Yes that is definitely what I was going for, thank you

Comments

• Vespair@lemm.ee ⁨1⁩ ⁨month⁩ ago

  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

  source

  • Gonzako@lemmy.world ⁨1⁩ ⁨month⁩ ago

    Gets way worse when doing multilanguage setups

    source

    • Vespair@lemm.ee ⁨1⁩ ⁨month⁩ ago

      God I can only imagine!

      source
  • LodeMike@lemmy.today ⁨1⁩ ⁨month⁩ ago

    Apple devices seem to arbitrarily swap its and it’s.

    source

    • affiliate@lemmy.world ⁨1⁩ ⁨month⁩ ago

      i’ve started to believe they know what they’re doing but have malicious intent

      source
• solarvector@lemmy.dbzer0.com ⁨1⁩ ⁨month⁩ ago

  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.

  source

  • affiliate@lemmy.world ⁨1⁩ ⁨month⁩ ago

    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.

    source
• joyjoy@lemm.ee ⁨1⁩ ⁨month⁩ ago

  I forgot the Alamo

  source

  • Pinklink@lemm.ee ⁨1⁩ ⁨month⁩ ago

    Pepperidge Farm remembers

    source
• DankOfAmerica@reddthat.com ⁨1⁩ ⁨month⁩ ago

  I doughnut care of autoconnect changes the meanings of my messages, at least I look likest I spells correction.

  source
• gmtom@lemmy.world ⁨1⁩ ⁨month⁩ ago

  It astounds me that we have AI shoulder into every aspect of our lives… except auto correct.

  source

  • ayyy@sh.itjust.works ⁨1⁩ ⁨month⁩ ago

    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.

    source

    • gmtom@lemmy.world ⁨1⁩ ⁨month⁩ ago

      That’s to train it. Even the most modern version of AIs like deepseek or get can run on a raspberry pi.

      source

      • -> View More Comments
• earphone843@sh.itjust.works ⁨1⁩ ⁨month⁩ ago

  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.

  source
• JohnDClay@sh.itjust.works ⁨1⁩ ⁨month⁩ ago

  This is the one use of LLMs I actually really want, smarter text prediction!

  source

  • DragonTypeWyvern@midwest.social ⁨1⁩ ⁨month⁩ ago

    Huh, that’s weird.

    It just keeps trying to sell me a credit card instead.

    source
• shneancy@lemmy.world ⁨1⁩ ⁨month⁩ ago

  my phone occasionally decided to “correct” “that” to “thar”, it is deeply annoying

  source

  • biggerbogboy@sh.itjust.works ⁨1⁩ ⁨month⁩ ago

    For me it corrects ‘that’ to ‘thst’ all the time, I wish the was some way to whitelist and blacklist words

    source

    • shneancy@lemmy.world ⁨1⁩ ⁨month⁩ ago

      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

      source
• DakRalter@thelemmy.club ⁨1⁩ ⁨month⁩ ago

  The best was on the old T9s where you’d try to type mum, but its first choice would be nun.

  source

  • __nobodynowhere@sh.itjust.works ⁨1⁩ ⁨month⁩ ago

    That’s your fault for not being American

    source

    • DakRalter@thelemmy.club ⁨1⁩ ⁨month⁩ ago

      My apologies.

      source
• Proprietary_Blend@lemmy.world ⁨1⁩ ⁨month⁩ ago

  It just works!

  source
• TheMinions@lemmy.dbzer0.com ⁨1⁩ ⁨month⁩ ago

  Weird. I just tried this and actually got alarm.

  source
• __nobodynowhere@sh.itjust.works ⁨1⁩ ⁨month⁩ ago

  Whatever algorithm Google search uses is 1000% better than whatever GBoard does.

  source
• Sam_Bass@lemmy.world ⁨1⁩ ⁨month⁩ ago

  Sometimes I think heliboard uses the same algorithm

  source

  • brachypelmasmithi@lemm.ee ⁨1⁩ ⁨month⁩ ago

    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)

    source