[HN Gopher] Launch HN: Marblism (YC W24) - Generate full-stack w...
___________________________________________________________________
Launch HN: Marblism (YC W24) - Generate full-stack web apps from a
prompt
Hi HN, We are Cyril & Ulric and are building Marblism
(https://marblism.com), an LLM-based dev platform to generate and
iterate on full-stack web apps. Here's a demo video that goes from
a comment on Twitter to a working app in 10 minutes:
https://www.youtube.com/watch?v=TapOPO-Gv20. Marblism started when
we realized that much of the code we write for web apps is just
slightly modified boilerplate: similar login flows, dashboards, API
integrations, CRUD operations, etc. While AI tools are helpful,
they fall short in delivering a well-architected codebase. The idea
of Marblism is to combine the best of both worlds: a solid
boilerplate, customized and enhanced with AI. Here's how it works:
_Generate your app_ - Describe your product, and the AI will build
your data model. We create a NextJS app with auth, custom CRUDs,
permissions, payment, emails. The AI then generates your front-end
pages. _Test and improve your app_ - Now that your app is set up,
use our online workspace to test your app and add more complex
features via an AI Chat or directly yourself in the VSCode editor.
_Go live_ - Once you're happy with your app, deploy it in
production in one click. Here are some examples of apps generated
on Marblism in couple of hours of prompting: Find and validate
startup ideas: https://www.muckbrass.com/ A design system
directory: https://awesomedesignsystem.app.io AI-Personalized
candle: https://www.scent-a-scene.com/ Marblism currently
generates web apps like SaaS, marketplaces, and social networks. It
doesn't support Chrome extensions or mobile apps, and it's not
really for small games like Snake/Tetris. The vision is to add
more tech stacks later this year and enable people to create their
own templates/tech stack that the AI can customize. We're really
excited to share this with you and we'd love to hear your thoughts
on the potential directions we can take this product.
Author : umussetu
Score : 84 points
Date : 2024-09-17 15:04 UTC (7 hours ago)
| altdataseller wrote:
| How did Marblism know what external APIs were available when it
| generated those search volume charts? (or is it mock data?)
| umussetu wrote:
| I asked it to integrate with https://dataforseo.com/ api which
| is 10x cheaper than the ahrefs or semrush apis (it's real data)
| sevmardi wrote:
| You can also try Bishopi.io APIs which is cheaper than
| dataforseo :)
| umussetu wrote:
| That's cool, could make a good domain-investing app
| morgante wrote:
| Did you make Marblism with Marblism?
| umussetu wrote:
| haha no, the infrastructure we use is a bit intense to be
| entirely managed by an AI but one day maybe :)
| beardyw wrote:
| I've been there and the chicken/egg thing doesn't come for
| free.
| meiraleal wrote:
| This should be the minimum requirement to launch a system like
| that
| bambax wrote:
| > _Find and validate startup ideas:https://www.muckbrass.com/_
|
| The first "startup idea" on that page[0] is... an "AI-Powered
| Startup Idea Generator". I don't know if Singularity is near, but
| we certainly have attained Circularity.
|
| [0] https://imgur.com/a/H3oNUeB
| nicksergeant wrote:
| I hope we can soon teach our robot overlords about web
| accessibility, because this is pretty rough:
| https://i.nick.sg/03510726333f4a2b85daf5dd156d6289.png
| umussetu wrote:
| indeed! our initial focus was to make it work, shouldn't too
| hard to make it score well on accessibility - good point
| ramesh31 wrote:
| >shouldn't too hard to make it score well on accessibility -
| good point
|
| * Laughs in UI Dev *
|
| Accessible components are far from an afterthought. LLM
| generated FE code will never be sufficient without some kind
| of base component library to pull from for things like
| selects, inputs, modals, etc. that are hand built and tested.
| colesantiago wrote:
| Sounds like a great startup idea I am sure someone will
| tackle, thanks!
| candiddevmike wrote:
| What kind of liability do you take on with the code? Can I sue
| you if my app gets hacked?
|
| I can't find anything around ToS or even a privacy policy.
| umussetu wrote:
| good question, it's not a no-code tool - we generate code
| (similar to a cursor or copilot) and we expect people to review
| the generated codebase. We'll add a section on the
| documentation like checklist you need to review to make sure
| there is no security issues. should probably add ToS also yes
| smt88 wrote:
| You can't have a "security checklist" with multiple Turing-
| complete languages involved.
|
| It's better to give up on security and tell the users that
| they're generating code at their own risk.
| candiddevmike wrote:
| It's probably better to have a "for entertainment purposes
| only" banner plastered all over the website since it
| doesn't seem like this startup consulted with lawyers at
| all over this.
| a2128 wrote:
| The autogenerated app in their demo video comes with fake
| reviews and falsely claims you can make lists private when
| they're actually all public. Of course there's also zero
| GDPR/CCPA compliance on the generated app, there is no privacy
| policy (not that an AI could really read your mind about what
| you wanna with user data), no privacy contact and no account
| deletion, just a faceless AI-generated website. Security-wise I
| would place no confidence, it even failed to add a check to
| stop two people from having the same username. Legally this
| should be treated more like a toy for personal entertainment
| than anything
| geor9e wrote:
| There is a joke about YC startups starting as "illegal taxi",
| "illegal hotel" ... It makes sense, since law firms don't
| bother with lawsuits until the target has deep pockets. There
| are a thousand ways a startup can fail, and "got sued" in
| somewhere in that list of worries to focus on, but maybe not
| near the top at first.
| mywittyname wrote:
| You'll find plenty of experienced people in the industry that
| tell you not to worry about the law. Either, the company is
| too small for it to matter, or it is large enough to afford
| lawyers and lobbyists.
|
| Given the acceptability of "saying the quiet part out loud"
| anymore, I'm sure you could find a famous tech guy expressing
| such sentiments.
|
| Though, I'm sure those same people will throw a fit if they
| end up on the losing side of AI generated startups. Imagine
| an AI prompt that replaces and entire Oracle cluster with a
| self-hosted postgres one for a fraction of the cost.
| austin-cheney wrote:
| This is exactly what the market predicted. AI to replace full
| stack developers, and it will overwhelmingly succeed.
|
| There are two reasons why this is predictable with high
| confidence. None of the more accurate predictions rest upon the
| trendiness of AI, but instead are vested in the current
| capabilities of the people primed for replacement and prior
| employment trends.
|
| Reason 1. Most, certainly not all, full stack developers are paid
| far too much for what they deliver. Over the past year I have
| been seeing many interview referrals for just under $200k even
| though I live in a very low cost of living area of the US. I have
| turned all of these down despite currently making far less. The
| high compensation is not enough to make up for working in a team
| that has no hope deliver to expectations (more on that in the
| second point) and is hostile to radical change.
|
| Reason 2. Prior employment trends suggest that many employers
| prioritize hiring and candidate compatibility over ability to
| deliver. Its a valid business decision that makes sense in the
| short term, but results in catastrophic debt over the long term.
| You have to understand that developers are a cost center and not
| sales people. This means they cost money and do not generate
| profit, so it makes sense to lower the costs of acquiring these
| people as much as possible.
|
| Starting about a year or two after I started doing full time
| JavaScript programming in the corporate space employers started
| looking at solutions to turn developers into commodities because
| they were spending too much on hiring with disappointing results.
| I can remember the entire industry trying to do this on both the
| front end and back end, but the movement received far less
| penetration on the back end, which was more entrenched. It
| received overwhelming success on the front end with tool suites
| like prototype.js and YUI before jQuery formed a dominating cult
| of personality. Then once Node got popular and the browsers got
| faster those front end libraries were largely replaced by large
| MVC frameworks like Angular and React.
|
| Before the strong focus on external tool libraries JavaScript
| developers had to do it all themselves. At that time the browsers
| were too slow for things like Photopea, but the first large
| browser apps were already rolling out. These were some really
| excellent developers, but it was really hard to find people who
| could perform at that level, and of course the pay was
| ridiculously low. Moving to these external libraries really
| opened up hiring to people who could not perform otherwise, and
| that really lowered the cost of candidate selection.
| Unfortunately, these external libraries were generally slow and
| sometimes broke when they were just expected to work, but now you
| had an entire work force that could not live without them.
|
| Reliance upon external tools to keep your job creates insecurity.
| It limits the availability of design options to what a given set
| of tools allow, and developer's first priority at work is to
| retain employment. That insecurity grows over time as
| applications grow larger, solution delivery slows, developers get
| further and further more reliant upon solutions in conflict with
| the desires of the business's profit generators. Its why a lot of
| people I have talked to over the past year moved on to other
| things and refuse to go back despite the far higher compensation.
| umussetu wrote:
| although there is a lot of truth in your analysis I think
| developers don't just output code but "think"/solve problems.
| And problem solving is not a common skills , it's interesting
| to see what non-technical people VS developers prompt on
| marblism. Like you would be surprised how many people struggle
| with the concept of an if condition.
|
| So developers are definitely not dead but will be empowered by
| the new tools and maybe their work will shift from solving
| problems+writing code to only solving problems.
| austin-cheney wrote:
| Perhaps, but this isn't about non-developers or developers in
| general. This is targeting "full stack" developers, the
| overwhelming majority of which cannot write original
| software. If a tool provides a business the ability to
| replace a developer that cannot solve problems on their own,
| without some tech stack and colossal framework, it pays for
| itself immediately. That's why it is inevitable.
| jimkoen wrote:
| > the overwhelming majority of which cannot write original
| software
|
| Usually a client or employer does not want write original
| software. I can code in C++/Rust/$LANGUAGE and am able to
| write you a high performance backend for some very
| specific, custom use case, but in 99% of the cases that
| isn't necessary because the underlying business is either
| 1) too generic or small to need something like this or 2)
| doesn't want the hassle of having to maintain something in-
| house.
|
| Most companies that hire typical web/full stack devs value
| speed over anything else for the nth crud app they churn
| out. But I also don't see the value in these companies
| either.
| austin-cheney wrote:
| In my 15 years of doing that work most of the time
| employers couldn't tell if a solution were original or
| not unless it was something they specifically requested.
| Even then most of the original work was in context of
| original content messaging, user interaction, and the
| measurements there of.
|
| Where employers in the past really cared is in the speed
| of delivery. Typically speed of delivery was faster using
| a framework solution only if the exact solution were
| already written and available as an extension. In
| absolutely every other case software originally written
| in house was always faster to deliver back to the
| business. This is because with original software the
| developers are not limited by prior existing conventions.
| It always comes down to the prior experience and
| confidence of a given set of developers.
|
| The business knows this before assigning the tasks to the
| development team, and that awareness (more than anything
| else) determines the opportunities for developers to
| identify their own speed of delivery. Most development
| teams are entirely unaware of just how thoroughly their
| performance is measured from a business perspective. That
| should be painfully obvious, because developers only cost
| money, and those costs go straight to the bottom line.
| pookha wrote:
| I agree with this. Businesses aren't big on spending for
| overhead and that's exactly how software and R&D gets taxed in
| 2024. If you spend 200k on software and only break even you get
| taxed on 200k (meaning you're fucked).
|
| https://leyton.com/us/insights/articles/senate-blocks-tax-re...
|
| This tool may be the solution for businesses struggling with
| 174...Replace developers with calculus and machine learning.
| mjomaa wrote:
| Congratz on the launch!
|
| Like with most boilerplates the focus is too much on the landing
| page, but less on the actual application.
|
| I'd be interested to know if you could integrate my boilerplate
| https://achromatic.dev somehow into the generation to be able to
| generate web apps. Would be absolutely fanstastic - endless
| customizations.
| umussetu wrote:
| thanks! did you log in on your generated app? that's a good
| idea, to integrate various boilerplates
| mjomaa wrote:
| Yeah I tried out Endura with the beneficiary CRUD demo.
|
| What are those generated components based on? Is there a
| component registry?
| umussetu wrote:
| we use ant design at the moment, looking to integrate more
| UI libraries
| TripleChecker wrote:
| Can I use my own existing postgresql database to connect it and
| generate the UI on top of it?
|
| Also, typo on homepage - 'Authentification' (per our error
| report: https://triplechecker.com/s/t2ryxA/marblism.com?v=M0bXQ)
| umussetu wrote:
| not at the moment, but it's a good idea yes it's technically
| possible Fixed! good catch :)
| dangoodmanUT wrote:
| Why do i have to choose between light and dark mode? If you can
| do both, why not support dynamic mode?
| umussetu wrote:
| we could indeed!
| blackhaz wrote:
| Everything looks great. I have tried to generate an app that
| generates stupid faces. At first it produced an app that
| generates what looks like random images - coffee tables, nature,
| people, pens... I have tried fixing it by chatting. It suggested
| to add an AI routine to make sure I'll be getting stupid faces.
| It broke itself and started to produce error messages instead of
| images. I have asked it to fix itself. It has added error
| handling, better error messages, and stupid face generation
| success rate bar to the UI, but I have never been able to
| generate a stupid face. Great idea though, and hopefully some day
| it will work.
| umussetu wrote:
| thanks for trying it out! I guess everything is fine in your
| code and just needed to direct the prompt a bit in the actual
| code (there is a tab 'code editor'). it's a bit what we're
| trying to improve. The AI gets 98% of stuff correctly, but for
| example here it missed to adjust the prompt to output stupid
| face generation - which literally takes 10 seconds to do in the
| code.
| henning wrote:
| Evaluating startup ideas based on search volume reminds me of the
| apocryphal Henry Ford quote about "If I had asked people what
| they wanted, they would have said faster horses". VC-backed
| startups don't succeed by finding an underserved niche and
| generating a nice, steadily growing profit over time. They are by
| their nature supposed to either explosively succeed or rapidly
| die.
| ned_at_codomain wrote:
| This is really cool, guys!
|
| One use case that occurs to me is to build personal SaaS apps.
| It's the sort of thing a lot of people use spreadsheets or Notion
| for.
|
| I just made a simple little app with Marblism to help me keep
| track of whether I took my medication on a given day.
|
| I couldn't tell you why, but I prefer this to little mobile apps
| and it's less upkeep than the spreadsheets I've tried to make in
| the past.
| umussetu wrote:
| thanks! true you could use it like that although I find notion
| and airtable to do a decent jobs if you really just want a todo
| list or a crm so unsure if we should dive into that segment
| Narhem wrote:
| This seems awesome! Anyone else find this to be kind of scary?
|
| The start to Web3.0 AIs making Web 2.0 applications to take over
| the world.
| darepublic wrote:
| Apps like these need to be fast, produce more valid results and
| also support fine grained control. Maybe I'm wrong but I haven't
| met an ai solution that offers all of these yet
| umussetu wrote:
| that's what we are aiming for yep! for now it takes about 10
| min to generate an full stack app which I feel it's still
| decent compared to do it all by yourself
| Narhem wrote:
| I'd love a tool like this to speed up development and I haven't
| used the app but you always have to manually edit things
| afterwards. The difficulty with web apps is getting people to
| use them.
|
| Cool tool, hope it takes off.
| onion2k wrote:
| I'm a huge fan of LLM-based tools, and I use them pretty much
| daily, but stuff like this concerns me a bit. In any dev process
| there needs to be a review step somewhere. Someone who
| understands code well needs to be looking at what the app is
| doing and making sure it's protecting my data. Someone needs to
| make sure there isn't a bug that loses the work I put in to
| creating records with a CRUD operation. They need to be making
| sure my privacy is respected in a legally compliant way. They
| need to make sure things are reasonably secure. None of that is
| guaranteed when you have a dev team, but it is a possibility at
| least.
|
| Telling Joe Random "describe you app in a prompt and press
| deploy!" guarantees that _isn 't_ happening. This sort of service
| is great for non-dev people who want to launch something but it's
| a pretty big threat to my data.
|
| I'm under no illusion that these services are going to be huge,
| and no doubt someone will sell an app built with one to a service
| that puts data about me into it. I _suspect_ that means one day
| an attacker is going to learn something I 'd rather they didn't.
| That sucks.
| space_fountain wrote:
| I wonder how much of this is that LLMs are worse than human
| developers (they are much more error prone right now) and how
| much of this is that we want someone to blame. When the
| elevator operator closes a door on someone fingers that's an
| honest mistake and/or we can fire them, but when the automated
| elevator bruises some 12 year olds finger that's a big problem
| that needs fixed
| curious_cat_163 wrote:
| That's an interesting idea!
|
| I think that the liability will just travel a layer of
| indirection. So in your example, I would think that the
| company that made the elevator would still be liable for any
| harm that their product causes -- if it can be established
| that it is their fault that a 12 year old's finger got
| bruised because of a poor design for the elevator.
| TeMPOraL wrote:
| In general case, won't it eventually hit the liability
| diffusers, i.e. insurance? Kid gets paid from an accident
| insurance, building owner will cover their costs from civil
| liability insurance, and the elevator designers or
| installers will get shielded by professional liability
| insurance.
| jfdjkfdhjds wrote:
| yall nerd spniping the example and missing the point that
| ofered it.
|
| the elevator example, the poster was giving chatbots the
| same excuse for mistakes as a person.
|
| imagine if elevators could just make mistakes and damage
| people, because well, a human would too, never minda that
| its very much trivial to design elevators with sensors in
| the correct place once and then they are accident free!
| this is the ridiculous world ai apologists must rely
| on...
| ofcrpls wrote:
| Disagree partly - once there is monetary alignment to said
| risk - lets say something like the insurance policy of a
| Surgeon, there will be a quick alignment. All this
| indirection is due to lack of actuarial involvement.
| jfdjkfdhjds wrote:
| I take it you never worked at a cheap/local/small software
| shop, usually associated with an advertising agency.
|
| because I would rather those fill-in-the-blank-forced-prompts
| that just add form fields and obviously broken business logic
| to a generic template they curate.
| dartos wrote:
| And the market for these tools suddenly appears before me.
|
| The software world is way bigger than most of us realize.
| bickett wrote:
| I'm most interested how the product can do at iterating and
| making a better product overall. Building a website can be kinda
| hard, but building the *right* website for the market is very
| hard
| codegeek wrote:
| "We create a NextJS app "
|
| Are you considering adding other languages in the future ? I
| would like to try but not with NextJS. I have a special hate for
| JavaScript so I try to avoid it as much as possible except for
| Frontend.
| smt88 wrote:
| TypeScript is one of the few languages (Rust being another)
| that _should_ be a target of LLM-generated code, just because
| the static analysis is so strict you 'd actually catch a lot of
| bugs before runtime.
| maleldil wrote:
| (Strict) Typed Python isn't that bad either, and LLMs seem to
| be quite good at generating that, given how popular Python
| is.
|
| Unfortunately, it tends to generate outdated types (e.g.
| `List` instead of `list`, `Optional[T]` instead of `T |
| None`, import `Iterable` from `typing` instead of
| `collections.abc`), so you always need to tell it to use the
| right one.
| ilrwbwrkhv wrote:
| I tried one and it threw this error:
|
| Error: Element type is invalid: expected a string (for built-in
| components) or a class/function (for composite components) but
| got: undefined. You likely forgot to export your component from
| the file it's defined in, or you might have mixed up default and
| named imports.
|
| The fact that this whole AI fuzzy controlled thing builds on top
| of Javascript fuzzy controlled thing is really messy.
| cryptoz wrote:
| How do you make modifications to code once it is generated? This
| is the most interesting part to me - you say there is a chat
| assistant that can make changes? Does it rewrite the whole file,
| or how does that work? Do you use git diffs?
| colesantiago wrote:
| I am so glad you made this Cyril and Ulric!
|
| Tools that gives the power to allow anyone to become a developer
| or create their own apps without the need to spend $$$ consulting
| with a developer is amazing
|
| I hope we get more startups like yours that lower the barrier to
| entry for tech for everyone and we get quality software at the
| same time.
|
| This is the best and most exciting time to create and build
| startups.
| welder wrote:
| Many competitors in this space, one that comes to mind is
| https://www.rapidpages.com/
___________________________________________________________________
(page generated 2024-09-17 23:00 UTC)