> It is a bad design trade-off to send a bunch of header fields on every request just to tell the server all of the possible variations of preference held by the user, particularly when there is a very small chance that any of those dimensions are applicable to the target resource. It has been a bad design trade-off ever since the very brief period in 1993-94 when folks didn't know which image format would be usable on all UAs and there was no CSS or javascript to allow for client-side adaptation.
> ...The caching impact of proactive negotiation is far worse than the one extra round trip per site for reactive negotiation, and even that round-trip isn't necessary in formats that support client-side adaptation.
On the caching impact, Simon Willison wrote:
> ...you can’t deploy an application that uses content negotiation via the Accept header behind the Cloudflare CDN — for example serving JSON or HTML for the same URL depending on the incoming Accept header. If you do, Cloudflare may serve cached JSON to an HTML client or vice-versa.
Note: I posted this in another comment with links to those two quotes which I couldn't copy easily now - will add later.
If you do content negotiation, then it’s imperative to send “Vary: accept” in your response. CF and all other CDNs will automatically do the right thing when they see that header.
Content negotiation still has its uses, but most of the time you’re better off using different endpoints.
Conceptually, I’m not sure I agree. There’s elegance in clients saying "I want this resource, and I’d like to get your markdown version of it. If you don’t have one, I’ll also take HTML." And if you couple that with optional "file extensions" at the end of the url to force a specific format (say, /foo for automatic negotiation, and /foo.html, /foo.json, or /foo.md for the respective media type,) you have a very easy to use API that adapts to the client; not the other way around.
I take the point that it makes caching harder, but I don’t think that should overrule ergonomics concerns.
I feel like I am going insane. Who in their right mind would feed an LLM raw HTML in the first place??
HTML is a markup language. User agents present it in a way that makes sense for the user—visually, or through assistive technology. Nothing about adding LLM “users” should change this—their user agent, the harness, should present HTML in a way they can natively understand, by translating it to Markdown.
We are not going to rewrite the entire web because harness developers are too lazy or stupid to pull an HTML to markdown package from npm. If some sites want to do so anyway, good for them, in many cases I’d love to skip the CSS/JS and read the markdown directly (or better, nicely formatted). But don’t blame website authors for your harness wasting your tokens.
Exa also has an API for it that has worked well for me, returning markdown for a URL, which means you don't need to render js or anything yourself. It doesn't need an account for up to 1k requests/month, which is more than I've ever needed.
I'll do that once any of the top 4 AI chatbots says they'll start making requests with this header. Before that it's just a neat idea with no adoption.
I also think it's exceedingly unlikely that any of the top 4 chatbots would choose to load websites this way. Too many risks for a 0.01% adoption even years later.
Is that even true? I most often use HTML. HTML is about 5%-20% more tokens than a similar Markdown. As a rule of thumb, the number of tags/structural tokens doubles, when going from markdown to html, while the rest don't change much. On the other hand, I can view HTML without any extra/unusual tools. And composing HTML when I need a bit of structure is far easier than composing markdown.
> On the other hand, I can view HTML without any extra/unusual tools. And composing HTML when I need a bit of structure is far easier than composing markdown.
This is kind of the opposite of reality no? Markdown is just plain text and meant to be human readable. You don't need XML tags to read and write it, opposed to html where you do and you need a browser to properly view it.
That's highly dependent on what sites you're visiting. Take a look around at a lot of modern sites, there's a sea of divs and spans. Markdown conversion helps LLMs a lot.
That used to matter to me back in the days when the best models still only accepted ~32,000 tokens, but these days even the models that run on my laptop are happy with ~100,000 and the hosted models I use take ~200,000 or more.
> Let's say you want to plan a trip to Thailand with your family. You could use the fancy AI to do it for you, or you could build a stupid frontend with minimal natural language understanding.
Everything is determined by cloudflare. If they supported Gemini on the same hostname I’d serve it everywhere. If they supported text/plain and text/html everywhere I’d serve that. But they don’t cache per content encoding so I just do what works for them.
I don’t disagree with you in principle but there is a difference.
The MD content isn’t intended for human consumption whereas HTML is. So you either have that injection readable to your users, which could be jarring to non-technical readers, or you play the cat-and-mouse game of hoping those pesky crawlers don’t ignore text that’s not human-visible on a rendered page.
Right. And today we have something similar with search engines going on where sites want to offer the full text to the engine for seo. But maybe they want to do the opposite to agent and poison the well. So human agents still get the “real” data and agents the “something plausible but not quite right” data.
Or everything just disappears behind something like cloudflare or a paywall.
I agree with Roy Fielding on this:
> It is a bad design trade-off to send a bunch of header fields on every request just to tell the server all of the possible variations of preference held by the user, particularly when there is a very small chance that any of those dimensions are applicable to the target resource. It has been a bad design trade-off ever since the very brief period in 1993-94 when folks didn't know which image format would be usable on all UAs and there was no CSS or javascript to allow for client-side adaptation.
> ...The caching impact of proactive negotiation is far worse than the one extra round trip per site for reactive negotiation, and even that round-trip isn't necessary in formats that support client-side adaptation.
On the caching impact, Simon Willison wrote:
> ...you can’t deploy an application that uses content negotiation via the Accept header behind the Cloudflare CDN — for example serving JSON or HTML for the same URL depending on the incoming Accept header. If you do, Cloudflare may serve cached JSON to an HTML client or vice-versa.
Note: I posted this in another comment with links to those two quotes which I couldn't copy easily now - will add later.
>On the caching impact, Simon Willison wrote:
Wrong: https://developers.cloudflare.com/cache/concepts/vary/
Yes. This feature is brand new: https://developers.cloudflare.com/cache/changelog/
Simon wrote that in 2023: https://simonwillison.net/2023/Nov/20/cloudflare-does-not-co...
If you do content negotiation, then it’s imperative to send “Vary: accept” in your response. CF and all other CDNs will automatically do the right thing when they see that header.
Content negotiation still has its uses, but most of the time you’re better off using different endpoints.
Conceptually, I’m not sure I agree. There’s elegance in clients saying "I want this resource, and I’d like to get your markdown version of it. If you don’t have one, I’ll also take HTML." And if you couple that with optional "file extensions" at the end of the url to force a specific format (say, /foo for automatic negotiation, and /foo.html, /foo.json, or /foo.md for the respective media type,) you have a very easy to use API that adapts to the client; not the other way around.
I take the point that it makes caching harder, but I don’t think that should overrule ergonomics concerns.
If CloudFlare isn't honouring vary: accept that's a pretty serious bug
I feel like I am going insane. Who in their right mind would feed an LLM raw HTML in the first place??
HTML is a markup language. User agents present it in a way that makes sense for the user—visually, or through assistive technology. Nothing about adding LLM “users” should change this—their user agent, the harness, should present HTML in a way they can natively understand, by translating it to Markdown.
We are not going to rewrite the entire web because harness developers are too lazy or stupid to pull an HTML to markdown package from npm. If some sites want to do so anyway, good for them, in many cases I’d love to skip the CSS/JS and read the markdown directly (or better, nicely formatted). But don’t blame website authors for your harness wasting your tokens.
> in many cases I’d love to skip the CSS/JS and read the markdown directly
I've been enjoying https://defuddle.md since learning about it. Works great. Not affiliated.
Exa also has an API for it that has worked well for me, returning markdown for a URL, which means you don't need to render js or anything yourself. It doesn't need an account for up to 1k requests/month, which is more than I've ever needed.
Most harnesses have a "zero config" plugin that works, eg: https://pi.dev/packages/pi-exa
(no affiliation to either)
I'll do that once any of the top 4 AI chatbots says they'll start making requests with this header. Before that it's just a neat idea with no adoption.
I also think it's exceedingly unlikely that any of the top 4 chatbots would choose to load websites this way. Too many risks for a 0.01% adoption even years later.
What about clean, semantic HTML?
It was already optimized for bots and search engines (which are bots) and it has been used for decades. Why we need to serve in markdown now?
There are also many parts of the HTML, like navs, that are useful for bots and AI and may be removed in the markdown version.
>What about clean, semantic HTML?
Which React package is this?
Presumably markdown uses far fewer tokens.
Is that even true? I most often use HTML. HTML is about 5%-20% more tokens than a similar Markdown. As a rule of thumb, the number of tags/structural tokens doubles, when going from markdown to html, while the rest don't change much. On the other hand, I can view HTML without any extra/unusual tools. And composing HTML when I need a bit of structure is far easier than composing markdown.
> On the other hand, I can view HTML without any extra/unusual tools. And composing HTML when I need a bit of structure is far easier than composing markdown.
This is kind of the opposite of reality no? Markdown is just plain text and meant to be human readable. You don't need XML tags to read and write it, opposed to html where you do and you need a browser to properly view it.
That's highly dependent on what sites you're visiting. Take a look around at a lot of modern sites, there's a sea of divs and spans. Markdown conversion helps LLMs a lot.
That used to matter to me back in the days when the best models still only accepted ~32,000 tokens, but these days even the models that run on my laptop are happy with ~100,000 and the hosted models I use take ~200,000 or more.
They accept more tokens these days, but they are still more accurate with a shorter context [1].
[1] https://arxiv.org/abs/2307.03172
If it's one of many tool calls, I'd assume that less is more.
hoping for this to get mainstream so that I can just view the pages without any ads, js and bloat
> But imagine for a second they did do that. You get the API, all the info is there.
> Why do you need AI then?
(from this HN comment, worth a read in full: https://news.ycombinator.com/item?id=43679585)
> Let's say you want to plan a trip to Thailand with your family. You could use the fancy AI to do it for you, or you could build a stupid frontend with minimal natural language understanding.
It's giving https://news.ycombinator.com/item?id=8863#9224
Yeah, that is why this will not get popular.
Markdown ads?
Time magazine already serves their pages like this to agents with ads for the agents in them, IIRC.
Best case scenario, this ends up being abused in order to feed LLMs crap responses (or worse).
No, I don't think I will. I publish things for people, not bots.
Hello … AI company that wants easier access to data
Everything is determined by cloudflare. If they supported Gemini on the same hostname I’d serve it everywhere. If they supported text/plain and text/html everywhere I’d serve that. But they don’t cache per content encoding so I just do what works for them.
They’re far too useful for me.
https://developers.cloudflare.com/cache/concepts/vary/
Even without AI this would be a nice feature.
Interesting...
A cherry.jpg image/jpeg file is shown as an image by the browser
A logo in svg like https://news.ycombinator.com/y18.svg too
So browsers should show readme.md as text/markdown and clicking on a link inside that file should also redirect to another markdown file, instant wiki
Browsers should implement that asap and we will follow
It depends on one question: does Markdown support <script> tags?
Technically, Markdown supports all HTML tags, including script tags.
Practically, Markdown is more of a vibe than a spec and everyone just uses whatever subset makes sense to them.
Hm, interesting avenue for prompt injection.
How is that different from today where agents just do searches and ingest web pages?
I don’t disagree with you in principle but there is a difference.
The MD content isn’t intended for human consumption whereas HTML is. So you either have that injection readable to your users, which could be jarring to non-technical readers, or you play the cat-and-mouse game of hoping those pesky crawlers don’t ignore text that’s not human-visible on a rendered page.
Right. And today we have something similar with search engines going on where sites want to offer the full text to the engine for seo. But maybe they want to do the opposite to agent and poison the well. So human agents still get the “real” data and agents the “something plausible but not quite right” data.
Or everything just disappears behind something like cloudflare or a paywall.
Yeah, this is the way forward. All the POW stuff is such a waste of energy.
The open internet deserves a real solution instead of gatekeepers in the form of brightdata, firecrawl, cloudflare and the likes.
So can I use this to serve actively harmful content to the Cocaine Piracy Parrots?
Maybe tarpit them into reading gigabytes of Markov Chain nonsense, really slowly?
Sounds like a great way to spread disinfo to LLMs, so I'm down