I do wonder when we're finally going to get LLM-level accuracy applied to text input (both keyboard and dictation).
Not to try to do anything predictive, but just to get words right when it would be clear to any human what the intended word would be in context, both gramatically as well as in subject matter.
I have to assume you could do this pretty well with a vastly smaller model that would run on an iPhone.
I mean, dictation on my iPhone is vastly better than it was 10 years ago -- it's usable for a lot of stuff that it simply wasn't usable for previously (dictating brainstorming ideas while lying on the couch, for example). But it still makes a lot of mistakes and just skips far too many words it can't seem to figure out.
I just wish the systems exposed the confidence of their guesses to the user. Should be a big heat map and some drop-downs to focus your review once you’re done. Instead you just see the final results of its guesses (or gaps).
Seems to be an issue across commercial dictation systems, not just iOS.
Really impacts their usage in a hands-off and eyes-off manner.
Not to try to do anything predictive, but just to get words right when it would be clear to any human what the intended word would be in context, both gramatically as well as in subject matter.
I have to assume you could do this pretty well with a vastly smaller model that would run on an iPhone.
I mean, dictation on my iPhone is vastly better than it was 10 years ago -- it's usable for a lot of stuff that it simply wasn't usable for previously (dictating brainstorming ideas while lying on the couch, for example). But it still makes a lot of mistakes and just skips far too many words it can't seem to figure out.