[HN Gopher] How we rebuilt Next.js with AI in one week
___________________________________________________________________
How we rebuilt Next.js with AI in one week
Author : ghostwriternr
Score : 223 points
Date : 2026-02-24 20:07 UTC (2 hours ago)
(HTM) web link (blog.cloudflare.com)
(TXT) w3m dump (blog.cloudflare.com)
| htch wrote:
| In hindsight, a totally expected achievement given where models
| are and the high quality tests available, but wildly impressive
| all the same.
|
| I don't know what this means but it feels like yet another
| milestone moment.
| verdverm wrote:
| NextJS is bad enough, cannot imagine an Ai version
|
| Cloudflare also lost my support because their support is among
| the worst, rep evn sneered (cannot update my WHOIS, still, after
| months of emails). Strongly recommend avoiding their platform.
| You will find that you lose more time & money to dealing with the
| issue of parity. God help you if you ever need support, almost
| every question in Discord goes unanswered as well.
| slig wrote:
| The former CTO commented a lot here and said numerous times
| about emailing him with issues that support couldn't figure
| out. Maybe try emailing the new CTO?
| switz wrote:
| This is pretty fascinating and comes with some complicated AI-
| world incentives that I've been ruminating on lately. The better
| you document your work, the stronger contracts you define, the
| easier it is for someone to clone your work. I wouldn't be
| surprised if we end up seeing open source commercial work bend
| towards the SQLite model (open core, private tests). There's no
| way Cloudflare could have pulled this off without next's very own
| tests.
|
| Speaking more about the framework itself, the only real
| conclusion I have here is that I feel server components are a
| misunderstood and under-utilized pattern and anyone attempting to
| simplify their DX is a win in my book.
|
| Next is very complex, largely because it has incrementally grown
| and kept somewhat backwards compatible. A framework that starts
| from the current API surface and grows can be more malleable and
| make some tough decisions here at the outset.
|
| Crazy to see it's already being run on a .gov domain[0]. TTFGOV
| as a new adoption metric?
|
| [0] https://www.cio.gov/
| anematode wrote:
| > The better you document your work, the stronger contracts you
| define, the easier it is for someone to clone your work.
|
| Well said; this is my thinking as well. One person or
| organization can do the hard work of testing multiple
| approaches to the API, establishing and revising best
| practices, and developing an ecosystem. Then once things are
| fairly stable and well-understood, another person can just
| yoink it.
|
| I have little empathy for Vercel, and here they're kind of
| being hoist by their own petard of inducing frustration in
| people who don't use their hosting; but I'm concerned about how
| smaller-scale projects (including copyleft ones) will be
| laundered and extinguished.
| falcor84 wrote:
| > There's no way Cloudflare could have pulled this off without
| next's very own tests.
|
| I'm very uncovinced. History showed us very complex systems
| reverse engineered without access to the source code. With
| access to the source code, coupled with the rapid iteration of
| AI, I don't see any real moat here; at best a slight delay.
| anematode wrote:
| Source code is one thing; tests covering the codebase are
| another.
|
| And if you just copy the source code or translate it one-to-
| one into a new language, rather than make a behavioral copy,
| there will be copyright issues.
| root_axis wrote:
| The tests are absolutely essential, otherwise there's no
| signal to guide the LLM towards correct behavior and
| hallucinations accumulate until any hope of forward progress
| collapses.
| rc1 wrote:
| > The whole thing cost about $1,100 in tokens.
|
| I like this is called out.
| jdthedisciple wrote:
| Shots fired, Vercel folks better hide!
| aggregator-ios wrote:
| Surprised this didn't get a higher placement on the HN front
| page, only 34 points?
|
| Absolutely impressive that this was done with $1100 in tokens and
| in 1 week. I agree, and so do a lot of my peers that code has
| quickly become nothing more than a tool to accomplish a task.
| Code never was and never should have been the product in and of
| itself. This is amazing news, and this is exactly where we should
| be as a civilization. The only people that have trouble with this
| development are the gatekeepers who think that code should be
| sacred and revered by itself. That is a perversion of computing,
| and we got the wrong group of people there.
|
| While Vercel continues to be the #1 host for Next.js projects,
| others seem to claim that migrating to their platform is as easy
| as enabling the Github integration. It's not. Cloudflare even
| mentions that you can port your Next project to run on its infra,
| but I couldn't get it to work. Replit markets the same, and yet,
| Next fails to on there too. You have to go through several
| painful hacks and try-build-fail loops and eventually not worth
| it.
|
| You know what took less time and frustration? I asked Claude Code
| with Opus 4.6 to convert the entire Next project to React+Vite.
| And as a shameless plug, I was able to get https://jsonquery.app
| fully up and running and the builds are lightning fast with Vite,
| and worked with just 2-3 tries on Cloudflare pages. If you don't
| need SSR and Next routing, I suggest you do the same.
|
| Oh, and in Next.js land, Turbopack had severe edge cases, that I
| had to revert to Webpack. Esp when dealing with WASM, as JSON
| Query uses the jq dependency brought in as a wasm to run on the
| web. This is not an issue with Vite.
| cpursley wrote:
| Or just skip/migrate off of the Next.js and other JS SSR rats
| nets to Elixir and Phoenix LiveView - Claude and Codex are both
| very good with Elixir now: https://elixirisallyouneed.dev
| cpursley wrote:
| see also: https://dashbit.co/blog/why-elixir-best-language-
| for-ai
| h4ch1 wrote:
| I see this sort of maximalism a lot where people are just
| turned off js and say f it I'll use HTMX or LiveView or
| Alpine or whatever promises that you won't have to write js,
| and that's fine; as long as you're building generic
| dashboards and/or the same repetitive UI patterns. And even
| then you're basically writing JS just in a worse way.
|
| I use Liveview and Elixir for 2-3 home-lab related frontend
| services; but when I have to do something _moderately_
| complicated I have to reach out for a darn js library and
| hooks and phx-commands. Try using native drag and drop or
| even client-side markdown rendering. This also leads to
| memory leaks when you can 't properly detach libraries.
|
| I just say think about your goals; these frameworks/platforms
| that promise to remove JS from your life or minimize it do so
| by sacrificing something. There's no silver bullet for
| building on the web.
|
| But whenever I do talk to people who are debating amongst
| frameworks SvelteKit and SolidStart are the two I recommend,
| it's easy to host anywhere (unlike Next), you can turn off
| SSR, just ship static files with very minor changes
| (exporting a variable in Svelte for ex). They're really
| quick, get the job done, actively being worked on, loads of
| resources, discussions and thriving communities.
| Hamuko wrote:
| > _Surprised this didn 't get a higher placement on the HN
| front page, only 34 points?_
|
| The last time Cloudflare vibe-coded something, it was a
| glorified proof-of-concept with TODOs up the wazoo.
| blibble wrote:
| > Surprised this didn't get a higher placement on the HN front
| page, only 34 points?
|
| looks like HN has finally defeated the cloudflare voting ring
| ojr wrote:
| last time I tried to use nextjs in a cloudflare worker there
| was a lot of issues
| somewhereoutth wrote:
| > Code never was and never should have been the product in and
| of itself
|
| Except that the code completely and precisely defines the
| actual product. Bad code => bad product.
|
| > code should be sacred and revered by itself
|
| As a production of the hand and mind, code _should_ be revered
| - if only as the mark of the human or groups of humans that
| made it.
|
| > the wrong group of people
|
| The group of people who care deeply about the world around
| them.
| bryanrasmussen wrote:
| someone spent over 1000 dollars to replicate the functionality of
| Next.JS, even 1 dollar would seem too much somehow. I suppose
| that is me being overly retributive.
| sailingparrot wrote:
| > it builds production apps up to 4x faster and produces client
| bundles up to 57% smaller.
|
| I suppose that is you being overly retributive indeed.
| thawab wrote:
| Nextjs had remote code execution vulnerabilities because of how
| they implemented react server side. I am not touching an AI
| version without waiting for a while.
| t-writescode wrote:
| Thank you. This is the part that shocks me the most. I was
| always wary of Next.js for this exact reason (in fact, I
| refused to use it for personal projects before the RCE because
| I was scared that _I_ would make a mistake and leak server-side
| data to the client.
|
| Bugs like this are easy to happen and even easier to miss if
| you're generating thousands of lines of code with AI.
| vercantez wrote:
| Great to see. Could have use this last month when we migrated
| from OpenNext on CF to React Router 7
| troupo wrote:
| Here's what is buried a bit in the text:
|
| --- start quote ---
|
| Something like 95% of vinext is pure Vite. The routing, the
| module shims, the SSR pipeline, the RSC integration: none of it
| is Cloudflare-specific.
|
| --- end quote ---
|
| The real achievement is human-built Vite (and it is an amazing
| project).
|
| Since Next.js's API surface and capabilities are known, this is
| actually quite a good use of AI: re-implement some functionality
| using a different framework/language/approach. They work rather
| well with that.
| acedTrex wrote:
| God cloudflare's blog quality has fallen off a fuckin cliff ehh.
| Used to be so good now its just llm slop both content and actual
| writing.
| spzb wrote:
| The core network products seem to be having a run of downtime
| issues too. Maybe they should focus on their homework before
| going out to play with the AI kids.
| bbkane wrote:
| This is interesting to my on both a technical level as well as
| a social-political level. I wonder what impact "AI-washing"
| will have on licensing for example
| thefilmore wrote:
| Yup. This was so jarring to read. Shame.
| hungryhobbit wrote:
| Man, I love Next ... but I also love Vite ... and I _hate_ the
| Next team, because they focus on fancy new features for 0.1% of
| their users, at the complete expense of the other 99.9% of the
| Next community (who they basically ignore).
|
| This gives someone like me everything we want. Better performance
| is something the Next community has been begging for for years:
| the Next team ignored them, but not the Cloudflare team.
| Meanwhile Vite is a better core layer than the garbage the Next
| people use, but you still get the full Next functionality.
|
| I wish Cloudflare the best of luck with this fork: I hope it
| succeeds and gets proven so I can use it at my company!
| 3rodents wrote:
| What is it you love about Next that isn't tied to Vercel and
| isn't available elsewhere? I love Next too but I find the value
| is inextricably linked to Vercel. I can't imagine choosing to
| use Next if I'm not choosing it for Vercel's fancy stuff.
| thousand_nights wrote:
| at my job we have some 7+ year old nextjs apps that don't
| receive new features but still do their jobs perfectly fine,
| and they keep changing random shit around for no reason, we've
| had to waste time on multiple refactors already for major
| nextjs version bumps once the older ones are no longer
| supported
| himata4113 wrote:
| I mean you don't want really want to use javascript for the
| backend anyway... What's the problem with just using vite and
| any backend of your choosing?
| qudat wrote:
| Next is the worst framework I've ever used next to rails. It's
| pure overhead for most apps.
| keeganpoppen wrote:
| i love how this disintermediates the next.js/vercel axis, which
| seems to be determined to make basically everything hard except
| for exactly what they want to do. as much as i love what vercel
| has done for open source in general (amazing stuff!) it is hard
| to interpret some of the stuff they do with next as anything
| other than vendor lock-in bs... the kind that i know is not in
| their hearts.
| evilhackerdude wrote:
| > The [next.js] developer experience is top-notch.
|
| let me add my own unqualified statement to that: no.
|
| > Next.js has invested heavily in Turbopack but if you want to
| deploy it to Cloudflare, Netlify, or AWS Lambda, you have to take
| that build output and reshape it into something the target
| platform can actually run.
|
| it's almost as if vercel had some kind of financial incentive to
| gear this towards their own platform.
|
| > reimplemented the Next.js API surface on Vite directly
|
| a clown car screeches to a halt; several burnt-out-bored oracle
| vs google lawyers climb out and, weirdly, i am there for it
|
| all in all, it's definitely a good example of something we
| couldn't have done for $1100 pre-llms, but: should we have? did
| somebody consult the lava lamps?
| jtbaker wrote:
| All my homies hate Next.js
| 2001zhaozhao wrote:
| This is another example that good tests (e.g. Next.js's own test
| suite) are SO incredibly important to making the AI able to work
| on big projects autonomously with lower steering. So is a very
| domain-knowledgeable human in charge of steering.
| ratorx wrote:
| I find it interesting that they _bought_ Astro
| (https://blog.cloudflare.com/astro-joins-cloudflare/), which from
| my definitely-not-a-frontend-person perspective seems to tackle a
| similar problem to Next. A month ago.
|
| If it is so cheap to make something that they recommend using
| (rather than a proof of concept), why buy Astro (presumably it
| was more expensive than the token cost of this clone?).
|
| One conclusion is that, at the organisational level, it still
| makes sense to hire the "vision" behind the framework, rather
| than just clone it. Alternatively, maybe AI has improved that
| much in 1 month!
| bastardoperator wrote:
| I think they just want steer users/developers to CF products,
| maybe not? It is interesting to see the two platforms. I've
| moved to svelte, never been a frontend person either but kind
| of enjoying it actually.
| 3rodents wrote:
| Astro is a different paradigm. Acquiring Astro gives Cloudflare
| influence over a very valuable class of website, in the same
| way Vercel has over a different class from their ownership of
| Next.js. Astro is a much better fit for Cloudflare. Next.js is
| very popular and god awful to run outside of Vercel, Cloudflare
| aren't creating a better next.js, they're just trying to make
| it so their customers can move Next.js websites from Vercel to
| Cloudflare. Realistically, anyone moving their next.js site to
| Cloudflare is going to end up migrating to Astro eventually.
| thierrydamiba wrote:
| Can you talk more about this? What's wrong with cloudflare
| pages plus Nextjs? Why do you need Astro?
|
| Thanks
| phpnode wrote:
| The acquisition is just a different play - they get access to
| the Astro user base and can steer the future direction of the
| framework. This move here is all about nerfing a direct
| competitors main advantage (to all of our benefit)
| satvikpendem wrote:
| > _which from my definitely-not-a-frontend-person perspective
| seems to tackle a similar problem to Next._
|
| It does not. Astro is more for static sites not dynamic web
| apps.
| pier25 wrote:
| That used to be the case 3-4 years ago. Today Astro is very
| much a serious contender for dynamic web apps.
| satvikpendem wrote:
| I tried it about 6 months ago for something I had to redo
| in NextJS afterwards, it is really not built for those
| sorts of web apps, even today.
| pier25 wrote:
| Unlike Astro, this looks more like a low effort experiment
| while making fun of a competitor than a project intended for
| any serious production use.
|
| Maybe I'm wrong. We'll see what happens a couple of years from
| now.
| selridge wrote:
| You buy that concern to hire the people. The stack is already
| free.
| input_sh wrote:
| Astro has "server islands" which rely on a backend server
| running somewhere. If 90% of the page is static but you need
| _some_ interactivity for the remaining 10%, then Astro is a
| good fit, as that 's what makes it different than other purely
| static site generators. Unlike Next.js, it's also not tied to
| React but framework-agnostic.
|
| Anyways, that's why it's a good fit for Cloudflare: that
| backend needs to be run somewhere and Astro is big enough to
| have some sort of a userbase behind them that Cloudflare can
| advertise its service to. Think of it more as a targeted ad
| than a real acquisition because they're super interested in the
| technology behind it. If that were the case, they could've just
| forked it instead of acquiring it.
|
| From Astro's perspective, they're (presumably) getting more
| money than they ever did working on a completely open source
| tool with zero paywalls, so it's a win-win for both sides that
| Cloudflare couldn't get from their vibe-coded project nobody's
| using at the moment.
| carverauto wrote:
| good job, now you have to support that mess that took 3774~
| contributors to build.
|
| have fun.
| kundi wrote:
| Next-js team is a bunch of inexperienced teens who like good
| looking UIs and their lousy platform to upsell their services.
| Very glad to see this
| eaf7e281 wrote:
| again?
| redwood wrote:
| I would not want to be working on Cloudflare's Vercel partner
| team about now.. talking about a diplomacy-forward role
___________________________________________________________________
(page generated 2026-02-24 23:00 UTC)