wrote: post #486
loandbehold wrote: post #183

Earlier quoted context omitted.

Most of software work is maintaining "legacy" code, that is older systems that have been around for a long time and get a lot of use. I find Claude Code in particular is great at grokking old code bases and making changes to it. I work on one of those old code bases and my productivity increased 10x mostly due to Claude Code's ability to research large code bases, make sense of it, answer questions and making careful…

I have the opposite experience. Claude can't get it all in the context window and make changes that will completely break something on the other side of the program. Granted that's because the program is incredibly poorly written, but still, context window will stay a huge barrier for quite some time.

Yep. It can refactor very well but that's it. For complex code bases it cannot even build boilerplate that makes sense; at most it saves some typing.

Re: Has the cost of building software dropped 90%?

#524

Post by weird-eye-issue »

layer8 wrote: post #193
thot_experiment wrote: post #53

Earlier quoted context omitted.

To be fair, writing a SaaS software is like an order, perhaps two orders of magnitude more effort than writing software that runs on a computer and does the thing you want. There's a ton of stuff that SaaS is used for now that's basically trivial and literally all the "engineering" effort is spent on ensuring vendor lock in and retaining control of the software so that you can force people to keep paying you.

We should also get a flurry of low-cost, decent-quality native local-first software, but I’m not seeing any.

I think you underestimate just how hard visibility is. If something is free or super low cost than they won't have any marketing budget for you to hear about it in the first place because it would be unprofitable...

One thing I've come to realize is that if something is cheap enough then people won't even want to promote it because if they get a commission on it then it won't be worth their time. So in some cases they will be better off recommending a much higher price competitor. Just go Google around for some type of software (something competitive and commercial like CRMs) and you'll notice why for commercial projects nobody is recommending free or really cheap solutions because it's not in anybody's best interest

Re: Has the cost of building software dropped 90%?

#525

Post by mbesto »

nine_k wrote: post #35

Had the cost of building custom software dropped 90%, we would be seeing a flurry of low-cost, decent-quality SaaS offering all over the marketplace, possibly undercutting some established players. From where I sit, right now, this does not seem to be the case. This is as if writing down the code is not the biggest problem, or the biggest time sink, of building software.

> Had the cost of building custom software dropped 90%, we would be seeing a flurry of low-cost, decent-quality SaaS offering all over the marketplace, possibly undercutting some established players.

Aha. Are developers finally realizing that just writing code doesn't make a business? We actually have a ton of SaaS companies being born right now but they're not making headway, because functionality and good code don't necessarily mean good businesses. Building a business is hard.

Re: Has the cost of building software dropped 90%?

#526

Post by enbugger »

adam_patarino wrote: post #514

I feel like people who write articles like this have never worked at big companies. My wife works at Shutterstock, first as a SWE, now as a product manager. Most of their tasks involve small changes in 5 different systems. Sometimes in places like Salesforce. A simple ask can be profoundly complicated. AI has certainly made grokking, and code changes easier. But the real cost of building has not been reduced 90%. Not…

The author "teaches workshops on AI development for engineering teams". This is nothing but a selling post for companies. I don't know what to discuss here honestly, this is more primitive bait than an average video preview picture on YouTube.

Re: Has the cost of building software dropped 90%?

#527

Post by dns_snek »

coldtea wrote: post #446
eru wrote: post #349

Earlier quoted context omitted.

> In some cases we aren't fully authorised to use the AI tools for actual coding but even just asking "how would you make this change" [...] Isn't the logical endpoint of this equivalent to printing out a Stackoverflow answer and manually typing it into your computer instead of copy-and-pasting? Nitpicks aside, I agree that contemporary AIs can be great for quickly getting up to speed with a code base. Both a new lib…

> Isn't the logical endpoint of this equivalent to printing out a Stackoverflow answer and manually typing it into your computer instead of copy-and-pasting? Isn't the answer on SO the result of a human intelligence writing it in the first place, and then voted by several human intelligencies to top place? If an LLM was merely an automated "equivalent" to that, that's already a good thing! But in general, the LLM ans…

> Isn't the answer on SO the result of a human intelligence writing it in the first place, and then voted by several human intelligencies to top place? If an LLM was merely an automated "equivalent" to that, that's already a good thing!

The word "merely" is doing all of the heavy lifting here. Having human intelligence in the loop providing and evaluating answers is what made it valuable. Without that intelligence you just have a machine that mimics the process yet produces garbage.

Re: Has the cost of building software dropped 90%?

#528

Post by pllbnk »

nine_k wrote: post #35

Had the cost of building custom software dropped 90%, we would be seeing a flurry of low-cost, decent-quality SaaS offering all over the marketplace, possibly undercutting some established players. From where I sit, right now, this does not seem to be the case. This is as if writing down the code is not the biggest problem, or the biggest time sink, of building software.

I have seen it commonly cited (although haven't bothered to check the actual sources, mostly because I believe they should be taken with a grain of salt) that developers spend somewhere in the ballpark of 50-60% of their time doing "coding work" - that is writing the code, thinking about the solution in terms of technical aspects, reading code reviews. The rest are meetings, coordination, administrative tasks, being blocked or whatever else you can think of. Even if, wishfully thinking, the value of the act of "coding work" fell by 90%, the act of doing "software engineering" work would still cost no less than 50% of what it currently does. Headlines like these are alarmist and have little substance.

Edit: I also feel stumped why so many people give in to this hype that LLMs are good at coding when they can't even do seemingly simple tasks of plain English language summarization accurately as evidenced in https://www.youtube.com/watch?v=MrwJgDHJJoE. If the AI summarizes the code in its own context incorrectly then it will not be able to write it correctly either.

Re: Has the cost of building software dropped 90%?

#529

Post by itgoon »

r_lee wrote: post #507
tangotaylor wrote: post #498

> Engineers need to really lean in to the change in my opinion. I tried leaning in. I really tried. I'm not a web developer or game developer (more robotics, embedded systems). I tried vibe coding web apps and games. They were pretty boring. I got frustrated that I couldn't change little things. I remember getting frustrated that my game character kept getting stuck on imaginary walls and kept asking Cursor to fix it…

These posts like the one OP made is why I'm losing my mind. Like, is there truly an agentic way to go 10x or is there some catch? At this point while I'm not thrilled about the idea of just "vibe coding" all the time, I'm fine with facing reality. But I keep having the same experience as you, or rather leaning more on that supercharged Google/SO replacement or just a "can you quickly make this boring func here that d…

Like another reply says: practice.

How many hours have you spent writing code? Thousands? Tens of thousands? Were you able to achieve good results in the first hundred hours?

Now, compare it to how much time you've spent working with agents. Did you dedicate considerable time to figuring out how to use them? Do you stop using the agent and do things manually when it isn't going right, or do you spend time figuring out how to get the agent to do it?

Re: Has the cost of building software dropped 90%?

#530

Post by adriand »

r_lee wrote: post #520
adriand wrote: post #515

Earlier quoted context omitted.

> Like, is there truly an agentic way to go 10x or is there some catch? Yes. I think it’s practice. I know this sounds ridiculous, but I feel like I have reached a kind of mind meld state with my AI tooling, specifically Claude Code. I am not really consciously aware of having learned anything related to these processes, but I have been all in on this since ChatGPT, and I honestly think my brain has been rewired in a…

That's really interesting. May I ask what kinds of projects, stack and any kind of markdown magic you use? And any specific workflow? And are there times when you have to step in manually?

Currently three main projects. Two are Rails back-ends and React front-ends, so they are all Ruby, Typescript, Tailwind, etc. The third is more recent, it's an audio plugin built using the JUCE framework, it is all C++. This is the one that has been blowing my mind the most because I am an expert web developer, but the last time I wrote a line of C++ was 20 years ago, and I have zero DSP or math skills. What blows my mind is that it works great, it's thread safe and performant.

In terms of workflow, I have a bunch of custom commands for tasks that I do frequently (e.g. "perform code review"), but I'm very much in the loop all the time. The whole "agent can code for hours at a time" thing is not something I personally believe. It depends on the task how involved I get, however. Sometimes I'm happy to just let it do work and then review afterwards. Other times, I will watch it code and interrupt it if I am unhappy with the direction. So yes, I am constantly stepping in manually. This is what I meant about "mind meld". The agent is not doing the work, I am not doing the work, WE are doing the work.

Post reply on HN