I preface because he's been using AI basically every day to build his SaaS.
His comments today:
> also gemini 2.5 is beating claudeBut 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.
That's kinda telling.
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.
It's like some people are triggered by non-veterans programming with AI. I think everyone understands the downsides. Why get angry about it?
Sarcasm is the internet default, though. Perhaps you didn't quite pick up on it that time?
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.
But they do lol.
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.
This is such a bizarre conversation. Yes, people on the internet sometimes get angry and don't go do something else. It happens.
No one is mistaking humor for anger.
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.
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.
This… warrants some self reflection.