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.
Apple’s new Transformer-powered predictive text model
21–30 of 268 posts
Re: Apple’s new Transformer-powered predictive text model
#22Earlier quoted context omitted.
An LLM is a transformer model. That’s the standard, industry term. What are you going on about?
I am very aware of that. Nowhere does the press release say LLM. That's because it's not very large or smart and when compared to most LLMs' "intellectual" performance, it looks bad. By avoiding that term, they are successfully sidestepping an important aspect of the evaluation of this system in the eyes of many Apple fans.
> Nowhere does the press release say LLM. That's because it's not very large
So your gripe is that they don’t have a LLM and didn’t say they did?
Re: Apple’s new Transformer-powered predictive text model
#23Earlier 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.
> It is still that type of model
“That type of model” are called transformers, not “like an LLM but small”. The fact that you didn’t know that doesn’t make it wrong.
Re: Apple’s new Transformer-powered predictive text model
#24I was surprised to see the direct references to GPT2 by name.
It's not an official Apple piece or anything.
Re: Apple’s new Transformer-powered predictive text model
#25I 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
Re: Apple’s new Transformer-powered predictive text model
#26Meanwhile 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.
My biggest multilingual gripe on iOS is that highlighting text in, say, Czech and pressing Translate on the popup just tells you to fuck off.
Like, sure, don't support the language, but at least give me a Google Translate link then.
Re: Apple’s new Transformer-powered predictive text model
#27I 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…
I regularly use 4 languages on my iPhone and my autocorrect is completely broken. I can’t be bothered switching between keyboards, so the English keyboard has just completely lost the plot…
Re: Apple’s new Transformer-powered predictive text model
#28I 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…
Word (or multi-word) prediction is a great starting place for an autocorrect model. If the keyboard I'm using knows the probability of all the possible next tokens I could type, then you can start making the tap targets for those keys bigger. And since the model is super cheap to run, you can replay the last n keyboard taps to simulate a different correction being made. That's at least how I'd make autocorrect better if I worked on the keyboard team.
Anecdotally, I've heard autocorrect is much better on iOS 17. But I won't update until the general release next week.
Re: Apple’s new Transformer-powered predictive text model
#29Earlier quoted context omitted.
An LLM is a transformer model. That’s the standard, industry term. What are you going on about?
I am very aware of that. Nowhere does the press release say LLM. That's because it's not very large or smart and when compared to most LLMs' "intellectual" performance, it looks bad. By avoiding that term, they are successfully sidestepping an important aspect of the evaluation of this system in the eyes of many Apple fans.
you want to compare llama2, inflection1, gpt4 et al. to apple's typing assistant model that is designed to run locally and in a tiny scope? large language model literally isn't accurate for something that's two orders of magnitude off what the term usually describes. if anything, give apple points for not hyping up "LLM technology" or whatever to boost their share price like every other tech-adjacent company is rn.
Re: Apple’s new Transformer-powered predictive text model
#30Earlier quoted context omitted.
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.
> It is still that type of model “That type of model” are called transformers, not “like an LLM but small”. The fact that you didn’t know that doesn’t make it wrong.
[flagged]