Ask HN: If HTML supersedes Markdown fr AI, Will it be versatile enough for devs?
6 points
8 hours ago
| 6 comments
| HN
Isn't Markdown's hallmark its versatility while performant? I see there is an increasing call from tech community towards HTML to be adopted instead of Markdown due to its richness in the agentic communication layer. But is it versatile across any kind of interfaces? versatile with different format conversions? and performant (as the md is lightweight)?
late_night_fix
3 hours ago
[-]
I feel like Markdown stays the human-feindly layer,while HTML/AST becomes the machine-to-machine layer.
reply
zameermfm
2 hours ago
[-]
True, Machine to machine is interesting to think about
reply
yossuf2000
4 hours ago
[-]
I think its just hype not worth it at all and you want be able to read it clearly from your editot
reply
zameermfm
2 hours ago
[-]
Yeah, Reading it clearly in the editor - Probably MD to HTML happens in the editor anyway. So what we are dealing with here are a battle between ease of writing, readability and various cost dimensions.
reply
digitaltrees
8 hours ago
[-]
What do you mean if? The internet is built on html. Markdown is a random flare up of an annoying annotation standard pushed by LLMs. No one used Markdown anywhere near at the scale of html before ChatGPT
reply
dnnddidiej
2 hours ago
[-]
So you write a HTML Readme? Markdown is what I write 99% of the time. Unless I am in a rich editor and HTML behind the scenes.

HTML is a communication layer. Hardly anyone is writing it directly. Using React etc. or whatever or even LLM.

reply
zameermfm
8 hours ago
[-]
Thats a complete reductive idea of MDs. MD was long spawn before LLMs as a need for light weight formatting and easy conversion to different formats. No one used at that scale doesnt mean the absence of the utility for it, as the primary adopters were tech community and that was a layer below the consumer market. Utility obviously stands, the question is, can HTML supersede on that utility side of it in all developer work components.
reply
LogicCraft678
5 hours ago
[-]
HTML offers more flexibility while markdown is usually easier to create
reply
zameermfm
2 hours ago
[-]
May be they should coexist for utilities they provide
reply
chichengl
5 hours ago
[-]
HTML for human? Markdown for Agent?
reply
zameermfm
2 hours ago
[-]
Agent to human?
reply
smt88
8 hours ago
[-]
A) Who cares? What performance are you even talking about? Number of tokens?

B) HTML can contain data, layout, and design within a single file. Markdown isn’t comparable. There will be many situations where Markdown can’t do what HTML, so this is overall a silly comparison.

reply
zameermfm
7 hours ago
[-]
A) Enterprises for one, e.g Rendering of an HTML page vs MD in an AI IDE or even tokens (compounding costs for a communication doc may be billions in a year) B) True, its a subset, nobody is arguing against it. HTML has overheads in terms of stylings. MD in essence is just a straight arrow.

If there is a communication between two points with ultimate low latency way with readability and threshold just enough to have the idea, MD passes that mark. As tokens needs to conserved

reply
potatosalad99
4 hours ago
[-]
What do you mean by the cost of rendering an HTML page in an IDE? You know those markdown previews are almost always rendered by converting them to an HTML snippet first, right? Also HTML does not need to be styled, the tags have their own semantic meanings just like the various semantic structures of markdown. The styling “overhead”, which gets added so the document is easier to visually interpret for a human, is exactly the same. The only time when styling doesn’t come into the equation is when you directly view markdown source.

Also, latency???

reply
zameermfm
2 hours ago
[-]
If cost of showing HTML and MD are same in the CPU level for UI, but generation of them costs uneven at AI level (as it should be mathematically), shouldn't the equation be what is the lowest cost to represent something considering the token usage
reply
sdevonoes
5 hours ago
[-]
Nobody cares about “tokens”
reply