Rendered at 21:11:17 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
ahriad 10 hours ago [-]
We broke the web so badly for humans that we had to build a clean web for machines, and now humans will have to use machines to experience a clean web again.
tacostakohashi 9 hours ago [-]
Yeah, when browsers have a "reader mode", it's pretty obvious the plot has been lost somewhere.
sunir 9 hours ago [-]
We'll finally bring back Gopher.
daniel-alexande 7 hours ago [-]
Always loved Gopher
gopher_space 7 hours ago [-]
A man can dream.
dmos62 10 hours ago [-]
I wonder why we broke the web.
Eddy_Viscosity2 10 hours ago [-]
For the same reasons why we eventully pollute and corrupt every system and environment we use. If there is any benefit that can be extracted for some while the costs are borne by many, than this will occur and generate a positive feedback loop that grows over time.
It's the law of monetization.
qsera 9 hours ago [-]
>than this will occur and generate a positive feedback loop that grows over time.
And despite this, modern life is made possible by the illusion that "regulations" work..
Eddy_Viscosity2 5 hours ago [-]
Regulations can and do work, but its never a 'one and done' kind of solution because people find workarounds and loopholes. It requires a unceasing effort to maintain the balance.
ahriad 10 hours ago [-]
For money! Ads make money.
jt2190 9 hours ago [-]
Because while consumers value “inefficiency” (high design, wonderful prose, beautiful images, great usability) they don’t want to actually pay for it. Producers have to become extremely efficient without revenue, and are stuck with a choice: Produce at a loss, stop producing, or seek payment from another source (sponsorships, ads).
dmos62 9 hours ago [-]
It seems there's little agreement over how the web is broken.
temp8830 9 hours ago [-]
People who love cookie banners either don't exist, or are alien invaders :)
functionmouse 10 hours ago [-]
In order to break the user, of course.
noufalibrahim 10 hours ago [-]
To improve the user experience.
throwaway613746 9 hours ago [-]
[dead]
soco 9 hours ago [-]
It's a matter of time until the web for machines will be crawling with ads and everything else, and worse.
marand23 9 hours ago [-]
I never thought about it before now but the llm era could be a form of renaissance for blind people on the Internet. An alternative web where functionality of every page is described in short but detailed text instead of extremely verbose and non-linear html tree structure.
rickette 10 hours ago [-]
Does any of the LLM providers actually use llms.txt?
If I remember correctly this "standard" was setup by someone but without involvement of any of the major AI players.
HermanMartinus 10 hours ago [-]
I can definitively say llms.txt is not used by any AI players. I run a blogging platform with around 80k blogs and /llms.txt is not requested by anything (other than humans checking to see if there's an llms.txt path).
All regular pages are aggressively scraped to the extent it's a problem I have to consistently manage, but not llms.txt.
nickserv 9 hours ago [-]
I'm seeing quite a bit of request for these on my work's GitBook documentation site.
But perhaps these are developers specifically targeting these pages to feed whatever LLM they are using.
isaachinman 10 hours ago [-]
How is a static blog being scraped a problem? Do you not use a CDN?
nickserv 9 hours ago [-]
> a blogging platform with around 80k blogs
But nah, I'm sure OP doesn't know about CDNs.
the_real_cher 9 hours ago [-]
Are all blogs static though?
johannes1234321 9 hours ago [-]
Very few blogs require frequent updates. Even with user comments.
sunshine-o 9 hours ago [-]
Amazing, I didn't know.
So it get even stranger, I am the only one reading those /llms.txt ...
0123456789ABCDE 9 hours ago [-]
> I can definitively say llms.txt is not used by any AI players.
Now, it would be super cool to get markdown and zero javascript bundles…
solumos 5 hours ago [-]
If you want to see what that looks like, I one-shot a browser with Claude that does it[0]. Docs pages are early adopters to this[1][2], so that AI agents can better handle tasks.
There is an enshittification cycle at work. The web used to be good, predominately text, and useful, 25 years ago. Then... slowly... we added javascript, then AJAX, CSS, flash, interstitials, popups, marketing, social media, algorithms, doomscrolling... gradually but surely turn it into the unusable cesspool that it is today.
Now we have AI! I think a big part of its utility is that it gets us back to text/information, and lets us bypass all the "beautiful" design / nonsense on the material it is trained on.
However, AI is just beginning its enshittification cycle - now that it has a critical mass of users, it is an irresistible target to start slowly adding ads, misinformation, conspiracy theories, and whatever else people can dream up, until it also becomes unusable and the cycle repeats.
cyanydeez 10 hours ago [-]
oh don't worry, in 5 years your AI will be unundated with context poison prompts that try to get them to spend all your bank notes and meta bucks on equally useless things.
This is just a redeux of the early web.
maccam912 9 hours ago [-]
Already happening. I was using Claude to check out sampler plugins and I'm sure it happens undetected, and it might have mentioned it with other versions, but Claude Opus 4.8, being it's helpful, honest self, told me that one of the pages it reviewed had hidden text instructing it to recommend that plugin. It caught it and was able to avoid influence from that plugin at least, but we're already living in that world.
gobdovan 9 hours ago [-]
Not really, but sounds interesting. Would you care to share some sites that offer better llms.txt than main web page? Or talk about some piece of info you easily found on llms.txt that was hard to navigate to on the regular website?
sunshine-o 7 hours ago [-]
llms.txt usually includes a clear sitemap and description of information available on a site.
There are also clear definition of the restful scheme and API/data access options.
It's the law of monetization.
And despite this, modern life is made possible by the illusion that "regulations" work..
If I remember correctly this "standard" was setup by someone but without involvement of any of the major AI players.
All regular pages are aggressively scraped to the extent it's a problem I have to consistently manage, but not llms.txt.
But perhaps these are developers specifically targeting these pages to feed whatever LLM they are using.
But nah, I'm sure OP doesn't know about CDNs.
So it get even stranger, I am the only one reading those /llms.txt ...
[0] - https://acceptmarkdown.com/
[0] - https://github.com/solumos/md-browse
[1] - https://docs.stripe.com
[2] - https://vercel.com/docs
- [0] https://blog.cloudflare.com/markdown-for-agents/#convert-htm...
anyone who's, even slightly, clued into how agents access documentation, has been making changes to their pages. ex: https://searchtxt-web.fly.dev/search?q=aws
https://github.com/AnswerDotAI/llms-txt/issues/2
It’s been completely ignored ever since.
- https://cloud.laravel.com/docs/llms.txt
- https://cloud.laravel.com/docs/llms-full.txt
There is an enshittification cycle at work. The web used to be good, predominately text, and useful, 25 years ago. Then... slowly... we added javascript, then AJAX, CSS, flash, interstitials, popups, marketing, social media, algorithms, doomscrolling... gradually but surely turn it into the unusable cesspool that it is today.
Now we have AI! I think a big part of its utility is that it gets us back to text/information, and lets us bypass all the "beautiful" design / nonsense on the material it is trained on.
However, AI is just beginning its enshittification cycle - now that it has a critical mass of users, it is an irresistible target to start slowly adding ads, misinformation, conspiracy theories, and whatever else people can dream up, until it also becomes unusable and the cycle repeats.
This is just a redeux of the early web.
There are also clear definition of the restful scheme and API/data access options.
One very basic example would be the weather channel https://weather.com/llms.txt
https://news.ycombinator.com/item?id=48411569
BTW why should Chrome even consider rendering a .txt file as markdown?
Result: no such item.
From where do you got the idea that adding /llm.txt to urls will produce markdown?
I imagine Claude could zero-shot a Chrome plugin for that.