TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Microsoft rejects documentation PR because AI chatbots can't display tables

108 pointsby panic5 months ago

12 comments

october81405 months ago
Maybe documentation shouldn’t be written for humans anymore. Maybe nothing should. Maybe we should all stop talking to one another and just communicate through AI chat bots. My chatbot will ask your chatbot if you’d like to go out tonight.
评论 #42441432 未加载
rsynnott5 months ago
This, surely, must be peak AI mania. Can&#x27;t make the docs readable to humans; it might upset the robots.<p>It does look like they&#x27;ve backed off, now:<p>&gt; I&#x27;ve learned today that you are sensitive to ensuring human readability over any concerns in regard to AI consumption<p>I mean, you&#x27;d think that would go without saying.
评论 #42442932 未加载
评论 #42441576 未加载
addandsubtract5 months ago
Ironic that their build bot uses a table to present its validation check.
anal_reactor5 months ago
Ah yes. The two times I had to use Microsoft documentation for something, it boiled down to:<p>a) we&#x27;ve detected that your browser is set to Kazakh. Please enjoy our automatic translation of technical documentation to Kazakh. You want English? Haha that&#x27;s a hidden option<p>b) the field &quot;WSFaddr&quot; contains the WSF address. Its type is &quot;string&quot;<p>Because of the above, I&#x27;ll never ever use Azure again
评论 #42440592 未加载
评论 #42440661 未加载
breadislove5 months ago
the way forward should be making llms understand tables better. those documentations should be written for humans, as an alternative you could have an llm friendly version
评论 #42440814 未加载
Crosseye_Jack5 months ago
:rolleyes:<p>AI should be a tool to aid humans, not humans trying to aid AI. When you start valuing the tool over humans things start going awry rather quickly.<p>I&#x27;m not against AI, but I don&#x27;t think we should be bending the world to make AI fit better.<p>In before there is a request to change the docs into pure tokens, as human language is far too inefficient for the AI to process.
monkeyfun5 months ago
He&#x27;s so incredibly personally offended and passive-aggressive, it&#x27;s wild. Especially when he can only accept SOME of what he&#x27;s read after apparently pretending half of it was his idea!<p>Just reading the actual content of his (minimal) replies, he constantly avoids addressing the content of what anyone said over acting personally hurt and calling everyone &quot;sensitive&quot; and acting like it&#x27;s arbitrary and unfair anger. I feel like that says a lot about microsoft, and a lot of Corporate types in general...
tpoacher5 months ago
&quot;Edited&quot;
agilob5 months ago
MS admitting their artificial &quot;intelligence&quot; is too stupid to understand tables, not even 20 hours after HN discussed how are developers preparing for AI to takeover our jobs. <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=42431103">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=42431103</a>
评论 #42440493 未加载
eterm5 months ago
This is our future. I hate it, but it feels inevitable.<p>My job is going to be unrecognisable in 10 years time, to the point where I&#x27;m not sure I&#x27;ll be particularly skilled to do it. And the tools I need to do my job are being made worse, just so that I can be overtaken by the next generation who are agile enough to switch to leveraging LLMs better.
评论 #42440522 未加载
评论 #42440682 未加载
评论 #42440449 未加载
评论 #42440773 未加载
jtchang5 months ago
Is the documentation for AI chat bots or for humans?<p>The PR is now closed but seems like we should be striving to do better.
评论 #42440777 未加载
apexalpha5 months ago
I&#x27;m not sure how I feel.<p>On the one hand I absolutely understand what all people are mad about. Docs are for humans, so LLMs understanding them shouldn&#x27;t be a reason to reject something as simple as a table.<p>However, it also makes sense to make sure we not <i>intentionally</i> put things in a format that&#x27;s bad for LLMs when other formats are available and just as useful for humans.<p>Personally, one of my favourite uses of ChatGPT is to just throw in any manpage followed by a question. If all manpages had specific sections that an LLM couldn&#x27;t process I&#x27;d be a little annoyed at least.<p>I mean at that point why not take the (future) LLMs into acount?
评论 #42442952 未加载
评论 #42440973 未加载