savory_pancake
Joined 4 years ago
Joined 4 years ago
I think the two-tiered input-output approach you propose makes sense. Allowing users to inspect and mutate lower-level languages allows the user to make modifications as needed. I think it's very much in the spirit of free software.
But then again, for text-based search specifically (search engines, notes, etc.), I think there is some value in querying the LLM directly, as it is able to fuzzy search by inspecting its weights. This results in a lesser degree of specificity, which allows for more false positives, but can maybe capture similar words (i.e., synonyms / typos / tenses) or higher-level semantic concepts.
Maybe they're just two different search algorithms, and the user should be able to choose between them.
Thanks for linking the article, I found it very interesting.
Niri for example, tiles but additionally introduces an infinite horizontal space, where you can slide between different windows like they’re on a film strip. The slide into view works with a mouse, and you can easily setup mouse bindings to move and reset windows. I think it’s better than just a stock floating windows manager because it feels easier for me to navigate an infinitely wide left-right and up-down space as opposed to an infinitely deep space into and out of the screen.
There’s always Van Gogh and Starry Night to think about as well.
95% of users might not want the double-textbox, but 5% might, and some might want to use it someday.
I think, make enough of these decisions, and there's bound to be mounting friction for users with different preferences navigating your app.
Ideally, the app should offer a way for the user to intuitively configure the app to their own liking.