Using Claude Code: The unreasonable effectiveness of HTML

BretonForearm

Many of us had CC routinely generate HTML ever since it became available. Surprised that it's presented as some kind of novelty.

apsurd

Web technologies got so many things right. People complain about it so much but it's amazing. I worked with a vibe coded app at my last job (and since quit due to it) and because it was a nextjs SPA frontend with a separate API backend, the user facing urls didn't match the backend endpoints. Because AI uses react hooks for everything, state is in-memory, url-based routing isn't a thing unless you design for it. So links aren't free and thus we have no way for users to link to anything other than top-level entry points. LINKS! Especially for internal tools, everything being linkable is vital to collaboration and problem solving. The need for uniform resource locations and verbs was so well thought out, 30 or 40 some odd years ago.

kulikalov

Md and plotly is all you need. The only thing that is truly missing is some sort of Markdown-based forms

gabesullice

It's been confusing to me that so many people have treated markdown as the lingua franca for agent instructions when their training corpus must be dramatically biased to HTML instead of Mardown. Markdown only makes sense for us meatbags becuse it's easy for us to edit and version control, but if you're sharing anything where the audience is an agent publicly, HTML must be just as interpretable.

koolala

The unreasonable effectiveness of HtmlX.

jdw64

So the argument seems to be that HTML is stronger than Markdown for disposable UI, visualization, and interactive artifacts. It also works well as an external memory object because it can be linked to and opened directly. For visualization and animation, I do think HTML can be a very good format. If LLMs become part of the workflow, this can definitely be useful. But on the other hand, maintaining HTML itself is more annoying than it first appears. I do something somewhat similar. I download good CodePen examples and store them in a GitHub library so I can reuse them later. It works, but version management becomes quite difficult in practice. So I think there are real tradeoffs.

Barbing

(Edit) nvm, the usual Xcancel ( https://xcancel.com/trq212/status/2052809885763747935 ) just links to an article ( http://x.com/i/article/2052796100608974848 )

ar_turnbull

I’ve been prompting my way to all kinds of interactive HTML artifacts the last month or so. It’s way more fun than making decks and static documentation. I even did a workshop with PartyKit cursors, dot voting, reflection comments, and an individual rating at the end. Oh, and I can add super lightweight analytics so I know who actually reads my things or interacts with my prototypes. ^_^

alsetmusic

> I’ve started preferring HTML as an output format instead of Markdown and increasingly see this being used by others on the Claude Code team, this is why. This is why I read long agent output either by using VIM and MacOS Quicklook (with a markdown extension for rendering) or paste output into MarkEdit (an editor with a preview pane; I think it’s cross platform?). Worst case, have an agent build you a simple local web page that interprets Markdown and renders it. Markdown was invented as a shorthand for web syntax[0]. That’s what it’s for! I bet you spend more tokens and time asking an agent to convert its native markdown to html than any of these. 0. https://daringfireball.net/projects/markdown/