docsorb

You're touching upon a very nuanced point of identifying the true "intent" behind these words. Do you think the way these models are trained should be different to correctly map the potential intent vs the true meaning?

like your example, "the meeting is at 3pm", _we got enough time_ intends something else with "the meeting is at 3pm" _where the hell are you?_ intends something else. It is not so obvious to get that intent without a lot of context (like, time, environment, emotion etc.)

Might as well use some legit OS fonts to make it even more realistic

I've been working on something called DocsOrb... a mobile app, for now only for iPhone, to help people (ICP: families, students, expats) get on top of all their important documents. The idea is: scan or import files, organize them by life moments (e.g. moving house, having a child), and make them easy to find when needed. And the additional magic stuff like 'select X photos or files, and the app automatically organises them for you in the right folders - this one is tricky because it needs to process their personal docs via AI - which im trying to avoid'

Not trying to pitch, just curious: > Do you already have a system that works for you? > What problems do you run into with keeping things organized and accessible? > Would you even want something like this, or is it a non-problem for most?

Would love honest thoughts. I'm pretty serious about this but want to know the vibe here :)