Maybe add something more based as a comparison? MSCI World or similar

do you mean popular shares?

Could also just be a bias in the audience

I what the article proposes is the wrong direction:

Instead of every single person to maintain an offering a vertical slice through the whole stack, we should make it easier to publish content in the first place.

The real issue that this pushes the burden of maintenance and infrastructure on the individual; But this should be a shared responsibility.

Instead we need:

- A federated content/file system - An open standard for viewer/app definitions (hosted on this system)

Ex. Content can be in Git repo. Site can be build via static site generators + automated via CI update site when add new content to Git repo. We only need good blog theme, photo albums theme and profile theme to replace FB, Linkedin even TikTok. Publishers have full control on their own data.

I found the react comments funny: Obviously a huge success but we're still discussing the same criticisms.

curious: what kind of tooling would you use here?

... and luckily, no one cared enough yet to automate the astroturfing

When presented with a choice, I'd prefer to pick something where I know that the sky is the limit in terms of features.

And going with a non-framework approach has the following risk: Of course I might build individual, customized skyscrapers but as soon as I'd like to connect them, I'm in the business of building an ad-hoc framework.

Hmm... I don't know how serious this wants to be taken

- first example argues that syntax is interchangeable

- but then the author tries to sell me his semis

???

And who even cares in the time of LLMs and auto formatting?

"My hammer has this slight angle and if I hit the nail with just the right motion, it feels really good"

I was trying to be EXTREMELY clear I am talking specifically about DECLARATION syntax only and how for the most part, the concrete syntax for the DECLARTAION syntax is not that important in many languages.

However concrete syntax matters a heck of a lot and cannot be trivially interchangeable.

I had to write a follow-up article to clarify this because of people like yourself wrongly interpreting the article: https://www.gingerbill.org/article/2026/02/21/does-syntax-ma...

I think this is a good idea.

The next one would be to also decouple the visual part of a website from the data/interactions: Let the users tell their in-browser agent how to render - or even offer different views on the same data. (And possibly also WHAT to render: So your LLM could work as an in-website adblocker for example; Similar to browser extensions such as a LinkedIn/Facebook feed blocker)

Why would Facebook or LinkedIn ever give you this?

Question: Are you writing this under the assumption that the proposed WebMCP is for navigating websites? If so: It is not. From what I've gathered, this is an alternative to providing an MCP server.

Instead of letting the agent call a server (MCP), the agent downloads javascript and executes it itself (WebMCP).