Technology

60016 readers

2661 users here now

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related content.
Be excellent to each another!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, to ask if your bot can be added please contact us.
Check for duplicates before posting, duplicates may be removed

Approved Bots

founded 2 years ago

MODERATORS

[email protected]

454

Can we all agree that whatever version of predictive text we have nowadays is crap, and has been for a long time? (lemmy.world)

submitted 7 months ago by [email protected] to c/[email protected]

188 comments fedilink hide all child comments

I'm sick of random capitalisations mid sentence. I'm sick of common words being replaced by less common ones or even downright nonsense. I'm sick of it taking three attempts to successfully get the word I want. I swear it's been like this for five years or more. Can we have a better version yet, or at least the old one back?

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 9 points 7 months ago (1 children)

Yes, fully agree. They make absolutely no sense at all.

Considering that predicting the next word from context is the one thing LLMs are really good at, I just don't understand how none of these developments have found their way into predictive keyboards.

I've actually switched to ThumbKey and while I don't think I'm faster with it (yet), it's at least so much less frustrating and that's worth a lot to me.

[–] [email protected] 4 points 7 months ago* (last edited 7 months ago)

Considering that predicting the next word from context is the one thing LLMs are really good at, I just don't understand how none of these developments have found their way into predictive keyboards.

The problem is that LLMs require a considerable amount of computing power to run, unlike the simple markov chain predictions that keyboards use. You could use a cloud-based service like ChatGPT or something, but most people wouldn't want their keyboards to send all their keystrokes to a remote server... and even if they didn't know or care, the response time wouldn't be good enough for real-time predictions.

Now smartphone SoC makers like Qualcomm have started adding NPUs (neural processing units) with their latest chips (such as the SD8 Gen 3, featured in the most recent flagship phones), but it's going to take a while before devices with NPUs become commonplace, and it'll take a while for developers to start making/updating apps that can make use of it.

But yeah the good news is that it is coming, it's only a matter of "when" - I suspect it won't be long before the likes of SwiftKey start to take advantage of this.