Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown • Hacker News Board

Re: Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown

#31

Post by asimovDev » Fri, Aug 29, 2025, 4:12 PM UTC

hirvi74 wrote: post #19

> "Ever notice Claude struggling to write Swift code? " Yes, that is why I quit using Claude and swapped to ChatGPT about a year ago. I've had substantially less issues with GPT.

I remember copilot with GPT helping me export Swift to C for interop. Something I could hardly find good examples and info on in my google searches.

Re: Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown

#32

Post by h1fra » Fri, Aug 29, 2025, 4:13 PM UTC

_mattt wrote: post #22

h1fra wrote: post #10

I think it's safe to assume most big players have browser rendering enabled (I hope so). imo AI is struggling with a lot of languages that are not as popular as javascript, mostly because it's more niche and you don't get a lot of good examples on the web.

In my experience, coding agents seem to do a normal fetch when provided links. Which makes sense — headless browser automation is expensive, and only really necessary for interacting with a webpage. But with these RLHF'd AIs, being confident and helpful as they are, it took me a while to realize that they couldn't actually read the Apple developer links I was giving them. Like a kid who can't read the chalkboard, but…

It's expensive for sure, but probably a drop in the water compared to the cost of renting H100. Plus, it would be a massive boost in terms of data quality/quantity for them. But maybe you are right, I'm just surprised it's not the case

Re: Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown

#33

Post by tiahura » Fri, Aug 29, 2025, 4:13 PM UTC

danielfalbo wrote: post #29

How to reliably HTML to MD for any page on the internet? I remember struggling with this in the past How hard would it be to build an MCP that's basically a proxy for web search except it always tries to build the markdown version of the web pages instead of passing HTML? Basically Sosumi.ai but instead of working on only for Apple docs it works for any web page (including every doc on the internet)

https://github.com/vivekVells/mcp-pandoc

Re: Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown

#34

Post by jordanmorgan10 » Fri, Aug 29, 2025, 4:14 PM UTC

Another awesome project that does this for Apple's docs: https://llm.codes/

Also, Apple has started shipping docs like this, too. They are a bit hidden but you can find them here:

/Applications/Xcode-beta.app/Contents/PlugIns/IDEIntelligenceChat.framework/Versions/A/Resources/AdditionalDocumentation

Re: Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown

#35

Post by the_arun » Fri, Aug 29, 2025, 4:15 PM UTC

Just wondering - can't AI read HTML? If so how are we training our models?

Re: Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown

#36

Post by CharlesW » Fri, Aug 29, 2025, 4:20 PM UTC

dewey wrote: post #3

For those wondering about the name, it has a fun story behind it: https://en.wikipedia.org/wiki/Sosumi

Jim Reekes talking about this in a deleted scene from the documentary Welcome to Macintosh: https://www.youtube.com/watch?v=k4J8AF25PjA

Re: Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown

#37

Post by dewey » Fri, Aug 29, 2025, 4:39 PM UTC

dewey wrote: post #3

For those wondering about the name, it has a fun story behind it: https://en.wikipedia.org/wiki/Sosumi

There's also a episode on https://www.macintosh.fm about the topic that I can recommend.

Re: Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown

#38

Post by y1n0 » Fri, Aug 29, 2025, 4:43 PM UTC

the_arun wrote: post #35

Just wondering - can't AI read HTML? If so how are we training our models?

Ai can’t read something dynamically rendered with JavaScript. At the moment.

Re: Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown

#39

Post by justmedep » Fri, Aug 29, 2025, 4:46 PM UTC

the_arun wrote: post #35

Just wondering - can't AI read HTML? If so how are we training our models?

The AI only sees a bit of HTML plus a bunch of JS that, when executed, generates more HTML. If the AI does not run the JS it won’t see everything. During training they probably use a crawler that runs a headless browser behind the scenes to get everything a human would get.

Re: Show HN: Sosumi.ai – Convert Apple Developer docs to AI-readable Markdown

#40

Post by michaelmior » Fri, Aug 29, 2025, 4:50 PM UTC

danielfalbo wrote: post #29

How to reliably HTML to MD for any page on the internet? I remember struggling with this in the past How hard would it be to build an MCP that's basically a proxy for web search except it always tries to build the markdown version of the web pages instead of passing HTML? Basically Sosumi.ai but instead of working on only for Apple docs it works for any web page (including every doc on the internet)

There are APIs such as Jina AI's reader API that do this pretty well. It doesn't produce output as clean as Sosumi for Apple docs, but it's free and does a decent job.

https://jina.ai/reader