Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Why XML tags are so fundamental to Claude

glthr.com

Post reply on HN
Print view View original

131–140 of 160 posts

Re: Why XML tags are so fundamental to Claude

#131

Post by toastal »

RadiozRadioz wrote: post #39

> a contrast between Claude’s modern approach [...] XML, a technology dating back to 1998 Are we really at the point where some people see XML as a spooky old technology? The phrasing dotted around this article makes me feel that way. I find this quite strange.

XML works great for XMPP. KDL is compatible with it too.

What gets me is going from this structured data to Markdown which doesn’t even have enough features & syntax that the LLMs try to invent or co-opt things like the blockquote for not quoting sources.

Re: Why XML tags are so fundamental to Claude

#132

Post by miki123211 »

rhdunn wrote: post #71
coldtea wrote: post #44

Earlier quoted context omitted.

XML has been "spooky old technology" for over a decade now. It's heyday was something like 2002. Nobody dares advertise the XML capabilities of their product (which back then everybody did), nobody considers it either hot new thing (like back then) or mature - just obsolete enterprise shit. It's about as popular now as J2EE, except to people that think "10 years ago" means 1999.

XML is used a lot in standards and publishing industries -- JATS, EPUB, ODF, DOCX/XLSX/..., DocBook, etc. are all XML based/use XML.

And I think this makes sense.

XML is really great for text documents with embeds and markup, either semantic (this part of the paper is an abstract) or visual (this part of the document should be 14-point and aligned right). You can do this in JSON, but it's a pain.

JSON is great for representing data. If you have some data structures and two machines trying to exchange them, JSON is great for that.

TOML / yaml / hcl / JSON with comments are great at config. If you have a human writing something that a machine is supposed to understand, you don't want turning completeness and you don't want to deal with the pain of having your own DSL, those are great.

Re: Why XML tags are so fundamental to Claude

#133

Post by fc417fc802 »

thayne wrote: post #130
fc417fc802 wrote: post #84

Earlier quoted context omitted.

It's not the hot new thing but when has hype ever mattered for getting shit done? I don't think anyone who considers it obsolete has an informed opinion on the matter. Typically a more primitive (sorry, minimal) format such as JSON is sufficient in which case there's no excuse to overcomplicate things. But sometimes JSON isn't sufficient and people start inventing half baked solutions such as JSON-LD for what is alre…

> It's not the hot new thing but when has hype ever mattered for getting shit done? But it used to be. And so it was used for a lot of things where it wasn't a great fit. XML works fairly well as a markup format, but for a lot of things, something like json models the data better. > which case there's no excuse to overcomplicate things. And that's a problem with xml. It's too complicated. Even if the basic model of x…

I don't think I'd agree that it's a problem with the tool. However you do raise a good point - that there are problems that JSON and similar struggle with where XML would introduce a noticeable amount of unneeded complexity. It's a wide enough gap that a simplified subset of XML is probably be warranted. (I assume it must exist by now and I've just never heard of it?)

Re: Why XML tags are so fundamental to Claude

#134

Post by dragonwriter »

cyanydeez wrote: post #61
Lerc wrote: post #51

I am unconvinced. To me it seems like handling symbols that start and end sequences that could contain further start and end symbols is a difficult case. Humans can't do this very well either, we use visual aids such as indentation, synax hilighting or resort to just plain counting of levels. Obviously it's easy to throw parameters and training at the problem, you can easily synthetically generate all the XML trainin…

Basically, the only way you're separting user input from model meta-input is using some kind of character that'll never show up in the output of either users or LLMs. While technically possible, it'd be like a unicode conspiracy that had to quietly update everywhere without anyone being the wiser.

Actually, all you need is an interface that lets you manipulate the token sequence instead of the text sequence along with a map of the special tokens for the model (most [all?] models have special tokens with defined meanings used in training and inference that are not mapped from character sequences, and native harnesses [the backend APIs of hosted models that only provide a text interface and not a token-level one] leverage them to structure input to the model after tokenization of the various pieces that come to the harnesses API from whatever frontend is in use.)

Re: Why XML tags are so fundamental to Claude

#135

Post by dragonwriter »

michaelbarton wrote: post #76
rhdunn wrote: post #71

Earlier quoted context omitted.

XML is used a lot in standards and publishing industries -- JATS, EPUB, ODF, DOCX/XLSX/..., DocBook, etc. are all XML based/use XML.

Without being facetious, isn’t HTML a dialect of XML and very widely used?

No, HTML was a specific application profile of SGML (modern HTML, I believe, no longer technically is), XML is a newer (than HTML) application profile of SGML inspired by HTML but aiming for greater generality.

XHTML was an attempt to encode HTML semantics (approximately, each version of XHTML also altered some semantics from HTML and previous XHTML versions) in XML, and the XML serialization of modern, WHATWG HTML exactly encodes HTML semantics in XML.

Re: Why XML tags are so fundamental to Claude

#136

Post by dragonwriter »

phlakaton wrote: post #94
michaelbarton wrote: post #76

Earlier quoted context omitted.

Without being facetious, isn’t HTML a dialect of XML and very widely used?

HTML is far loosier-goosier in its syntax than XML allows. There was an attempt to nail its syntax down in the pre-HTML 5 days; that's XHTML. When HTML 5 pivoted away from that, that spelled the end of these two things ever coming together. Really, I think you can trace a lot of the "XML is spooky old technology" mindset to the release of HTML 5. That was when XML stopped being directly relevant to the web, though of…

> There was an attempt to nail its syntax down in the pre-HTML 5 days; that's XHTML. When HTML 5 pivoted away from that, that spelled the end of these two things ever coming together.

Exactly the opposite; WHATWG “Living Standard” HTML (different releases of which were used as the basis for W3C HTML5, 5.1, and 5.2 before the W3C stopped doing that) includes an XML serialization as part of the spec, so now the HTML-in-XML is permanently in sync with and feature-matched with plain HTML.

Re: Why XML tags are so fundamental to Claude

#137

Post by what »

galaxyLogic wrote: post #48
marxisttemp wrote: post #43

Earlier quoted context omitted.

XML is much more readable than JSON, especially if your data has characters that are meaningful JSON syntax

I think readability is in the eye of the reader. JSON is less verbose, no ending tags everywhere, which I think makes it more readable than XML. But I'd be happy to hear about studies that show evidence for XML being more readable, than JSON.

>But I'd be happy to hear about studies that show evidence for XML being more readable, than JSON.

But I’d be happy to hear about studies that show evidence for JSON being readable, than XML.

Re: Why XML tags are so fundamental to Claude

#138

Post by thayne »

fc417fc802 wrote: post #133
thayne wrote: post #130

Earlier quoted context omitted.

> It's not the hot new thing but when has hype ever mattered for getting shit done? But it used to be. And so it was used for a lot of things where it wasn't a great fit. XML works fairly well as a markup format, but for a lot of things, something like json models the data better. > which case there's no excuse to overcomplicate things. And that's a problem with xml. It's too complicated. Even if the basic model of x…

I don't think I'd agree that it's a problem with the tool. However you do raise a good point - that there are problems that JSON and similar struggle with where XML would introduce a noticeable amount of unneeded complexity. It's a wide enough gap that a simplified subset of XML is probably be warranted. (I assume it must exist by now and I've just never heard of it?)

> a simplified subset of XML is probably be warranted

There are several. And that's the problem. It isn't hard to find a subset with a library for a single language that uses a slightly different subset from the other subsets. But none of them ever caught on.

Re: Why XML tags are so fundamental to Claude

#139

Post by Kerrick »

WD-42 wrote: post #90
RadiozRadioz wrote: post #39

> a contrast between Claude’s modern approach [...] XML, a technology dating back to 1998 Are we really at the point where some people see XML as a spooky old technology? The phrasing dotted around this article makes me feel that way. I find this quite strange.

XML is back, everyone is rediscovering the terminal. Soon we’ll discover that object oriented programming is good again.

Unambiguously, though, it is. There's so much trash imperative code in its training data that LLMs tend to vomit out garbage. But if you anchor it with OOP, the quality tends to be higher.

Re: Why XML tags are so fundamental to Claude

#140

Post by OutOfHere »

prima-facie wrote: post #55

Amazing how an entire profession that until yesterday would pride itself on precision, clarity (in thought and in writing), efficiency, and formality, has now descended into complete quackery.

I can understand the benefit from XML if there is a at least a three-level variable structure to share with the LLM. If there is strong consistency in a repeated three or more level structure, then JSON ought to be sufficient. If there is just a one or two level structure, it feels like unnecessary quackery, possibly reflective of a poorly trained model if the structure is a genuine necessity.
Post reply on HN