my phone occasionally decided to “correct” “that” to “thar”, it is deeply annoying
For me it corrects ‘that’ to ‘thst’ all the time, I wish the was some way to whitelist and blacklist words
you can technically unteach your autocorrect a word but you do have to catch it trying to “correct” it and longtap the culprit, which can be tricky when it only happens sometimes and you have a habit of typing fast
What’s 100x more annoying is when you type a real word but they decide you must have meant something else. That shit makes me bonkers
Gets way worse when doing multilanguage setups
God I can only imagine!
Apple devices seem to arbitrarily swap its and it’s.
i’ve started to believe they know what they’re doing but have malicious intent
My favorite apple auto correct: changing the word before the one you just finished. You mentally verify that it’s correct, type the next word, auto correct fucks up the next word and then retroactively fucks up the word you already moved on from. Absolutely brilliant interface.
this is especially awesome when the first word has already been erroneously “corrected” and then manually fixed. and then apple decides to “correct” the first word again after you type the second word.
I forgot the Alamo
Pepperidge Farm remembers
Will humanity ever make autocorrect that’s more reliable than a Ouija board?
I would assume that LLMs would actually be a useful tool for this (instead of trying to use them for things they are not fit for)
Most Android keyboards are pretty good
Maybe with a direct to brain interface we won’t have to.
I doughnut care of autoconnect changes the meanings of my messages, at least I look likest I spells correction.
It astounds me that we have AI shoulder into every aspect of our lives… except auto correct.
Edit case in point. I typed “shouved” and it corrected it to shoulder instead of shoved
Apple’s autocorrect is based on GPT, of chatGPT fame, but it’s the GPT2 model which came out around 2015. Back then it ran on supercomputers, now it fits in your pocket. ChatGPT uses the GPT4 model which requires really big supercomputers for now.
That’s to train it. Even the most modern version of AIs like deepseek or get can run on a raspberry pi.
Only if you distill it to the point of uselessness (well, even more useless). Otherwise you wouldn’t have headlines like this.
No? I litterally run a local deepseek model on a raspberry pi to use as an alexa-like personal assistant.
Yea I guess it works fine for anything that doesn’t require a real context window.
My phone will not let me type ‘was’ without trying to autocorrect it to SAS. I’ve told it not to suggest SAS multiple times, but no luck. Swiping always works, though, so it’s only when I press each key.
This is the one use of LLMs I actually really want, smarter text prediction!
Huh, that’s weird.
It just keeps trying to sell me a credit card instead.
The best was on the old T9s where you’d try to type mum, but its first choice would be nun.
That’s your fault for not being American
My apologies.
It just works!
Whatever algorithm Google search uses is 1000% better than whatever GBoard does.
Sometimes I think heliboard uses the same algorithm
it really does seem like it, though at least it doesn’t get worse on multi-language setups, which i thought would happen but thankfully didn’t (at least for me)
Weird. I just tried this and actually got alarm.
