Live data from Hacker News

WebMCP is available for early preview

developer.chrome.com

221–226 of 226 posts

Re: WebMCP is available for early preview

#221

Earlier quoted context omitted.

The website is the API though. HTML is one of the few RESTful systems people still use today, build semantics into the page and humans and LLMs can understand how to use it. A11y specs and APIs are just a way of presenting those semantics differently, often for those who can't see the page, whether visually impaired or in this case an LLM. At least in my view, we should expect anything claimed to be artificial intell…

I think you are confusing two things. - the semantics of a form and a button and the resulting http POST/GET - and what the page actually does! So I can have two pages - both with html forms - what they actually do on submission might be completely different - one buys a potted plant the other submits a tax return. ie the meaning of the action is in the non-semantic elements - the free text, the images, the context.…

A human needs to be able to distinguish the buttons though, both visually and via accessibility tools.

I would hope those two buttons and forms include labels, description text, indicators for required fields, etc. All of that should live in the HTML and includes attributes as needed for a11y. LLMs can use that, they don't need yet another API to describe it.

Re: WebMCP is available for early preview

#222
The last days I built the WebMCP plugin for the RxDB database [1]

The goal is to let agents interact with apps through explicit tools instead of DOM scraping or visual navigation. This works nicely because agents can run operations directly on the local-first data the UI already uses.

[1] https://rxdb.info/webmcp.html

Re: WebMCP is available for early preview

#223

Earlier quoted context omitted.

> But kindly don't waste everyone's time by commenting with your irregard & wasting all of our time. Don't tell people not to disagree with you. The "marketplace of ideas" you celebrate here is full of disagreement. If you disagree with people, just make the best substantive argument you can. Don't characterize your fellow participants. Criticize the idea, not the person. And expect to lose your fair share of argumen…

I LOVE DISAGREEMENT. But I expect some actual engagement, & willingness to explore the topic. I maintain that you have avoided engagement, and blanketly worked to shut down thought and discussion, rather than explore ideas. > If you disagree with people, just make the best substantive argument you can. I've done just that, raising and supporting my points and responding to your arguments. But you ignore the previous…

> > Don't characterize your fellow participants. Criticize the idea, not the person.

> You deserve criticism for the way you have misdirected away from exploration or consideration, in a non-engaged fashion. It has been a mis-service to the topic, and a mis-service to everyone else's time.

Attempting to "double down" was the wrong move.

I think we've reached the end of this "discussion."

Re: WebMCP is available for early preview

#224

Earlier quoted context omitted.

I think you are confusing two things. - the semantics of a form and a button and the resulting http POST/GET - and what the page actually does! So I can have two pages - both with html forms - what they actually do on submission might be completely different - one buys a potted plant the other submits a tax return. ie the meaning of the action is in the non-semantic elements - the free text, the images, the context.…

A human needs to be able to distinguish the buttons though, both visually and via accessibility tools. I would hope those two buttons and forms include labels, description text, indicators for required fields, etc. All of that should live in the HTML and includes attributes as needed for a11y. LLMs can use that, they don't need yet another API to describe it.

> they don't need yet another API to describe it.

WebMCP isn't accessibility support for humans, it's accessibility support for agents, which despite all the hype, are less capable than humans in working out what's going on, and find functions and data schema's easier to understand than a web page designed for human ( whether that's a partially sighted human or not ).

Re: WebMCP is available for early preview

#225

Earlier quoted context omitted.

I LOVE DISAGREEMENT. But I expect some actual engagement, & willingness to explore the topic. I maintain that you have avoided engagement, and blanketly worked to shut down thought and discussion, rather than explore ideas. > If you disagree with people, just make the best substantive argument you can. I've done just that, raising and supporting my points and responding to your arguments. But you ignore the previous…

> > Don't characterize your fellow participants. Criticize the idea, not the person. > You deserve criticism for the way you have misdirected away from exploration or consideration, in a non-engaged fashion. It has been a mis-service to the topic, and a mis-service to everyone else's time. Attempting to "double down" was the wrong move. I think we've reached the end of this "discussion."

I didn't insult you, I insulted your arguing. You haven't provided anything worthwhile and haven't responded to my points, and have generally not made any "right" moves. That's a pretty key difference! My opinion is slipping for sure but I have kept that to myself!!

You just don't like my characterizations. And normally I do want to take a higher path! This brings me no joy to use this form. But you haven't given me any grounds to respond on, you never address my points or show that you are at all capable of hearing anything I am saying, so I have to argue and characterize something else instead. Your form is bad, would lose you even the most basic high school debate. I have to work around your distracting words to return us to some relevant point again and again and again.

That's the Brandolini's Law problem. That's the hacker spirit being attacked, that's possibility picked apart by close minded arguments and over-awe-ing projections of negativity and refusal. That's chance, denied.

That's why I keep engaging. We cannot deny all hope, let it be smothered like this. Especially not by such mal-engagement.

I'm surprised a lawyer like you would be so unable to tell such a basic difference between characterizing you vs characterizing your form. And would insist on acting so so sorry for themselves. But you've acted mostly in bad faith so far & haven't actually engaged in discussion, so it fits the pattern.

Agreed that this "discussion" ended, but it ended a long time ago imo. Bad faith engagement from you throughout, this was trash. I caution readers again that what you have to say distracts & takes away rather than helps them think about this all.

Re: WebMCP is available for early preview

#226

Earlier quoted context omitted.

> for WebMCP you have to expose and maintain internal APIs per page Perhaps. I think an API for the session is probably the root concern. Page specific is nice to have. You say it like it's a bad thing. But ideally this also brings clarity & purpose to your own API design too! Ideally there is conjunct purpose! And perhaps shared mechanism! > This opens the site up to abuse/scraping/etc. In general it bothers me that…

> You say it like it's a bad thing. But ideally this also brings clarity & purpose to your own API design too! Ideally there is conjunct purpose! And perhaps shared mechanism! I update my website multiple times a day. I want to have as much decoupling as possible. Everytime I update internal API, I dont want to think of having to also update this WebMCP config. Basically I have to put in work setting up WebMCP, so th…

If you have a nice core architecture, you can just have WebMCP expose the core directly. Folks using GraphQL or some rpc system might be able to have an always in sync system automatically.

> so that Google can have a better agent that disintermediates my site.

This isn't disintermediated by or for Google.

The beneficiary here is the user, who gets to do what they want with their agent directly. I realize the idea of users doing what they want makes a lot of site owners nervous and scared, but RFC8890, the internet is for end users: site's attempts to coral and control users is interpreted as damage and routed around. This is a moral and ethical specification that actually helps users do what they want to do. Without Google or perhaps 3rd party scraping bots having to be involved.

> A lot of sites already expose chatbots,

Which very often are pretty dumb menu trees. Or sometimes have some data services or capabilities they can access. But is a crappy ultra-slim model going to make your users happy? Are they going to get what they want from this chatbot? Is it going to help them do what they want? Is it going to work with their calendering app or their email app, to get the job done? I think what you are saying is once again: fuck the user, take my crappy bad experience that sucks, and deal with it. No one likes chatbots. They like their agents.

> its trivial to rate limit and captcha on abuse detection

What if the user is there, but asks computationally complex questions? There's so so many examples of prompt hijacking, of break outs, of ways to fool AIs. Turns out that if you add some punct.uation or spa ces in words, prompt injection attacks tend to be far more effective. That's just one of thousands of things we've found for attacking LLMs.

The idea that you can just rate limit and captcha your way out of users using an agent you are hosting has to be a joke, right?

Nothing about anything you've said makes me think you have any respect or desire to let users have a good experience.

Post reply on HN