If you use the privacy respecting Gboard alternative called FUTO keyboard, you’ve probably noticed that the built in swipe typing is HOT GARBAGE. (Typing this currently with two thumbs for this exact reason.)
Most keyboards improve their swipe algorithms by simply spying on you and logging your typing data. FUTO isn’t about that, so they have built a simple webpage based typing game that you can use to improve their system in an ethical and voluntary manner! Just swipe the website’s keyboard to type a provided sentence.
I love this, they can crowdsource the improvement without invading privacy!
Share with any relevant communities you’re a part of. The more data, the better this gets.
They should simply allow collecting this data via opt-in. I’d gladly provide it, but I don’t want it to be opt-out, because then this feels sneaky.
I don’t think the keyboard does that, it’s a dedicated webpage you visit to help improve it
Yes, that’s the point of my reply. I’m saying it should be built into the keyboard and not just a website, if that wasn’t clear.
The entire point of the keyboard is that it’s not built in. The philosophy behind the organization making it says that it shouldn’t be built in.
Nowhere in their site does it say such a thing, and I think you’re interpreting it the way you want to believe it.
They simply say that people should have control over their information.
I agree. That’s why it should be built into the keyboard, and ONLY activated if the user opts-in. If they don’t, then they will be cutting off their nose, in order to spite their face.
Users will gladly contribute, so long as the path to contribution is the least painful it can be. Opting in via the keyboard app is the only reasonable route to do this; not via some website.
You’re welcome to read their beliefs here: https://futo.org/about/what-does-futo-believe/
If the data needed to help improve swipe accuracy goes to helping improve the product, and is not sold and used as a business model - then that is perfectly within reasonable use of the data as explained by their beliefs page.
https://play.google.com/store/apps/details?id=org.futo.inputmethod.latin.playstore
You’re missing the whole anonymization layer they’ve implemented here. If actual typing data is used, the app can’t guarantee user control of the data after opt-in. The data they’re using here is not private user typing data to begin with.
I’d recommend listening to Louis Rossman’s talks on the subject.
I’m not missing anything, I’m one of Louis Rossman’s Patreon members. I work in the same field as he does (or, well, used to, technically).
The only data they’re collecting is what swipe pattern coincides with which word. You swipe, it mispredicts, you choose the word that it should have been, and poof - a library of swiped shapes -> word gets created.
It doesn’t violate privacy, it’s anonymized, and it helps improve the system for others.
There’s no reason to go to the extent you claim they must.
Ok cool, but I’ll still support this initiative, because as FUTO states, a keyboard should not connect to the internet.
That would require a lot of data privacy concerns to be addressed. Even if it’s an explicit opt-in. The current method uses sample text which can’t include PII. Using user supplied text would almost guarantee they’d get names and other PII in their data set.
I also imagine it’s harder to train the model when you don’t know exactly what the user was trying to type. I.e. Was the swipe detection wrong, or did the user delete the word because they changed their mind on what to write?