Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Hey, it's the semantic web, but with ~~XML~~, ~~AJAX~~, ~~Blockchain~~, Ai!

Well, it has precisely the problem of the semantic web, it asks the website to declare in a machine readable format what the website does. Now, llms are kinda the tool to interface to everybody using a somewhat different standard, and this doesn't need everybody to hop on the bandwagon, so perhaps this is the time where it is different.



I think there has to be a gradual on-ramp for things to pick up steam. You can't go over the "activation energy" required to set up the semantic markup etc. upfront that would have been needed for the Semantic Web back then (ontologies, RDF, APIs). Instead, AI agents can use all websites to some extent, even before you do any agent-accommodations. But now you can take small steps to make it slightly better, then see that users want it, or it drives your sales or whatever your site does, and so you can take another small step and by the end of it you have an API. Not to mention that AI agents can code up said API faster as well.


There's nothing wrong with XML.


The parent post is a list of failed technologies. Perhaps XML failed for a bad reason, but fail it did. Web MCP will likely fail for the same reasons as the other listed techs.


If you think XML is a failed technology you haven't stepped foot anywhere near a serious enterprise company.


It's a failed technology for websites.


How is it failed? Just compared to, like, the prevalence of HTML?

I've worked in web dev for almost 20 years. Almost every year has had some kind of work with XML.


Client side? i think not. 25 years ago we were told web sites were going to make their data available in nice machine readable XML form which would be transformed by xslt etc into presentation form and available for machine use without the presentation form. Same promise as semantic HTML but earlier, and same promise as webmcp now.


We are using HTML and not XHTML. I have not used XML on websites in over 15 years when HTML5 got stable.


the CNC machine I'm working retrofitting right now has XML definitions for basically the entire thing from GPIO setup to machine size parameters. Kinda crazy but at least it isn't a cursed hex file


By what criterion is XML a "failed technology"?


This is similar to building a React SPA and complaining that Google can't index it.

LLMs will use your website anyway. You're just choosing whether to pay the cost in structured endpoints upfront or hand that cost to browser emulation and lose control of how you're represented.


Are AI smart enough to automatically generate semantics now? Vibe semantics? Or would they be Slop semantics?




Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: