The more interesting problem is learning doc -> image directly. With Dropbox's s... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		lspears on Jan 28, 2021 \| parent \| context \| favorite \| on: Machine learning saves us $1.7M a year on document... The more interesting problem is learning doc -> image directly. With Dropbox's scale of data, seems feasible for some data types.

caturopath on Jan 28, 2021 [–]

I'm sure that couldn't leak anything important.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact