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

11–20 of 160 posts

Re: Why XML tags are so fundamental to Claude

#11

Post by dmd »

rafram wrote: post #5
TheJoeMan wrote: post #2

That first image, “Structure Prompts with XML”, just screams AI-written. The bullet lists don’t line up, the numbering starts at (2), random bolding. Why would anyone trust hallucinated documentation for prompting? At least with AI-generated software documentation, the context is the code itself, being regurgitated into bulleted english. But for instructions on using the LLM itself, it seems pretty lazy to not hand-t…

No, it’s two screenshots from Anthropic documentation, stitched together: https://platform.claude.com/docs/en/build-with-claude/prompt... The post even links to that page, although there’s a typo in the link.

They're not even stitched together ; there's just no padding between the two images.

Re: Why XML tags are so fundamental to Claude

#12

Post by glth »

rafram wrote: post #5
TheJoeMan wrote: post #2

That first image, “Structure Prompts with XML”, just screams AI-written. The bullet lists don’t line up, the numbering starts at (2), random bolding. Why would anyone trust hallucinated documentation for prompting? At least with AI-generated software documentation, the context is the code itself, being regurgitated into bulleted english. But for instructions on using the LLM itself, it seems pretty lazy to not hand-t…

No, it’s two screenshots from Anthropic documentation, stitched together: https://platform.claude.com/docs/en/build-with-claude/prompt... The post even links to that page, although there’s a typo in the link.

Author here: I have just fixed the typo. Thank you.

And yes, these are screenshots from Anthropic’s documentation.

Re: Why XML tags are so fundamental to Claude

#13

Post by wolttam »

pocketarc wrote: post #6
wolttam wrote: post #3

Anthropic’s tool calling was exposed as XML tags at the beginning, before they introduced the JSON API. I expect they’re still templating those tool calls into XML before passing to the model’s context

Yeah like I remember prior to reasoning models, their guidance was to use tags to give models space for reasoning prior to an answer (incidentally, also the reason I didn't quite understand the fuss with reasoning models at first). It's always been XML with Anthropic.

Exactly the same story here. I still use a tool that just asks them to use instead of enabling native reasoning support, which has worked well back to Sonnet 3.0 (their first model with 'native' reasoning support was Sonnet 3.7)

Re: Why XML tags are so fundamental to Claude

#15

Post by apwheele »

I think XML is good to know for prompting (similar to how was popular for outputs, you can do that for other sections). But I have had much better experience just writing JSON and using line breaks, colons, etc. to demarcate sections.

E.g. instead of

    
      
        ....
        .....
      
      ....
      ...
    
    ....
    {actual input}
Just doing something like:

    ...instructions...
    input: ....
    output: {..json here}
    ...maybe further instructions...
    input: {actual input}
Use case document processing/extraction (both with Haiku and OpenAI models), the latter example works much better than the XML.

N of 1 anecdote anyway for one use case.

Re: Why XML tags are so fundamental to Claude

#16

Post by croes »

TheJoeMan wrote: post #2

That first image, “Structure Prompts with XML”, just screams AI-written. The bullet lists don’t line up, the numbering starts at (2), random bolding. Why would anyone trust hallucinated documentation for prompting? At least with AI-generated software documentation, the context is the code itself, being regurgitated into bulleted english. But for instructions on using the LLM itself, it seems pretty lazy to not hand-t…

You just hallucinated the content is AI generated.

Re: Why XML tags are so fundamental to Claude

#17

Post by TheLNL »

Zebfross wrote: post #8

I thought the goal was minimal instruction to let Claude determine the best way to solve the problem. Not adding this to my workflow anytime soon.

It is not for the end user, it is more for things like wrappers and automation scripts.

Nobody expects the end user to prompt the AI using a structured language like xml

Re: Why XML tags are so fundamental to Claude

#18

Post by ekjhgkejhgk »

apwheele wrote: post #15

I think XML is good to know for prompting (similar to how was popular for outputs, you can do that for other sections). But I have had much better experience just writing JSON and using line breaks, colons, etc. to demarcate sections. E.g. instead of .... ..... .... ... .... {actual input} Just doing something like: ...instructions... input: .... output: {..json here} ...maybe further instructions... input: {actual i…

Could you clarify, do those tags need to be tags which exist and we need to lear about them and how to use them? Or we can put inside them whatever we want and just by virtue of being tags, Claude understands them in a special way?

Re: Why XML tags are so fundamental to Claude

#19

Post by michaelcampbell »

Total tangent, but what vagary of HTML (or the Brave Browser, which I'm using here) causes words to be split in very odd places? The "inspect" devtools certainly didn't show anything unusual to me. (Edit: Chrome, MS Edge, and Firefox do the same thing. I also notice they're all links; wonder if that has something to do with it.)

https://i.imgur.com/HGa0i3m.png

Re: Why XML tags are so fundamental to Claude

#20

Post by twoodfin »

This isn’t surprising: XML’s core purpose was to simplify SGML for a wider breadth of applications on the web.

HTML also descended from SGML, and it’s hard to imagine a more deeply grooved structure in these models, given their training data.

So if you want to annotate text with semantics in a way models will understand…

Post reply on HN