Comment by sampsonj
3 days ago
The LLM approach is simpler and more flexible since it works with every library and language out of the box.
Looking up official documentation would require shipping sophisticated parsers for each language, plus a way to map tokens to their corresponding docs. I'd also need to maintain those mappings as libraries evolve and documentation moves. Some ecosystems make this easier (Rust with docs.rs), but others would be much harder (AWS documentation, for example).
I also want explanations visible directly in hover hints rather than linking out to external docs. So even with official documentation, I'd need to extract and present the relevant content anyway.
Beyond that, the LLM approach adapts to context in ways static docs can't. It generates explanations for code within the documentation you're reading, and it works on code that doesn't compile, like snippets with stubs or incomplete examples.
It could be interesting in the future to look into doing some type of hybrid approach where an LLM goes out and searches up the documentation, that way it's a little bit more flexible. But that would also be a bit slower and more costly.
> Looking up official documentation would require shipping sophisticated parsers for each language,
You could just token match (use tree-sitter or something similar) and fetch the official docs. Keep it dead-simple so there's no way you can provide false positives (unlike what's happening rn where hallucinations will creep in).
> It generates explanation
Again, I don't want that. It's not a feature, it's a limitation that right now gives you fake information.
> The LLM approach is simpler
For whom? The whole reason I want to consult docs is to get the official documentation on a given topic. How could I trust anything it says, and what’s to say any earned trust is durable over time?
> For whom?
what is the name for this kind of pointless, lazy, selective, quoting that willfully misconstrues what's being quoted? the answer to this question is incredibly clear: for the developer that created this tool. if that makes you unhappy enough to malign them then maybe you should just not use it?
> pointless, lazy, selective, quoting that willfully misconstrues what's being quoted
They quoted the part they were replying to. The point was to show what they were asking about. If your question pertains to only a part of the text, it only makes sense to be selective. That's not wilfully misconstruing anything; that’s communicating in a clear, easy-to-follow way. The context is still right up there for reading, for anyone who needs to review it.
> the answer to this question is incredibly clear: for the developer that created this tool
Questions aren’t only ever asked out of pure curiosity; sometimes they’re asked to make the other person give them more consideration. The question you quote was accompanied by an explanation of how the commenter found the approach less simple for them as a user, suggesting that perhaps they think the developer would have done better to consider that a higher priority. (I might add that you, too, chose to selectively omit this context from your quoting—which I personally don’t see as problematic on its own, but the context does require consideration, too.)
> if that makes you unhappy enough to malign them then maybe you should just not use it?
The author of the extension chose to share what they made for others to use. They asked for feedback on user experience and expressed doubt about their design decisions. If someone finds they might not want to use it because of what they consider fundamentally flawed design, why couldn’t they tell the author? It’s not like they were rude or accused them of any wrong-doing (other than possibly making poor design choices).
lol thank you, I was just going to respond to them. One thing I should mention too is that if it were at all practical to build without using generative AI, someone would have built something similar years ago before LLMs.
6 replies →