_mattt
Joined 9 years ago
Joined 9 years ago
GitHub repo here: https://github.com/mattt/AnyLanguageModel
Happy to answer questions about the implementation or trade-offs we made.
For the Swift standard library and other open-source frameworks, you could probably extract this from documentation comments using DocC, Jazzy, or the like.
In many cases, a Markdown distillation of HTML can improve the signal-to-noise ratio — especially for sites mired in <div> tag soup (intentionally or not). But that's an optimization for token efficiency; LLMs can usually figure things out.
The motivation behind Sosumi is better understood as a matter of accessibility. The way AI assistants typically fetch content from the web precluded them from getting any useful information from developer.apple.com.
You could start to solve the generalized problem with an MCP that 1) used a headless browser to access content for sites that require JS, and 2) used sampling (i.e. having a tool use the host LLM) to summarize / distill HTML.
Even for those open source projects, there is still some value added in the generated documentation that isn’t directly available from documentation comments, such as type members and protocol conformances (though a LLM could certainly suss that out with the right context).
Long live Jazzy.
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 doesn't realize they need glasses.