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

Show HN: I quit coding years ago. AI brought me back

calquio.com

Post reply on HN
Print view View original

261–270 of 460 posts

Re: Show HN: I quit coding years ago. AI brought me back

#261

Post by SPICLK2 »

meetingthrower wrote: post #166
keyle wrote: post #90

Earlier quoted context omitted.

Hear hear. It too shall pass. They'll get tired, they'll grind the same apps 500 times and leave. Just like SEO experts, marketing experts, trade bots and crypto experts; the vibe coders will weed out.

Vibecoder here. I don't think so. I am a PE investor, and we are using it in our small portfolio companies to great effect. We can make small little mini-apps that do one thing right and help automate away extra work. It's a miracle. Simply wouldn't have been done before. I think we'll see an explosion of software in small and midsize companies. I admit it may be crappy software, but as long as the scope is small - w…

>an explosion of software in small and midsize companies

For me, that is nightmare fuel. We already have too much software! And it's all one framework or host app version update away from failure.

Re: Show HN: I quit coding years ago. AI brought me back

#262

Post by skeledrew »

anonymous908213 wrote: post #110
skeledrew wrote: post #104

Earlier quoted context omitted.

> I guess people who aren't software engineers don't realise that merely making a trivially basic website is not what software engineering is. "Software engineering" doesn't matter to anyone except to software engineers. What matters is executing that idea that's been gathering dust for ages, or scratching that pain point that keeps popping up in a daily basis.

Software engineering matters very much to anyone who has ideas or pain points that are beyond the capabilities of a next-token prediction engine to solve.

Not really. Those ideas or pain points are simply ignored or endured by anyone who isn't a software engineer until the tools (no-code platform, LLM, etc) become good enough, or someone else builds the thing and makes it available.

Re: Show HN: I quit coding years ago. AI brought me back

#263

Post by Tistel »

I have seen code bases that are amazing. I have seen ones that look bad, but work. About a year and half ago I saw my first fairly large scale fully AI generated project and it filled me with dread. It looked like the figma, which is very impressive. But under the hood it was bizarre. It was like those sci-fi movie tropes of teleportation where one of the people teleport and the destination coordinates are wrong and the merge with a tree or rock or whatever. There was so much unused junk that had nothing to do with anything. Ugh. My task to was to figure out why the initial render took so long. (unsurprisingly it was loading all the data then rendering, so with toy dev loads it was fine, in production nightmare and getting worse). So I just got to it and made some progress. But the new grad (who thought I was a dinosaur (might be right)) who made it was working in parallel and reintroducing more slop. So it became this Sisyphean task where I am speeding things up (true dinosaur so measuring things) and they were cutting and pasting and erasing the gains.

I have always found management to be just silly exercise in day full of meetings. I like to make things. I could retrain, but, the salary drop would be very hard. Hope to find one last gig and have enough to retire. I still get that spark of joy when all the tests pass.

Re: Show HN: I quit coding years ago. AI brought me back

#264

Post by fourside »

> Stack: Next.js, React, TailwindCSS, shadcn/ui, four languages (EN/DE/FR/JA). The AI picked most of this when I said "modern and clean."

I’m not an AI hater but I do see this as evidence of LLMs being susceptible to chasing trends as much as people.

Next.js with server rendered React is not a stack that an experienced web developer would have recommended for a “clean” solution to a collection of financial calculators. It’s the answer you’d get if you asked for the stack that’s trending the most lately.

Re: Show HN: I quit coding years ago. AI brought me back

#265

Post by greenchair »

voidUpdate wrote: post #162
SamPatt wrote: post #152

Earlier quoted context omitted.

Well yeah! This is objectively a great process for getting a lot of work done.

I guess I'm an outlier then because I actually like programming, and I've never wanted to be a manager, even a manager of an LLM. At least half the fun of making software is doing the programming

You aren't an outlier. Most of us got into coding because we enjoyed coding, not writing documentation that talks about coding.

Re: Show HN: I quit coding years ago. AI brought me back

#266

Post by boesboes »

gxs wrote: post #223
bitwize wrote: post #84

Earlier quoted context omitted.

It sucks the joy out of it because to the extent that you build something with AI, (Obama voice) you didn't build that. I am allergic to the concept of developing with AI, especially for personal work, because AI-authored code isn't something I built , it's something I commissioned . It's like if I went onto Fiverr or Upwork with a spec and paid money and said "Here, build this" to a freelancer and then went back and…

Huh? What about all the open source software you use, did you build all of it? What about the phone in your hand, did you design that? HN loves to believe they are the noble few - men and women of math and science, driven by nothing but the pure joy of their craft But this whole AI thing has been super revealing. Almost everyone here is just the same old same old, only that now that the change is hitting close to hom…

You are going to end up property of openai and with zero skills. Good luck

Re: Show HN: I quit coding years ago. AI brought me back

#267

Post by abalashov »

aenis wrote: post #260
abalashov wrote: post #245

Earlier quoted context omitted.

> Do you not fear that future/advanced AI will be able to look at a vibe-coded codebase and make sensible refactors itself? This is a possibility in very well-trodden areas of tech, where the stack and the application are both banal to the point of being infinitely well-represented in the training. As far as anything with any kind of moat whatsoever? Here, I'm not too concerned.

I am no longer sure thats the case. I had it chew through a gnarly problem with my own custom webrtc implementation on a esp32 SOC. It did not rely on any existing documentation as this stuff is quite obscure - it relied on me pointing to specs for webrtc, specs for esp32 SDK, and quite some prompting. But it solved the problems I was dreading to solve manually in a matter of a 2hr session. Thats for a hobby project,…

That might be true for WebRTC...

Re: Show HN: I quit coding years ago. AI brought me back

#268

Post by foke82 »

The current trend made me realize I don't like coding so much as I like creating stuff. So I'm happy I can build the stuff faster in an increasingly tight schedule as I'm getting older. I have always done small projects at home, few of which would reach maturity, and I was doing less and less every year, until recently!

Re: Show HN: I quit coding years ago. AI brought me back

#269

Post by lelanthran »

abalashov wrote: post #244
lelanthran wrote: post #242

Earlier quoted context omitted.

> On the plus side, vibe coding disaster remediation looks to be a promising revenue stream in the near future, and I am rubbing my hands together eagerly as I ponder the filthy lucre. I don't think it will be; a vibe coder using Gas Town will easily spit out 300k LoC for a MVP TODO application. Can you imagine what it will spit out for anything non-trivial? How do you even begin to approach remedying that? The only…

> How do you even begin to approach remedying that? The only recourse for humans is to offer to rebuild it all using the existing features as a functional spec. There are cases where that will be the appropriate decision. That may not be every case, but it'll be enough cases that there's money to be made. There will be other cases where just untangling the clusterfuck and coming up with any sense of direction at all,…

I've read your whole reply and agree with most of it; what I don't agree with (or don't understand) is below:

> If you are in need vibe coding disaster remediation consulting, it's not because you need to refactor 300,000 lines of slop real quick. That's not going to happen.

My experience as a consultant to business is that they only ever bring in consultants when they need a fix and are in a hurry. No client of mine ever phoned me up to say "Hey, there, have you any timeslots next week to advise on the best way to do $FOO?", it's always "Hey there, we need to get out an urgent fix to this crashing/broken system/process - can we chat during your next free slot?".

> Like everything else worth doing, deep specialisation is valuable and, to some extent, insulating.

I dunno about this - depends on the specialisation.

They want a deep specialist in K8? Sure, they'll hire a consultant. Someone very specialist in React? They'll hire a consultant. C++ experts? Consultants again.

Someone with deep knowledge of the insurance industry? Nope - they'll look for a f/timer. Someone with deep knowledge of payment processing? No consultant, they'll get a f/timer.

Re: Show HN: I quit coding years ago. AI brought me back

#270

Post by abalashov »

lelanthran wrote: post #269
abalashov wrote: post #244

Earlier quoted context omitted.

> How do you even begin to approach remedying that? The only recourse for humans is to offer to rebuild it all using the existing features as a functional spec. There are cases where that will be the appropriate decision. That may not be every case, but it'll be enough cases that there's money to be made. There will be other cases where just untangling the clusterfuck and coming up with any sense of direction at all,…

I've read your whole reply and agree with most of it; what I don't agree with (or don't understand) is below: > If you are in need vibe coding disaster remediation consulting, it's not because you need to refactor 300,000 lines of slop real quick. That's not going to happen. My experience as a consultant to business is that they only ever bring in consultants when they need a fix and are in a hurry. No client of mine…

> My experience as a consultant to business is that they only ever bring in consultants when they need a fix and are in a hurry.

No, that's fair, and I think you're right about that. But refactoring 300,000 lines 'real quick' isn't going to happen, regardless of that. :)

> They want a deep specialist in K8? Sure, they'll hire a consultant. Someone very specialist in React? They'll hire a consultant. C++ experts? Consultants again.

I implicitly had narrow technical specialisations in mind, albeit including ones that intersect with things like "insurance industry workflows".

Post reply on HN