This text/markdown scheme feels like it's begging for adversarial shenanigans since it lets you serve different content to agents than humans, by design.
It seems hard to tell what to think of a company that is simultaneously trying to poison the content that it sends to agents [1] and also doing things like this.
I understand their arguments for it - and completely disagree - so I can't help but think that anyone who is on the pro-AI side of things would do well to steer clear of them if possible.
>We already see some of the most popular coding agents today – like Claude Code and OpenCode – send these accept headers with their requests for content.
This seems useful beyond agents.
It will save tons of traffic for scripts, text browsers, low-bandwidth connections,etc
markdown is incredibly compact and easy to parse.
I don't care about the AI implications but having someone put money into a flawless conversion of html into markdown will certainly improve terminal based web browsing :)
19 comments
[ 3.1 ms ] story [ 49.6 ms ] thread> Otherwise please use the original title, unless it is misleading or linkbait; don't editorialize.
https://news.ycombinator.com/newsguidelines.html
I understand their arguments for it - and completely disagree - so I can't help but think that anyone who is on the pro-AI side of things would do well to steer clear of them if possible.
[1]: https://arstechnica.com/ai/2025/03/cloudflare-turns-ai-again...
After reading the blog, turns out it is about markdown on the edge. lmao.
Expect this to be used to block agent traffic
They're not even coy about it so let me say it again: they're not working for the people using the agents, their working to serve the agents.