It works well with a very specific stack of chosen tools. Not to say it won’t scale to others but if you aren’t a react dev using tailwind and shadcn it’s useless for now.
What were you trying to get it to do? It was working alright for me but I was mostly doing quick HTML/CSS templating. I just paste in boilerplates and get it to make tailwind styles changes
I can see it working well for something like what Microsoft is doing with Adaptive Cards inside Teams conversations. I can imagine an AI chatbot that serve you targeted UI on the spot. It's integration with a whole site/app that is challenging.
Think it could be the recent debacle of making clone apps as a marketing move & one CS rep misusing access to harass a customer over a project domain/name.
Wow. At what point do we get Generative Web Apps or Site, full backend and front end.
Make a similar site to Basecamp, Notion, or something much simpler like an Online calculator? So people can bootstrap their App idea without even being a professional programmer?
Unless we are talking about generic things that already exist in forms of boilerplate/templates (like what all of GPT-generated apps are) - can be in a few years, can be never.
seems pretty close for non-cutting edge stuff. It's really just about making a solid UI to tie the developer experience together because with tools like this and an OpenAPI spec you can generate a huge chunk of the frontend and backend code. Anything that isn't very niche business logic can be generated by AI
once you have the prototype you can then give the AI some of your observability data and spin up a sandbox environment and have it iterate on any code that is slow, have it create 10 new versions of the code and send some mirrored traffic to test it and then deploy the best version.
You can already do this quite well. Check out my product: https://picoapps.xyz/ We allow you to interact with backend APIs including some builtin integrations like OpenAI and image generation. We do some basic custom backend generation as well.
Not sure why I'm getting down voted for this comment. I'd like to see an example of anything created by "AI" remotely close in complexity to Notion out there.
Every new generation reinvents stuff previous generation tried and hated. I think it is natural and kind of funny. I’ve been doing software for over 20 years + being obsessed since late 90s and I especially enjoy oscillations between server and client computing - “let’s do everything on server and make client dumb” - (5 years later) - “noooo, ma responsiveness and user experience!!!”
For a moment this post made me think I was going crazy. This post is 3 days old but it shows that it was posted 5 hours ago. I thought it was a repost but then reading the comments, I was sure I had read the exactly same thing. Is it some HN bug?
anway about v0:
this open box to start a project is the AI feature with lowest effort, they are bringing nothing not even a better UI but they have the userbase. Which is good to bring more customers to AI apps.
Hi Jared, I'm currently working on Commitspark, a headless CMS that uses vanilla GraphQL to define the content model and GitHub for storage and workflows. With this approach I can already today use ChatGPT to not only generate a website content model from a user prompt (e.g. "I want a component-based website with a hero component with title and image, a product component with article number, ...") but also entire web page content from user prompts (e.g. "I have this marketing text here, turn it into content data for a web page using the components in my content model: ...").
The perfect addition here would be to also enable users to generate React components that visualize each content component (I was able to prototype that already with ChatGPT, but I assume what you're doing is more advanced).
Wrap all of this up into a Git repo with Vercel deployment workflow for GitHub and it should be possible to go from prompt to CMS-driven website in a really short time.
So, my question: Would it be possible to get access to V0? Also, feel free to reach out if you see potential for collaboration.
v0 saves loads of time by allowing you to quickly generate UIs with React via Shadcn UI (https://ui.shadcn.com) with simple text prompts. While full scale design tools are very useful, not every UI in your app needs that level of fidelity. Furthermore, a lot of UIs inside of apps and websites are already extremely programmatic (such as forms, tables, modals, etc.). The goal with v0 is to get you started (hence the name) faster....to give you something you can copy and paste and then modify yourself.
Can't find any mention of which AI is used but I suppose it is OpenAI GTP4 given the waitlist (OpenAI enforces strict rate limits on their API except for ChatGPT) and expensive pricing.
I've had access for a bit and it's a pretty neat tool to experiment with but not much beyond that.
I actually tried to recreate the functionality with Cody [cody.dev] in VS Code and it actually worked pretty similarly minus the GUI, but I found it a little less restrictive and I could specify the CSS framework.
It does seem to output a regular web application based on their description here.
> v0 produces code using open-source tools like React, Tailwind CSS, and Shadcn UI.
So you can just debug it as always. I guess this product is for someone that COULD make the app they’re generating, but chooses not to. Rather they want an app, that they then only have to refactor.
The intention is the output is quite literally your v0. It’s a normal React application, so you’d debug it and build it as such. It’s unlikely you’d take the output and launch right away. You’d probably have other refactoring and modifications first.
We're embracing copy-and-paste with the product rather than increasing abstraction. The tool provides the HTML or React code for building the generated UI. The way you actually use it, is by copy-pasting it into your app. From that moment on your workflow and specially debugging workflow is exactly as before. The tool just writes the first 100 lines of code to get you started with a great UI.
I'm not the biggest fan of this product, but I do have to say that they're pretty intentional about this not being meant for production code. It's more for testing out ideas, hence the name "v0" as in "what happens well before a v1."
Sure, however, if you have been around longer, you will know that tons of these will end up in (critical) production anyway. It doesn't matter what label they put on it.
This is indeed a fair point, and part of why I'm not really into it.
In theory, you'd save a bunch of time and then use that extra time to add more polish to the product. But in practice, what you'd actually be doing is reading someone else's (or something else's) code, and people who want to rely on AI are not the same people who have the stomach to do that.
So they're either going to (a) abandon the generated code and write their own, in which case, what was the point to begin with? Or (b) they're going to just say "fuck it" and push the generated code to prod.
I mean this is no different than life now. You have some MVP code patched up by startup hacker or "CTO", etc, then as team grows it's hard to work with.
This is going to be a major disaster. NextJs, the "framework" that underpins Vercel, is already a massive failure for anything beyond a simple basic static site with a few server-side functions.
Maybe it'll push us for the final collapse of the web though. This video is very relevant at this moment: https://youtu.be/ZSRHeXYDLko
Nextjs and Vercel destroyed React turning it into PHP, but that was the only way they could make VC-worthy money. Great move for them, terrible for the ecosystem. React makes no sense anymore and is painful to use.
Congrats on shipping this game changer Vercel, this is absolutely huge for indie devs and product teams to bridge the gap of design and development without friction or insane dev costs.
Bravo!
Edit: Why the downvotes? I don't understand this at all?
Nope, just someone who likes vercel's design plus UX/UI, :)
What's great about this is that not only this is a next step in AI generated websites, but this is actually shipped software which is much better than the overpromised and overhyped thegrid.io vapourware.
Ahhh the grid, I remember that. There was another highly touted company around the same time that also had some mildly interesting tech and ideas sort of in the same vein but just burned through VC money. I was hoping the grid layout system based on constraints would mature enough to become a proper css standard at some point. We did eventually get css grid, which is pretty good, but having a constraints solver in css would be pretty neat. (Or just a performance nightmare.)
I think it was an interesting idea that unfortunately didn't really work out. This was before both flex and grid layouts were a thing, so anything new in this space was exciting really. It's a much better css layout world today than it was 8-10 years ago, and particularly grid layout is a very welcome change, but I can't help but think some great ideas have been left by the wayside. Maybe for good reasons, but still.
I think it is a fair criticism about the intention as the tone in the post is a bit strange? What is shown in the video isn't great and the app isn't publicly available yet so any excessive praise really sounds strange.
It's curious that many people are rushing to defend the notion that there's nothing suspicious about calling a non-public product with a mediocre 5/10 video a 'game-changer'.
"make the company logo blue". This is only game-changer if you also think React-PHP (RSC) is game-changer (which was, but to stop React growth and start its demise).
