Sorry you’re going through this, that sounds brutal. You mentioned an abusive childhood making things worse; if you’re open to sharing, has anything in therapy (trauma-informed work, CBT, EMDR, etc.) actually helped?
Do you have any take on non-med things like mindfulness/yoga nidra or gentle ambient sound at night? I’m on the fence about starting meditation myself and curious what’s been useful, or not, for you.
And if meds are what’s giving you relief right now, I’m glad you’ve found something that helps.
You have a great way of demystifying things. Thanks for the insights here!
Do you think a non-programmer could realistically build a full app using vibe coding?
What fundamentals would you say are essential to understand first?
For context, I’m in finance, but about 8 years ago I built a full app with Angular/Ionic (live on Play Store, under review on Apple Store at that time) after doing a Coursera specialization. That was my first startup attempt, I haven’t coded since.
My current idea is to combine ChatGPT prompts with Lovable to get something built, then fine-tune and iterate using Roo Code (VS plugin).
I’d love to try again with vibe coding. Any resources or directions you’d recommend?
If your app has to display stuff, you have no code kits available that can help you out. No vibe coding needed.
If your app has to do something useful, your app just exploded in complexity and corner cases that you will have to account for and debug. Also, if it does anything interesting that the LLM has not yet seen a hundred thousand times, you will hit the manual button quite quickly.
Claude especially (with all its deserved praise) fantasizes so much crap together while claiming absolute authority in corner cases, it can become annoying.
That makes sense, I can see how once things get complex or novel, the LLMs start to struggle. I don't think my app is doing anything complex.
For now, my MVP is pretty simple: a small app for people to listen to soundscapes for focus and relaxation. Even if no one uses, at least it's going to be useful to me and it will be a fun experiment!
I’m thinking of starting with React + Supabase (through Lovable), that should cover most of what I need early on. Once it’s out of the survival stage, I’ll look into adding more complex functionality.
Curious, in your experience, what’s the best way to keep things reliable when starting simple like this? And are there any good resources you can point to?
You can make that.
The only ai coding tools i have liked is openai codex and claude code.
I would start with working with it to create a design document in markdown to plan the project.
Then i would close the app to reset context, and tell it to read that file, and create an implementation plan for the project in various phases.
Then i would close context, and have it start implementing.
I dont always like that many steps, but for a new user it can help see ways to use the tools
I already have a feature list and a basic PRD, and I’m working through the main wireframes right now.
What I’m still figuring out is the planning and architecture side, how to go from that high-level outline to a solid structure for the app. I’d rather move step by step, testing things gradually, than get buried under too much code where I don’t understand anything.
I’m even considering taking a few React courses along the way just to get a better grasp of what’s happening under the hood.
Do you know of any good resources or examples that could help guide this kind of approach? On how to break this down, what documents to have?
> Do you think a non-programmer could realistically build a full app using vibe coding?
For personal or professional use?
If you want to make it public I would say 0% realistic. The bugs, security concerns, performance problems etc you would be unable to fix are impossible to enumerate.
But even if you had a simple loging and kept people's email and password, you can very easily have insecure dbs, insecure protections against simple things like mysqliinjections etc.
You would not want to be the face of "vibe coder gives away data of 10k users"
Ideally, I want this to grow into a proper startup. I’m starting solo for now, but as things progress, I’d like to bring in more people. I’m not a tech, product or design person, but AI gives me hope that I can at least get an MVP out and onboard a few early users.
For auth, I’ll be using Supabase, and for the MVP stage I think Lovable should be good enough to build and test with maybe a few hundred users. If there’s traction and things start working, that’s when I’d plan to harden the stack and get proper security and code reviews in place.
One of the issues AI coding has, is that its in some ways very inhuman. The bugs that are introduced are very hard to pick up because humans wouldnt write it that way, hence they wouldnt make those mistakes.
If you then introduce other devs you have 2 paths, they either build on top of vibe coding, which is going to leave you vulnerable to those bugs and honestly make their life a misery as they are working on top of work that missed basic decisions that will help it grow. (Imagine a non architect built your house, the walls might be straight but he didnt know to level the floor, or to add the right concrete to support the weight of a second floor)
Or the other path is they rebuild your entire app correctly. With the only advantage of the MVP and the users showing some viability for the idea. But the time it will take to rewrite it means in a fast moving space like start ups someone can quickly overtake you.
Its a risky proposition that means you are not going to create a very adequate base for the people you might hire.
I would still recommend against it, thinking that AI is more like WebMD, it can help someone who is already a doctor but it will confuse, and potentially hurt those without enough training to know what to look for.
If I'd use Vibe coding I wouldn't use Lovable but Claude code. You can run it in your terminal.
And I would ask it to use NextAuth, NextJS and Prisma (or another ORM), and connect it with SQLite or an external MariaDB managed server (for easy development you can start with SQLLite, for deployment to vercel you need an external database).
People here shit on nextjs, but due to its extensive documentation & usage the LLM's are very good at building with it, and since it forces a certain structure it produces generally decently structured code that is workable for a developer.
Also vercel is very easy to deploy, just connect Github and you are done.
Make sure to properly use GIT and commit per feature, even better branch per feature. So you can easily revert back to old versions if Claude messed up.
Before starting, spend some time sparring with GPT5 thinking model to create a database scheme thats future proof before starting out. It might be a challenge here to find the right balance between over-engineering and simplicity.
One caveat: be careful to run migration on your production database with Claude. It can accidentally destroy it. So only run your claude code on test databases.
I’m not 100% set on Lovable yet. Right now I’m using Stitch AI to build out the wireframes. The main reason I was leaning toward Lovable is that it seems pretty good at UI design and layout.
How does Claude do on that front? Can it handle good UI structure or does it usually need some help from a design tool?
Also, is it possible to get mobile apps out of a Next.js setup?
My thought was to start with the web version, and later maybe wrap it using Cordova (or Capacitor) like I did years ago with Ionic to get Android/iOS versions. Just wondering if that’s still a sensible path today.
I am unsure of what to think of this. It sickens me. In Scotland, Amazon workers chose to sleep in tents near the warehouse. In the depths of winter.
1) Workers in the warehouse at Amazon are in pretty bad conditions but how does this compare to working in a warehouse in other companies? Not sure if things are rosy elsewhere
2) What I fear is the growth and normalization of this behaviour in the future. Crappy jobs and child labour were acceptable during the Industrial Revolution, it was always better then no job in the rural area. But now it feels like a step backwards. In the information age, when tech giants are changing/destroying entire industries to create this new (great?) future?
3) And then, what happens when delivery drivers are replaced by drones and autonomous car makes car ownership irrelevant? Cloud subscription has made hardware servers irrelevant. Will we have car subscription to Google, Tesla and Uber? How will we earn money to pay for those subscriptions and buy on Amazon?
I can't wait until drones and other autonomous deliveries are available because maybe people will start getting their packages when they are supposed to.
For example I ordered a small package from Amazon last week. I don't order a lot from Amazon but when I do, there seems to always be delays and problems.
They guaranteed it by yesterday but it's still not here and isn't scheduled to be delivered for another 2 days putting it 4 days past the "guaranteed" delivery time.
This was standard shipping which is treated in the same way as free shipping in terms of delivery times.
Reason? Who knows, all I know is it was very likely a human error out of my control.
- Amazon's dashboard tells me I requested an address change even though I didn't.
- Amazon's phone rep tells me the USPS screwed up by delivering it to the wrong zone's post office.
- USPS tells me Amazon tends to ship things in pallets of 100 parcels and the pallet for my zone was filled so they put it into a different pallet (clearly knowing it would delay the package).
- USPS won't compensate me (I was put into a 30min 3 way conversation with Amazon, USPS and myself).
- Amazon updates me today saying the item has been dropped from tracking and is tagged as "lost in transit".
- USPS tells me the package is on the other side of the state I'm in (NY).
- Amazon said they will ship a new item out with 2 day delivery which doesn't help me get the item when it was supposed to arrive.
I understand that every single US govt ran service tends to be horrendous in terms of efficiency and quality but Amazon is supposed to be one of the most efficient platforms in the world.
I'm guessing this entire issue was due to some over worked warehouse employee just saying "fuck it" and threw my box into the wrong pallet but a robot would haven't made this mistake and a drone would have likely gotten to my residence a few hours after ordering instead of closer to 11-12 days.
I suspect Amazon may be overloading their capacity to actually fulfill their promised delivery timeframe (the hotel industry does this a lot with overselling rooms) for the simple reason that most people won't complain or can be placated easily. In the past year or so I've noticed a big change with Amazon Prime in particular to that end. I still get the items ordered after 1-2 days in shipping, but it's increasingly common to not ship for a day or two after the order is placed.
Without prime it typically takes 4-5 days for the order to go into "preparing for shipment", then 1-2 days for it to be shipped, followed by 2-3 days to get here.
It's kind of sad really. It's like your item is being held hostage because you haven't bought into using Prime.
For the reasons you just mentioned (it takes a day or 2 for it to ship) is the reason I'll never buy Prime. I don't like the idea of paying for a service that says 2-3 day free shipping but rarely comes in time.
Back in the good old days of mid-2000 you could order stuff from NewEgg and you'd get your package in 3-4 days all the time for the same shipping price that takes Amazon 6-10 days.
When an order is stuck in 'preparing for dispatch' it is easier just to cancel the order and try again. The same item magically gets dispatched as normal.
Why not look at Wikipedia and see how they are tackling controversial topics? Here it sounds like a disappointing ostrich experiment. Let's bury our head in sand, let the storm pass away and see what happens.
I think it's a good think that people are indignant on both side. Let's organise ourself. We have the tools, the concepts, the technology. I am sure it's possible to find some common ground and have some data-driven debates/discussions and form some more balance opinions/belief.
I have been using Firebase for two months now and it is a total nightmare to me. The support is awful.
1) I don't get answers on Stackoverflow.
2) I have stopped using your slack as it's close to impossible to get any answer. It's a complete joke.
3) When I tried to google, I often end up getting the legacy documents which are deprecated
4) There are too many breaking changes between your different versions. This makes it so confusing to use angularfire/firebase and finding deprecated code examples.
5) The youtube videos feels like a huge marketing stunts and you are all busy trying to promote an ever changing/incomplete firebase. 10 month old videos are no longer valid because of breaking changes.
6) The security rules difference between firebase storage & firebase database
7) Querying being such a huge pain. There was an effort made in a 2014 blog post but obviously code is obsolete.
I know in the end. It must be the developer's fault who’s not smart enough for firebase maybe.
Firebase YouTuber, Slacker, AngularFire contributor, and Stackoverflower here. Feel free to ping me personally in the Slack channel (davideast) of via email (david@firebase.com) to talk more about all of these problems you've hit. We work hard to make sure people get their questions answered so I'd love to have a discussion with you.
Do you have any take on non-med things like mindfulness/yoga nidra or gentle ambient sound at night? I’m on the fence about starting meditation myself and curious what’s been useful, or not, for you.
And if meds are what’s giving you relief right now, I’m glad you’ve found something that helps.