151–160 of 160 posts
All system prompts are already wrapped in specific role markers (each LLM has its own unique format), so I'm sure every lab is familiar with the concept of delimters, in-band vs out-of-band signalling and such. It'd not clear why within any section XML markers would do better than something like markdown, other than claude being explicitly post-trained with XML prompts as opposed to markdown. One hypothesis could be…
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.
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…
It looks like a screenshot from the Claude desktop app, so I don't think the author is trying to disguise the AI origin of the marerial
Earlier quoted context omitted.
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.
I'm sorry for not elaborating. My original complaint is with Anthropic! The 7-figure Anthropic engineers couldn't be bothered to write down how to use their tool. And there is no way for the tool to already have latent knowledge about how to use itself since that wouldn't have been part of the internet/books/github training material.
> 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.
If you think XML is old tech, wait until you hear of EDI, still powering Walmart and Amazon logistics. XML came in like a wrecking ball with its self-documenting promise designed to replace that cryptic pesky payload called EDI. XML promised to solve world hunger. It spawned SOAP, XML over RPC, DOM, DTD, the heyday was beautiful and Microsoft was leading the charge. C# was also right around this time. Consulting firm…
Earlier quoted context omitted.
XML is a bit more special/first class to Claude because it uses XML for tool calling: /path/to/file 100 50 I'm sure Claude can handle any delimiter and pseudo markup you throw at it, but one benefit of XML delimiters over quotation marks is that you repeat the delimiter name at the end, which I'd imagine might help if its contents are long (it certainly helps humans).
How well do we understand the tokenization for Claude? I'd posit that the exact human-representation of this markup is likely irrelevant if it's all being converted into a single token.
Earlier quoted context omitted.
Without being facetious, isn’t HTML a dialect of XML and very widely used?
HTML is actually a dialect of SGML. XHTML was an attempt to move to an XML-based foundation, but XML's strictness in parsing worked against it, and eventually folks just standardized how HTML parsers should interpret ill-formed HTML instead.
I suppose the proof is in the parsing
If this is true, the why does Claude Code's own system prompt not use this style? https://github.com/Piebald-AI/claude-code-system-prompts/tre...
https://github.com/Piebald-AI/claude-code-system-prompts/blo... They seem to use XML-esque tags here in the first prompt I looked at
Earlier quoted context omitted.
didn't know html was spooky tech, TIL. /s
HTML predates XML by 5 years. What's more, the web standards bodies even abandoned a short-lived XML-hype-era plan to make a new version of HTML based on XML in 2009. That from this touted to the heavens format a handful of uses remain (some companies still using SOAP, the MS Office monster schemas, RSS, EPUB, and so on) is the very opposite of the adoption it was supposed to have. For those that missed the 90s/early…
Earlier quoted context omitted.
XML is a bit more special/first class to Claude because it uses XML for tool calling: /path/to/file 100 50 I'm sure Claude can handle any delimiter and pseudo markup you throw at it, but one benefit of XML delimiters over quotation marks is that you repeat the delimiter name at the end, which I'd imagine might help if its contents are long (it certainly helps humans).
Cannot believe it's efficient. XML is the most verbose and inefficient of communicating anything. The only benefit of XML was to give lifetime work to an army of engineers. The next news will be "Why DTD is so fundamental to Claude".
It gets a bit muddier with attributes, but you can still capture the core semantics of the tag with a single token. The model will learn that tag's attributes through training on usages of the tag.