Hacker News

points by xenator 9 hours ago | 0 comments

Autocomplete should be following the user's own behaviour. If a user thinks that "trans women are men", then it will be not a universal experience, it is just this separated user's own statistics.

[–] hairofadog 8 hours ago

I can imagine that autocompleting following users' behavior could bite people who do a lot of sexting or could reveal other secrets, ex. `the door code is`

[–] howunfortunate 8 hours ago

This is a good solution but you still have to deal with the cold start problem for the ML

[–] throooooo 8 hours ago

Then you just don't suggest anything if there isn't enough data yet. Regardless, auto-complete suggestions is different from what TFA is about.

[–] conception 8 hours ago

Yes, please allow me to have corps not only know everything about me but have a hyper accurate way to know what I’m thinking as well.

Or we could just type the whole sentence we need.

[–] reorder9695 7 hours ago

Futo keyboard on Android has a transformer LM option that uses local ML for text prediction, I've found it to work very well. As far as I'm aware it's completely on device.

[–] SV_BubbleTime 4 hours ago

“Generated entirely on device” seems like an omission that doesn’t cover diagnostic, telemetry, “product improvement” logs.

[–] stavros 6 hours ago

A friend made a keyboard for iOS because he didn't like any of the existing ones, and it doesn't send any data anywhere: https://typeneuma.com

[–] alfjal 8 hours ago

That's asking a lot given the current state of the iOS keyboard.

[–] nostrademons 8 hours ago

It already does this. I've found it'll suggest my kids' names frequently, after just 1-2 letters. It didn't do this before they were born. I assume it's training on my previous messages.

[–] stackghost 7 hours ago

I never understood the memes about autocorrect until I got an iPhone. The keyboard is so much worse than GBoard it’s incredible.