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

Using Claude Code: The unreasonable effectiveness of HTML

twitter.com

Post reply on HN
Print view View original

171–180 of 308 posts

Re: Using Claude Code: The unreasonable effectiveness of HTML

#171

Post by temporallobe »

austin-cheney wrote: post #70
laurels-marts wrote: post #63

Earlier quoted context omitted.

You have been authoring HTML by hand for decades. Not every SWE is a FE dev.

Most front end devs can’t get HTML right either.

This is shockingly true. Most newer FE devs I have encountered are mostly trained on the popular frameworks and lack understanding of the underlying fundamentals, e.g., they only know TypeScript + SCSS and some smattering of HTML but more often know whatever templating engine and MVC(ish) backend the framework uses. It’s really helpful to understand what the browser is actually doing and all the “stuff” the framework spits out on the other end.

Re: Using Claude Code: The unreasonable effectiveness of HTML

#172

Post by readitalready »

yokoprime wrote: post #92
readitalready wrote: post #41

I moved from Markdown to JSON for all spec writing about 9 months ago. Although not HTML, it still has the same benefits. Claude and the other models are just so much more reliable in a structured format like JSON/HTML/XML. The most important thing is that I can run static analysis on a structured format. This is important even for my spec documents. I can write data fields and have static analysis analyze it. For ex…

I think this is super interesting, but i think you and the OP is talking about two different problems: presenting text to end users and structuring text for agents

This flow is really for LLM consumption, since Markdown spec documents are for LLMs anyways. And you can always write a JSON-to-markdown converter for human use (actually, LLMs remember Markdown content better than JSON, so you should use that in your flow a well).

The real change is in generation side, and now the spec docs are LLM generated JSON based on other spec docs or human prompts. LLMs seem to write JSON better than Markdown or YAML, if you tell it to follow a schema.

Re: Using Claude Code: The unreasonable effectiveness of HTML

#173

Post by renticulous »

edoloughlin wrote: post #104
tmhrtly wrote: post #21

My concern here is that by gravitating to HTML you lose the ability for a human (you!) to easily co-author the document with the LLM. If it’s just an explainer for your consumption, that’s not a concern - but if it’s a spec sheet for something more complex, I deeply value being able to dive in and edit what is produced for me. With a HTML doc it is much harder to do that than with MD. Now of course you could just rep…

I’ve started using HTML for reports recently. But I always use a markdown file as an intermediate and tell the LLM to generate a fancier version of it with SVG for graphs/pictures based on tables in the markdown.

One idea that could be useful for products like Browser Use and Stagehand is instead of using videos of the session, they can use HTML slideshows to show the step-by-step progress of the session. Single file HTMl can be downloaded and shared and annotated as well. I hope someone from those companies are here and will take this advice. I am not advocating for replacing the video sessions but also have the HTML Slideshow as another session artifact.

Re: Using Claude Code: The unreasonable effectiveness of HTML

#174

Post by voxleone »

4k0hz wrote: post #33
tmhrtly wrote: post #21

My concern here is that by gravitating to HTML you lose the ability for a human (you!) to easily co-author the document with the LLM. If it’s just an explainer for your consumption, that’s not a concern - but if it’s a spec sheet for something more complex, I deeply value being able to dive in and edit what is produced for me. With a HTML doc it is much harder to do that than with MD. Now of course you could just rep…

Is HTML really that much worse to edit than MD?

[dead]

Re: Using Claude Code: The unreasonable effectiveness of HTML

#175

Post by BowBun »

throwatdem12311 wrote: post #124
momojo wrote: post #12

When exploring a new idea or tool, my go to prompt is ``` In a single index.html, no dependencies, sparse styling, create an app that ``` Even before AI, it's how I built small tools, and there's something lovely about being able to email my friends the tool, and tell them "If you want to make a change, toss it to your LLM!"

My manager does this and with a straight face comes to me after with it and goes “put this in production” and wonders why it takes more than 5 minutes. I absolutely hate the absolute rot these tools have caused to people’s brains.

Last week, we discovered our 'AI-native' marketing VP put his team's entire documentation hub on a public Github Pages site for an entire week. This included prospect lists, meetings, marketing metrics like CaC/lead times, funnel metrics, etc. He did not solicit feedback from engineering and violated multiple points in our AI policy. Of course there will be no repercussions.

Re: Using Claude Code: The unreasonable effectiveness of HTML

#176

Post by odiroot »

tmhrtly wrote: post #21

My concern here is that by gravitating to HTML you lose the ability for a human (you!) to easily co-author the document with the LLM. If it’s just an explainer for your consumption, that’s not a concern - but if it’s a spec sheet for something more complex, I deeply value being able to dive in and edit what is produced for me. With a HTML doc it is much harder to do that than with MD. Now of course you could just rep…

We should ask the agents to output TeX instead. /s

On a serious note some kind of rich Markdown would definitely help.

Re: Using Claude Code: The unreasonable effectiveness of HTML

#177

Post by mohamedkoubaa »

tmhrtly wrote: post #21

My concern here is that by gravitating to HTML you lose the ability for a human (you!) to easily co-author the document with the LLM. If it’s just an explainer for your consumption, that’s not a concern - but if it’s a spec sheet for something more complex, I deeply value being able to dive in and edit what is produced for me. With a HTML doc it is much harder to do that than with MD. Now of course you could just rep…

You could just do `my two cents`

Re: Using Claude Code: The unreasonable effectiveness of HTML

#178

Post by mohamedkoubaa »

Jakob wrote: post #34
tmhrtly wrote: post #21

My concern here is that by gravitating to HTML you lose the ability for a human (you!) to easily co-author the document with the LLM. If it’s just an explainer for your consumption, that’s not a concern - but if it’s a spec sheet for something more complex, I deeply value being able to dive in and edit what is produced for me. With a HTML doc it is much harder to do that than with MD. Now of course you could just rep…

We have been authoring HTML by hand for decades with ease. Text editors are very good at it, and many have commands to auto-wrap, auto-close etc. Reading and writing is simple.

I did this on an airplane once because I didn't have Internet and I've never felt more like a real hacker since

Re: Using Claude Code: The unreasonable effectiveness of HTML

#179

Post by kschiffer »

fredwilliams wrote: post #167
athrowaway3z wrote: post #119

Earlier quoted context omitted.

I actually think there is a second level to this. Yes HTML will get you most anywhere, but I found that letting the LLM define its own language is also unreasonably effective. Currently working on a dumb little mobile game with isometric view and sound: - told codex to write a tool that lets its place blocks in a prepared three.js document and have chromium dev tools take a screenshot. It made up a little JSON struct…

[flagged]

Typical HN condescending bitterness at it again. Thank you for this very constructive feedback.

Re: Using Claude Code: The unreasonable effectiveness of HTML

#180

Post by znort_ »

looks like a disproportionally huge wall of text (on twitter no less) for a non-issue. just choose your tools sensibly:

- work text / human or mixed input: markdown, plain text

- fancy looks / interaction: html

avoid creating problems, try solving them instead. and don't start futile smoke campaigns.

Post reply on HN