Sites in ChatGPT
chatgpt.com100 points by polvi 21 hours ago
100 points by polvi 21 hours ago
I have been using Sites a few months now, really underrated feature IMO. Any time I get a quick app idea I just hand it off to Sites and usually get a working prototype within the hour.
For example, here's a game where you are a mouse hunting for cheese in higher dimensional mazes: https://manifold-six-axis-escape.nathan338932.chatgpt.site/
Idea came to me while at a concert, was ready to play that same night.
Really cool idea! Beat level 6! I'm still not sure how to explain how it is showing more than 3 dimensions on a 2D screen though! Would be nice to be able to choose which dimensions are represented at the various N-dimensions, but the UI might be tricky to get nice.
Yeah you have actually picked up on something that the game intentionally does to help the user: If the cheese can be reached by any of the dimensions you are currently on, then it will ensure that dimension is in the subset of dimensions you receive when you go down a dimension.
Otherwise I'd have to introduce some kind of dimension picker. Maybe a fun hardmode.
I made it through the 6th puzzle, it was a lot of fun. I basically just stayed in 3 dimensions until I had to move up and then went back to 3.
Yeah I think moving up and down dimensions is the best strategy. I find spamming movements in 6D works but only because the paths are dense enough.
Wow that game makes my head hurt. Cool idea!
Thanks! Yeah I find it helps to jump back down to lower (comprehensible) dimensions, move closer at that level, then jump back up.
pretty fun! beat level 6 after about 4 minutes... should add some more levels :)
Yeah if I were to make it harder I would introduce more sparse connections requiring the user to actually understand the layout, right now you can kind of "feel" your way towards the exist. Most brutal maze would be one with only one possible path and lots of backtracking required.
Maybe I'll do that and post to HN later, didn't expect this much response!
I wonder if they'll combine this with the currently-in-closed-beta Sign In with ChatGPT to let people make sites that can make inference calls that get charged to the user's ChatGPT subscription rather than the site owner's API billing account, like Claude Artifacts already lets you do. That would synergize well with ChatGPT Sites being generally more robust and feature-complete than Claude Artifacts.
This is probably going to be hugely successful with the majority of the population.
It's a matter of weeks/months before they'll host a complete webapp, not just a site. The Saaspocalypse will be complete.
On one hand, I am incredibly tired of seeing the absolute train wreck of waste that is suave founders taking millions and blowing it on hundreds of personnel who do practically nothing— especially having seen what a single person can do with these tools.
On the other hand, death of a livelihood in a social structure that doesn’t care about you.
We’ve always had pump-and-dump trash. The terrible stuff loses and the good stuff wins. I don’t see why that would change.
The companies that ditch the management structures of yore and successfully build better software faster with the new tools will come out on top. I don’t think these companies will replace ALL saas subscriptions with in-house solutions, because one huge benefit of paying someone else to hold that bag is liability and regulatory overhead.
Honest question for devs out there... is anyone worried? I don't see enough frank conversation happening around this subject. Timelines. How long until salaries fall? Is it too early to stalk thinking about back up plans? Am I crazy?
Coding is probably solved. Honestly it’s probably going to be 5 years of runtime starting now depending on industry lag and uptake.
A team I was managing spent a whole year converting government forms into a web app. It took a while and there was a lot of discussion with the end users and a bunch of back and forth (keep in mind this is government software with a lot of onerous legal requirements). Then about 4 months ago, we just fed Codex the forms, along with the UI design and the legal requirements and it spat it out in 1 hour. Was it perfect? No. But our iterative loop became make the web app, show it to end users and then incorporate feedback and completely cut out the UX team, product etc. We were able to complete the conversion in 2 weeks with one guy (something like 150+ government forms/applications). For most simple to medium corporate development work it’s basically over.
We're in a similar boat. Entire eng team went full AI about a year ago, and honestly we're struggling to find things to do. Features that would take weeks, take minutes.
I just don't see how we keep going like this without layoffs. The company cannot responsibly continue paying for this many engineers, when half, or less, could do the same job.
You'll need less people but not no people.
Yeah, probably 10% of our current workforce is all that’s needed.
You could argue this was true prior to AI. A lot of the workforce is doing questionable value bureaucracy
I think this has always been the end result - when the user can enter a business problem and it spins up a site, and they don't have to think about the hosting, database, app, etc.
Vibe coding full circle
And it will be good enough for 90% of use cases.
And whose neck can you choke when an error from the AI generated site forces you to refund customers or something worse?
Its not for those uses cases. though. THink about squarespace/wix hosting all the company landing pages, restaurant menus, daycares. This will replace it.
given the percentage of business processes that still run on a manually updated spreadsheet, I am not sure that is actually worse.
It is likely better in some ways and worse in others...and few of hte people involved will have the understanding to tell the difference.
I don't think this provides a lot of value for more complex applications. It just lowers the bar for getting started.
Once the app gets a bit more complex, it won't be that much different to any more traditionally vibe coded application (code, git/pr, test, deploy, ops). It only removes the barrier to get started, but doesn't solve any of the real problems. Problems like AI slop, code rot, bad architecture, security issues, data loss/breach because of bad code, and so on.
The Saaspocalypse was a wet fart that never went anywhere. People aren't using these AI tools to kill or replace SaaS at their jobs as much as HN wants us to believe.
https://www.stripeeconomics.com/p/the-saaspocalypse-was-more...
The argument there wasn't that everyone everywhere would use individually customized software* instead of packaged SaaS; it was that, because AI greatly reduces the cost of building an internal app or service, it improves enterprises' BATNA when dealing with SaaS vendors, which means surplus will shift from producers to consumers. It's not obvious to me that that's not happening, since it may have been masked by a general increase in automation since AI also synergizes significantly with SaaS. (The Stripe Economics post gets into this a little, though it's mostly less curious than I'd like about why the "SaaSpocalypse" didn't materialize. Of course, Stripe has an economic interest here.)
* Some people do think this (e.g., https://sockpuppet.org/blog/2026/09/25/what-even-is-an-os-no...), but I remain somewhat skeptical that this'll be true for the most economically significant applications. This is not because I'm an AI capabilities skeptic (I'm not, I'm more of a doomer), but because even in a world where AI is designing and implementing all the software, there are probably still significant benefits to standardization. I see it as sort of analogous to compilers; we might get a world where compilers are both used and maintained almost exclusively by LLMs, but we probably won't get one where compilers stop being used or maintained at all because LLMs write everything in assembly.
I mean, with a Cloudflare API key you can pretty much already do that. But keeping your data straight and putting in the right authentication guards, etc. are all still where the business problems meet technical and the AI is not enough unless the agent is both architect and customer.
Except for the companies that pay anti-competition money to OpenAI: cloning their applications will be restricted.
Yeah, I'm seeing how I can move my dad's website to this so he can manage his site on his own.
They'd better be proactive with checking for abusive users, because I can easily see people trying to spin up honeypots, crypto miners, scam sites, etc. on this. Especially given that the hosting appears to be free with undefined CPU/RAM limits.
Looks good. Like most ChatGPT things, though, it will probably take good prompting and iteration, to ensure that the sites have individuality.
Still, I suspect a lot of independent Web developers are sweating. It was already getting tough, but this is a coffin nail.
This seems to close a gap that both Claude and chatgpt had.
If you ask something like "please make a little website for me and my friends to plan our shopping lists on", I would expect the result to be:
"Here you go: https://shopping-lister.chatgpt.com/"
Unfortunately right now most AI models get into the weeds of asking the user to sign up to netlify or firebase or buying a domain etc - none of which most users are interested in doing.
i love sites
i make it for anything, i made one as a food guide for the UW chow down https://uw-chow-down-2026.corruptbytes.chatgpt.site/
Gonna wager good money they attempt to relaunch Apps or something of the sort, where you build, launch, host within ChatGpt, seamlessly making it easier really soon.
Then the app economy gets going within ChatGPT
I’m getting dejavu. Is this the 2026 version of Yahoo GeoCities
I love the concept, but the `.chatgpt.site` suffix reflexively makes me think of those early-2000s era sites.
Looks very useful.
I’ve been using exe.dev to throw up micro sites. It has a built in web agent and first party mobile app agent. And any coding agent that can use “ssh” (all of them) can easily figure out how to drive it.
It also has a lot more developer and PaaS tools like GitHub integration.
RIP Heroku for imploding before the wave of vibe coding. We had the ability to “spin up a free app on the internet” before it was cool.
I'd like to have one of this but where the content is dynamically updated by a 'cloud' agent on schedule, is this feasible today?
My fun little project has been Sherlocked! https://weejur.com
For whatever reason most of the sites are Arabic-language prototypes for things like plumbing companies. I'm not sure why - if those are solving a real problem, or whether someone is running a scam, or what.
Very nice. I really like the design.
I got tired of spinning up repos for basic pages, so made my own host last year - https://pageplane.app.
I think the SEO/AEO agencies are using them to seed content for clients.
Looks like a jab at Lovable.
Wonder what domain they're going to pick next. I feel like many LLM-dependent businesses are going to get sherlocked by OpenAI and Anthropic.
honest question what is the sherlock proof business/app/saas we can do as independent builders
hard out here hard for startups too
something that solves a real problem for businesses, that you are uniquely positioned to execute on well. If you target the lowest common denominator, or consumers, or build something really quickly - good luck
We’ve been building something like this, but perhaps even more powerful, safe, and beginner friendly. If Sites looks like it’s the right speed for you, we’d love your feedback on https://vibes.diy/
I've been using this for probably six weeks. It just popped up as an option one day in Codex.
hows your experience been?
I've found it to be very helpful. A fairly painless approach for hosting a quick prototype.
My guess is Google and Apple are going to eventually take all the market share for this "app builder" category. They own the device market-share and can offer way better integration
If Apple doesn't up its AI game soon, their entire ecosystem will be rebuilt by AI.
Probably the most underwhelming feature of Chatgpt. I dont know why its so slow and overall terrible as compared to Claude artifacts
Is there anything similar that's open source and self hosted and can be hooked into any agent via MCP?
I know that Vercel or something similar is quite close to that, but it's not that well integrated into MCP/Skills.
Funny how the showcased "Tidal house" has unreadable text on an image.
https://tidal-house-retreat.openai.chatgpt.site/
> Quiet cabins. A view of your own.
Does anyone know if Claude makes it easy to publish sites u vibe coded to a custom subdomain or new domain? That’s the biggest reason I use this feature in ChatGPT over Claude
Pretty sure if you give Claude your AWS keys, it will easily deploy the stock CloudFront setup in minutes. But that's not as seamless.
Sadly while the example: https://below-the-surface-ocean.openai.chatgpt.site can be detected as SLOP on the first contact of photon with the retina, I honestly cannot detect https://frame-studio-motion.openai.chatgpt.site and it is giving me depression. The website is basic, but it doesn't feel slop. And I guess that is something.
I'm genuinely sad that what we learned with hard work and sweat, our craft, our identity, our soul; is now something you can buy. I've been in this profession for a long time and now I see people who have absolutely no fucking clue, but lots of money, and they buy all these agents and make things that work (way more broken, with absolutely shit quality), but they work and so they brag about their creations to me all day long, and man that makes me feel like a total loser.
I spent decades trying to master media theory, language design, computer graphics, compiler design, rewriting systems, mathematics, logic, build systems, graphs, data-flow systems, making GUI kits, layout systems, ... all to make a better system for thinking, and now the whole idea of thinking is outsourced (as altman says "sold as utility by the meter"). I need to become an addict or something and be wasted. This is not a life.
> I honestly cannot detect https://frame-studio-motion.openai.chatgpt.site and it is giving me depression. The website is basic, but it doesn't feel slop. And I guess that is something.
Are we looking at the same website? My eyes immediately go to the font and typeface styling and it registers immediately as AI generated. There’s a very distinct “AI” website aura that Claude and ChatGPT make that requires you to change a ton of the styling to make go away.
Yeah OP comment is really, really weird. It sounds as slop as the links shared.
uBlock needs a slop filter post haste.
And I wish there was a SponsorBlock type, crowdsourced slop filter for Youtube.
Add WYSIWYG site builders to the list of businesses on the chopping block.
If you're wondering why OpenAI's models seem to be struggling to stay ahead of Anthropic and are falling further behind, I think it's because of side quests like this.
They have dots, they had Sora, so many other things that take away attention from just having the best model. There are already a bazillion ways to do this. Sure, the integration's nice, but it's just not needed.
> There are already a bazillion ways to do this.
Which means non-technical ChatGPT users are a bit bewildered as to how to pick.
This makes that easy; I suspect normies will fucking love it. My boss will.
Weird to describe something they could really easily sell to non-coders as a "side quest".
I think programmers make the mistake of thinking generative AI is for us, when it is much more ominously about us.
Newsflash: a company that plans to be the most valuable business on earth and has a desperate need for revenue is not going to stay out of anyone’s lane if there is money to be found in it. If you can make an AI wrapper, so can they.
This actually looks like it has meaningful potential, and given how easily they could train it to connect to a whole bunch of off-the-shelf APIs running in data centres they control, looks like a little glimpse of the future, and of the kind of power the industry has gleefully handed to the crypto-for-your-eyeball-scans guy.
Cloud AI has been the face-eating leopard of the tech industry for the last three years. This is them just starting to chew. How long before they tweak it to generate intranet apps, mini stores, specific AI wrappers? Why wouldn’t a firm that has so much influence over data centre rollout, RAM and processor prices simply directly start using their code generation tools and data centres to build and run the work product?
Maybe some of the big firms who have been helping train ChatGPT to eat their lunch will now wake up to the need for open weights.
I think at this point assessments like this are more qualitative than quantitative. I use Codex far more than I use Claude for coding and my results are generally higher quality. I would not, however, go to someone and tell them that Codex is better than Claude generally. In large part it depends on how you use the model and the harness.
All of these "side quests" (and especially this one) are attempts to build a walled-garden.
Especially this. OpenAI will host it. OpenAI will throw "Sign in with ChatGPT" there. "Apps" will be built that depend on end users ChatGPT "connections". The app will fundamentally not work without an end-user having a ChatGPT account/subscription and "connected apps".
Having "the best model" will absolutely not support a $1T+ valuation. Owning the activity of 25-50% of internet users (assuming a split between OAI/Anthropic/Google/maybe-Meta), is.
OpenAI is trying to build a business to justify their valuation, while they pursue ASI at the same time.
Anthropic is just trying to get to ASI and relying on the blind faith of investors that there will be a return at the end.
What matters is which strategy is more effective for attracting investor capital, because neither can survive without it.
This take sounds like engineering not "getting" what product even does. OpenAI has a company to run and a business to build.
The frontier companies are scrutinized heavily for their trillion dollar valuations all without a clear mass-consumer use-case. They're trying stuff.
It’s pretty obvious that they are trying to lock in consumers.
They are trying to build an ecosystem that can capture the value of AI, whereas LLMs are quickly becoming a commodity.
Where is the moat? How can they convert users?
If you were sitting on a rocket burning cash to not crash you would do that too.
OpenAI has an enormous team working on Codex. The folks who train models are different people.
Is it surprising? Most devs at my company (2k+ employees) are using Oppus and casually burning millions token a day.
OpenAI models are not falling behind Anthropic. They just have different strengths.
I’d be firing my entire marketing team if this is all they came up with.
Been using it for a while. Very good experience so far. Maybe even better than claude or replit
Is this better than Claude? Probably not, right?
I haven't used ChatGPT in over a month. I bounce between Grok, Gemini & Claude. Is ChatGPT even worth it.
Grok can do things the other two can't, like read and fetch websites sometimes where Claude and Gemini cannot.
Gemini is just someone to feed javascript to when you want to save on Claude tokens.
It's worth for the token budget. You can do so much with gpt-6.1-sol (high) on a small sub. If the money is not aan issue it's probably still worth it for Astra because it can occasionally be smarter than Fable 5.1 (or so I heard).
This is my impression as well; ChatGPT/Codex is very affordable for what you get.
If you want a solution that works with any model/harness, try ht-ml.app!
wow there goes lovable's moat
rip base 44 /wix
geocities vibes?
Could you just be an API to serve intelligence instead of moving into the app layer and putting your clients out of business. How much wealth and power do you need to accumulate seriously?
The "intelligence API" layer seems like a pretty rough business to be in. The smarter the models the more they're commodities (since they can use any harness or scaffolding) resulting in a race to the bottom on pricing. And then each new better model requires double the cost of the previous one.
I'm surprised there's not a bigger push into better and useful memory, since that would result in actual lock-in.
The question of them moving into the app layer is completely irrelevant. If you are threatened by this the reality you need to begin making peace with is that your business is not going to exist within 10 years. And that's being extremely generous.
I hope you support UBI.
This was always the play… Wait until the models are trained to work on “capsules of your data” stored by OpenAI, and deploy your apps/services onto OpenAI cloud where you can _easily_ share the development with your team members’ AI agents. Ofcourse, they will all work only if you use and pay for their models via their subscriptions. A new global {K-V, Relational, Vector} database that your coding model is already trained to work with! will come very soon…
They know the API price wars are a race to the bottom with little/no profit margins.
I think this is going to back fire. I have talked to 5 tech leaders at companies and universities this week about setting up their own infrastructure for inference and training. They are worried about multiple rug pulls: increasing cost of tokens, stealing ideas, training on data etc. they are all willing to uses less intelligence models if they avoid these issues. They’ve seen me setting up propelcompute.com for my start up and propelcode.app neither of which are intended to be commercial products and want to do the same.
Don't worry, we had DreamWeaver, Wordpress and other tools for a long time now but it still did not replace web developers. Build quality tailor made websites that connect to humans and you will be fine.
DreamWeaver and WordPress both had limits on the complexity of site they could build. If you wanted more than what they can do, you look to web developers.
That limitation doesn't exist with ChatGPT
The limitation actually is: your fantasy and knowledge how the thing you want actually should work.
[flagged]
[flagged]