Live data from Hacker News

Apple’s new Transformer-powered predictive text model

jackcook.com

41–50 of 268 posts

Re: Apple’s new Transformer-powered predictive text model

#41

Just give me the option of not having autocorrect change the previous word when I am typing a new one. I don’t move on to the next word unless the current one was correct or I have already corrected it. Why does it assume I’m stupid? It even does this when I’ve picked the completion for the prior word or swiped to type and then made manual corrections. It’s painfully obvious that it shouldn’t be touched again.

And then deleting BOTH words with a single backspace. This is its most irritating behavior.

Re: Apple’s new Transformer-powered predictive text model

#44
post #41

Just give me the option of not having autocorrect change the previous word when I am typing a new one. I don’t move on to the next word unless the current one was correct or I have already corrected it. Why does it assume I’m stupid? It even does this when I’ve picked the completion for the prior word or swiped to type and then made manual corrections. It’s painfully obvious that it shouldn’t be touched again.

And then deleting BOTH words with a single backspace. This is its most irritating behavior.

Settings > General > Keyboard > Delete Slide-to-Type by Word = Off

Re: Apple’s new Transformer-powered predictive text model

#45
post #15
post #12

Earlier quoted context omitted.

> It's a small, fairly dumb LLM. I have no idea whether you really don’t know what “LLM” stands for or are just trolling. Not calling it an LLM actually is more honest marketing precisely because it’s small, and “transformer-based model” is a precise technical description that everybody with even superficial knowledge of the field understood immediately. And I’m actually onboard with most of your other examples. I’d…

I know that LLM stands for large language model. It is still that type of model even though that final parameter count is not very large. They are deliberately avoid "LLM" because it doesn't compare favorably with most.

This model wasn't advertised by apple, someone who is probably not even affiliated with apple wrote a piece on how he found, analyzed and activated a small neural network inside of an obscure folder. There are no misguided "apple fans" to incorrect here.

Re: Apple’s new Transformer-powered predictive text model

#46

Meanwhile my language and dozens of others with hundreds of millions of speakers still don’t get the predictions at all, don’t support multi-language typing and don’t support swipe typing. Typing on a $1000 iPhone in one of these languages is still a 2007 experience.

Even worse, on the Apple Watch you cannot input text at all in one of these languages, as you cannot (!) turn autocorrect off on the watch.

They managed to fit a full QWERTY keyboard on the screen yet made it completely useless.

Re: Apple’s new Transformer-powered predictive text model

#47
post #25

I don't want better predictive text. I need better autocorrect. Something happened about 6 years ago where the quality of the autocorrect fell off the roof, and it's been absolutely terrible since then. I spend too much of my time fighting with either mispelling, flipping to the wrong word even though I spelled the word properly, etc. It has made typing on my iPhone an unpleasant experience and I need it to change. T…

Same with voice to text translation. It's absolutely, utterly, worthless. I end up having to go and edit half the message. Apple can't even get basic things right

I broke my right (dominant) collarbone on Wednesday so I’ve entered the realm of the temporarily disabled user.

So far I prefer iOS because the predictive text above the keyboard (in iOS 16 too) and in particular the speech to text feature has been so good!

The only egregious error that I have encountered has been confusion around the phrase “into” when I mean “in two”. An understandable mistake.

Re: Apple’s new Transformer-powered predictive text model

#48

Meanwhile my language and dozens of others with hundreds of millions of speakers still don’t get the predictions at all, don’t support multi-language typing and don’t support swipe typing. Typing on a $1000 iPhone in one of these languages is still a 2007 experience.

Meanwhile, Microsoft managed to add Inuktitut to its products, despite only 30K speakers in the world.

I think the Czech government needs to intervene. I believe that's what happened with getting Welsh into Windows too?

Re: Apple’s new Transformer-powered predictive text model

#49

Meanwhile my language and dozens of others with hundreds of millions of speakers still don’t get the predictions at all, don’t support multi-language typing and don’t support swipe typing. Typing on a $1000 iPhone in one of these languages is still a 2007 experience.

Well, maybe you're not the target group for this product and company and should buy one from the competition? Also tell it to your friends.

I don't think companies like Apple listen to anything but the numbers.

Re: Apple’s new Transformer-powered predictive text model

#50
post #40
post #32

Earlier quoted context omitted.

I've had a similar experience with autocorrect on Android across multiple phones (lg, samsung) and keyboards (gboard, swiftkey) around the same time, I'm curious to know whether it's just my own bias being validated or something happened. All predictions have become completely stupid (switching languages mid sentence when they were robust in the past, finding least consistent suggestion first, suggesting very random…

Typing on Android was perfect when Swype was still around. GBoard and SwiftKey were worse and seem to actually decline in accuracy till this day.

Swype was the best. Google should buy it and release it as the new version of Gboard
Post reply on HN