cross-posted from: https://lemmy.world/post/44912178
Is anyone familiar with the specifics of how Circle to Search (linked) works? I was looking for a FOSS alternative to the google circle to search tool and came across it. It seems to describe its implementation in a clear way on the GitHub page, but I have not validated that it does actually operate using that architecture, or that it keeps to its promises about not caching info that is pulled from its third party OCR tools.
On android it asks for “advanced permissions” which I presume are needed to take screenshots and share these with the third party OCR service. Since I havent validated how it works though, I wanted to check if anyone else has before I provide it those permissions.
You must log in or register to comment.
This app is not free. You are the product and the data is the payment. Every feature is engineered to maximize your engagement and by extension the value extracted from your attention. Calling it free because the subscription is optional is like calling a casino free because you can also just watch other people gamble.
Circle to Search is a solution to a problem nobody asked for. Googles actual innovation strategy has been copying Apple features in a worse way and calling it ambient computing. The actual useful features get deprecated because they do not serve engagement metrics. This is not intelligence, it is design theater.
