[danudey]

> The problem your encountering is downstream from point 1. Basically your keyboard thinks due to the way most people construct a particular sentence, you're gonna want to type "bold" next, despite "hold" clearly clearly making more sense. So it'll force "b" on you 4 times in a row until it realizes you really want to type "h".

In the video, the user is typing 'Thumbs up', and when they get to the first 'u' the keyboard shows a 'u' being pressed but a 'j' is inserted instead. Are you suggesting that, due to the way most people construct sentences, the OS thinks that 'thjmbs' is the most likely word? And then the next time the OS thinks that 'thhmbs' is the most likely word?

Both of the issues you've mentioned are common, and irritating, but if you watch the video you can see that that's not what's happening here. Before any autocorrection or adjustment is being done, the keyboard is registering a 'U' and the OS is inputting a J or H or I or some other nearby letter.

The video also debunks the touchmap discontinuity issues as well, because you can clearly see which key the keyboard is registering; it's not assuming that you meant to press J or it would highlight the J; it's registering a U, highlighting U, and inputting J.

It sounds to me as though you didn't watch the video and just assumed what issue was being discussed; please do watch it, because this is another, relatively new, issue that lots of people have seen and which is far worse and more frustrating than the other legitimate issues you mentioned.

[mrguyorama]

The above commenter is talking about why touchscreen keyboards have become worse over time in general

Apple additionally may have just bugged up their implementation as well, but the above mentioned issues exist even on Android, and didn't a decade ago.

I still contend that the single best touchscreen keyboard and autocorrect implementation was the onscreen keyboard on the Microsoft Zune HD. A tiny tiny screen, and you could still type without looking and nearly always end up with the right text. It was magical, and creepy in retrospect.

But nobody bought it so we had less good keyboards for a decade. Then companies insisted that they could throw "Algorithms" at the problem (which is what we had been doing for a decade but whatever) and make it magically better and now everyone gets worthless autocorrect because of the everpresent "Nobody is actually average so tuning your system to the average makes it bad for everybody" problem that has infected literally all "Data driven" product decisions.

We literally had better text prediction using boring methods. We literally had working voice control on flip phones from the 90s. All on device too.

[walterbell]

We need a github repo with a list of past tech with good taste and poor market timing, for revaluation in newer markets.

[WorldMaker]

> In the video, the user is typing 'Thumbs up', and when they get to the first 'u' the keyboard shows a 'u' being pressed but a 'j' is inserted instead. Are you suggesting that, due to the way most people construct sentences, the OS thinks that 'thjmbs' is the most likely word? And then the next time the OS thinks that 'thhmbs' is the most likely word?

In addition to the other problems (the keyboard being too prone catching extremely subtle slides below UI response time), there certainly is the problem of when you crowd source enough data you crowd source all of their collective mistakes, too. In a lot of that raw data mistakes are going to be as common or more common than corrections and/or originally correct spellings.

We do have a great filter for this called a "dictionary", but as the above commenter laments companies have given up on "just autocorrect to dictionary words" for much more complex "learning" models and filtering them back to just dictionary words is antithetical to the (sunken cost) expense that went into training these models, and/or the KPIs and promotion incentives that keep prioritizing "AI" and giant crowd sourced data vats over simpler mechanics and local user specifics.

[iknowstuff]

No dude it's just a bug. Watch the video.

[robocat]

> it's registering a U, highlighting U, and inputting J

The voiceover is deceptive (unintentionally?)...

They touch the [u] which shows the popover U but you can see them slide their thumb down off the [u] key onto the [j] key.

I guessed that was the issue, repeated it on my phone (SE) and only then looked at video and it's obvious when you see him do it in slo-mo. Edit: I have most prediction turned off (I mostly find slyde typing to be fastest, and I hate automiscorrect on uncommon words).

iPhones are very very sensitive to tap-slides which causes many UI gremlins (a variety of terrible side effects that you can't avoid if you're designing a UI).

Over time, most people seem to intuitively learn not to slide when tapping.

I'm unsure how many designers/developers even notice the effects of slide since they have learnt to avoid sliding? When I watched beginners on iPhones you see them get frustrated by things not tapping and other subtle effects (HTML event interactions, scrollable areas, buttons, inputs).

Same thing can happen on Android. One menu button repeatably failed if I used my left hand - took me a while to work out the issue (and a bit of work to increase the tappable area so a bit of slide was accepted and worked better for neophyte users).

[trymas]

Could it be slide to type issue as pointed in another comment: https://news.ycombinator.com/item?id=46233219 ? Disabling it might help?