Serve Markdown to AI Agents with Accept Headers

(acceptmarkdown.com)

62 points | by tilt 3 hours ago

13 comments

  • k1m 18 minutes ago
    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.

  • joshum97 50 minutes ago
    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.

    • alsetmusic 19 minutes ago
      > 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.

      • usef- 7 minutes ago
        Exa has an API for returning markdown for URLs (and search results), which also handles javascript-rendered pages, etc. It's free for up to 1k requests per month without any account, which is more than I've ever needed.

        Most harnesses have a "zero config" plugin that works, eg: https://pi.dev/packages/pi-exa

  • lekevicius 1 hour ago
    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.

  • collimarco 1 hour ago
    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.

    • slowin 50 minutes ago
      Presumably markdown uses far fewer tokens.
      • simonw 35 minutes ago
        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.
  • kaangiray26 2 hours ago
    hoping for this to get mainstream so that I can just view the pages without any ads, js and bloat
    • Elfener 1 hour ago
      > 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)

      • phoghed 1 hour ago
        > 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

    • qznc 2 hours ago
      Yeah, that is why this will not get popular.
    • jiehong 1 hour ago
      Markdown ads?
      • qingcharles 1 hour ago
        Time magazine already serves their pages like this to agents with ads for the agents in them, IIRC.
  • LunicLynx 1 hour ago
    Hello … AI company that wants easier access to data
  • maurelius2 1 hour ago
    Even without AI this would be a nice feature.
  • Kuyawa 1 hour ago
    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

  • a2ff6eeb0 1 hour ago
    Hm, interesting avenue for prompt injection.
    • spockz 1 hour ago
      How is that different from today where agents just do searches and ingest web pages?
      • hnlmorg 1 hour ago
        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.

        • spockz 1 hour ago
          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.

  • monneyboi 1 hour ago
    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.

  • ErroneousBosh 1 hour ago
    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?

  • xgulfie 25 minutes ago
    Sounds like a great way to spread disinfo to LLMs, so I'm down
  • shahariaa 1 hour ago
    [dead]