Friend is working on a SaaS startup solo as a non-technical founder. Been building using Replit and Cursor with Claude 3.5 and 3.7 and launched with live customers.
I preface because he's been using AI basically every day to build his SaaS.
I've been enjoying just trying to one-shot little pages that I think are useful with v0.dev. It does a pretty good job and I like that I can just one-button deploy to my Vercel account (which "just works"). Here's one I did today:
He has asked to not reveal it and not likely to reveal it. I asked him about it because I think the press would be insane, but it's a niche B2B SaaS and he doesn't want the "made with AI" branding to hurt the image of the product from a customer perspective. Second concern is people trying to hack it in case the LLM took shortcuts on security.
But I can say that as a 20yr+ eng. and having worked with him on a prior startup, I'm super, super impressed how far he got by himself in under 4 months. Basically a full-blown industry specific CRM with Stripe integration, OCR from mobile web app, desktop web app, marketplace. He himself is concerned that it's the end of SaaS as he thinks anyone can build these things now, but I think there's still a bit of a chasm when it comes to some ancillary pieces like databases.
I ran into a Show HN thread not so long ago where people were outright hostile to a minimally technical developer that did something actually impressive, in my eyes at least, but he was open about using AI for everything. I've not seen a more badly mannered thread on HN.
It's like some people are triggered by non-veterans programming with AI. I think everyone understands the downsides. Why get angry about it?
Yeah. It seems t me though that there two distinct demographics at play here. The"HN commenting crowd" and the "potential customers for a SaaS".
I understand and (mostly) stay out of the arguments between HN users (both "technical" and "non-technical" business types) about AI coding. (And I'm not particularly interested in airing those grievances again in this subthread, well mannered or not.)
But I'm intrigued that the dev mentioned upthread is intentionally hiding his use of LLM coding, instead of joining in with the AI buzzword bandwagon jumping that's going on pretty much everywhere I look in tech, from tiny to behemoth corporations.
It is inconceivable that someone would become angry on the internet. You're going to turn off the computer and run outside as fast as possible if you sense that your emotions are even just ever so slightly shifting from enjoyment.
Sarcasm is the internet default, though. Perhaps you didn't quite pick up on it that time?
If promoting your app as AI-made is going to draw ire regardless of whether it makes sense to, then it's just pragmatic business not to do so. You gain nothing by it. Doesn't have anything to do with being upset or offended by internet comments. Not all criticism is sensible.
The question asked why would people get angry about AI on an internet forum? The answer is that they don't.
What does that have to do with promoting apps and whether or not it is sensible business decision to do so? You must have accidentally hit the wrong reply button? I think I saw that discussion taking place elsewhere.
No they don't. Computers have a power button. If there was even the slightest indication that you were no longer having the time of your life, you'd press it and find something more enjoyable to do.
But as people on the internet do find great enjoyment in being funny (for some definition of funny), sometimes their humour might come across as being "angry" if you don't understand the context in which it is taking place.
>No they don't. Computers have a power button. If there was even the slightest indication that you were no longer having the time of your life, you'd press it and find something more enjoyable to do.
This is such a bizarre conversation. Yes, people on the internet sometimes get angry and don't go do something else. It happens.
It's not that simple. People do get mad on the Internet and it's not just that "Hey, why don't you just go outside and touch grass then?" because they can slander your SaaS, they can take malicious actions like hacking the site or exploiting it.
Sarcasm or cynicism is the default for some people and some communities. That's fine if it works for them. I'm not interested in it, and the HN I know has little of it. When I said "hostile" I wasn't talking about either of these though.
At the same time, he's really helping small business customers by offering a competitive product at a fraction of the price of the dominant vendors in the space (a duopoly) because he has no overhead. Customers love the product. No ads or marketing and he's got 30ish customers via word of mouth.
Interesting but a CRM built by a non-technical person using AI?
I think that's pretty irresponsible - building a product that holds PII without any concern for security. Not to mention that's a lawsuit waiting to happen.
Tooling: started developing in Replit including hosting, added Cursor later when it got a bit more complicated.
FE: React SPA with Tailwind; I don't think he was knowledgeable enough to pick a UI component library.
BE: Database is Supabase, auth is Firebase. He had a hard time getting the AI to work with Supabase auth so I suggested Firebase instead (Firebase auth is dead simple and lots of docs). This created another challenge which was using the claims from Firebase in Supabase for the row level security. Rest of the backend is running in Replit autoscale deployments. Stripe integration for payments and other integrations for common third party systems in this particular industry. All done via AI and handing it relevant documentation and code samples.
Replit's tooling is interesting because it can run the app and see the errors in the console. It can also take its own screenshots to see if it's getting it right. I watched some of his sessions and the LLM often makes mistakes. He'll try a few passes to get the LLM to fix the mistake, but if it doesn't work, he moves and will come back to it if it is non-breaking.
I talked to him a bit more and he said he thinks his "super power" is managing an offshore team in India for a few years so he's very used to managing features and code quality via written instructions. Where an engineer (like me) might just give up and take it into our own hands when things go wrong, he can just keep chatting with the AI and pointing it to docs and such.
I preface because he's been using AI basically every day to build his SaaS.
His comments today: