Thunderbird launches Thundermail and Pro services to offer an open-source alternative to Gmail and Office365, focused on privacy, freedom, and user control.
Perhaps for native speakers this AI systems might not offer an much of an edge, but it does to those that have it as a second language. I know sometimes what I wrote doesn’t have the best structure, so running it in a filter like this helps a lot without changing the intended purpose
It’s a *lot* better these days. Here’s how you could use it to improve the English in your comment:
Can you point out and characterise the grammar mistakes in the following sentence, with tips on how the writer could avoid similar mistakes in future - “I must admit its been a while, but all these things where horrible last time i played with them.”
Sure — that sentence has a few grammar issues, each pointing to a common kind of slip. Here’s the breakdown:
“its been a while” → “it’s been a while”
Mistake: “its” is a possessive pronoun (like his, her, their), while “it’s” is the contraction of “it has”.
Fix: Use “it’s” because the writer means “it has been a while”.
Tip: When in doubt, try expanding “it’s” to “it is” or “it has” and see if the sentence still makes sense. If it doesn’t, you probably want “its”.
“where horrible” → “were horrible”
Mistake: “where” (a location) is confused with “were” (past tense of are).
Fix: Use “were” to correctly form the past tense of “to be”.
Tip: Say it aloud—“they were horrible” sounds natural, while “they where horrible” doesn’t. If it’s a verb (they were), you want “were”.
“i played” → “I played”
Mistake: Lowercase “i”.
Fix: Always capitalize “I” when it’s a pronoun referring to oneself.
Tip: This is more about habit than logic—just train yourself to always type “I” in uppercase, even in casual writing.
Full corrected version:
“I must admit it’s been a while, but all these things were horrible last time I played with them.”
Pretty sure this use case was solved 3 decades back with spellcheck. Not sure why we need to burn good energy having an AI prompt with the same suggestions.
Well spelling was solved even earlier than that, with rote-learning at school in combination with the very environmentally friendly technologies known as the paddle and cane. What was wrong with that way of doing things?? Is it progress? Or were things better in the old days?
In any case, all the words in the sentence in question are spelt correctly - the problem is grammar. Correctly determining if the grammar of a sentence is correct is a much harder problem than simply checking the spelling of words against a dictionary.
I really don’t think there was any malice intended by them. Pretty sure the intent was more along the lines of"Yes, it has gotten better. Here’s a quick demonstration using the current conversation as context." (which reads very similar to what they said)
They could’ve left it at “Yes it’s gotten better” but I suppose it’s similar to the idea of “A picture is worth a thousand words”. Rather than “Ugh your grammar is terrible.” Of course no one should expect perfect grammar on Lemmy or similar platforms.
(Unless I’m just missing a giant ‘whoosh’ moment here - in that case, I’m sorry)
Yes you got it! The person I replied to was talking about those inline grammar checkers you have in word processors, which are pretty limited in value so I wanted to show what you could do with an LLM, and how it can go beyond just correcting but also helping learning.
I did think about adding a sentence to say to imagine writing in some important official context e.g. a letter to a government agency rather than a comment on Lemmy, but decided in the end it would probably be obvious.
I see the point of the message. I still dont plan to use AI though. English is my 3th language, people who take offense to my spelling errors… Well thats their problem, not mine.
I took no offense to it ;-) I see the point of the poster. But i also don’t think i’ll be using AI to fix some minor mistakes i make because english isn’t my first language ;-)
AI really has come a very long way hasn’t it. It was not that long ago that you had to train the computer on your own voice and even then accuracy was annoyingly bad. Now it can transcribe speech from just about anyone at much better levels of accuracy.
It’s reasonably good although it has gotten worse lately weirdly. Sometimes it just completely ignores what I say or hilarious sound alikes come from what I’m saying. It is a lot better than it was about 5 years ago though.
Yeah I’ve noticed it sometimes seems to get worse. Don’t know what phone you use, but when I use Google’s voice-to-text on Android, I often have to correct mistakes, because it tries to do it word-by-word, but sometimes what I actually intend is not clear until I’ve spoken the whole sentence - and for whatever reason, Google very rarely goes back and changes a word it’s already transcribed. For instance, if I say, “I think your speaking” it’s not yet clear if that should be a “your” or a “you’re”, and it won’t become clear until I complete the sentence/clause.
If I want to dictate a long piece of text, I will use OpenAI’s text-to-speech, which is almost flawless (it doesn’t start transcribing until you’ve finished everything you’re going to say). I appreciate some people don’t like OpenAI, but to be honest, Google isn’t much better, and likewise Apple is not a lot better than Google.
And with the exception of the first, commonplace for a long time.
I would also argue the first use is actually a process flaw if implemented. That’s a great way to make sure no one reads emails, and all kinds of information is lost
Well, i’m interested in a serious answer?
Summary, auto-correct, translation, text-to-speech, speech-to-text
Perhaps for native speakers this AI systems might not offer an much of an edge, but it does to those that have it as a second language. I know sometimes what I wrote doesn’t have the best structure, so running it in a filter like this helps a lot without changing the intended purpose
I must admit its been a while, but all these things where horrible last time i played with them.
It’s a *lot* better these days. Here’s how you could use it to improve the English in your comment:
Mistake: “its” is a possessive pronoun (like his, her, their), while “it’s” is the contraction of “it has”. Fix: Use “it’s” because the writer means “it has been a while”.
Tip: When in doubt, try expanding “it’s” to “it is” or “it has” and see if the sentence still makes sense. If it doesn’t, you probably want “its”.
Mistake: “where” (a location) is confused with “were” (past tense of are). Fix: Use “were” to correctly form the past tense of “to be”.
Tip: Say it aloud—“they were horrible” sounds natural, while “they where horrible” doesn’t. If it’s a verb (they were), you want “were”.
Mistake: Lowercase “i”. Fix: Always capitalize “I” when it’s a pronoun referring to oneself.
Tip: This is more about habit than logic—just train yourself to always type “I” in uppercase, even in casual writing.
Full corrected version: “I must admit it’s been a while, but all these things were horrible last time I played with them.”
Pretty sure this use case was solved 3 decades back with spellcheck. Not sure why we need to burn good energy having an AI prompt with the same suggestions.
Well spelling was solved even earlier than that, with rote-learning at school in combination with the very environmentally friendly technologies known as the paddle and cane. What was wrong with that way of doing things?? Is it progress? Or were things better in the old days?
In any case, all the words in the sentence in question are spelt correctly - the problem is grammar. Correctly determining if the grammar of a sentence is correct is a much harder problem than simply checking the spelling of words against a dictionary.
this comment sucks. let people type in lowercase. lemmy isn’t fucking academia.
I really don’t think there was any malice intended by them. Pretty sure the intent was more along the lines of"Yes, it has gotten better. Here’s a quick demonstration using the current conversation as context." (which reads very similar to what they said)
They could’ve left it at “Yes it’s gotten better” but I suppose it’s similar to the idea of “A picture is worth a thousand words”. Rather than “Ugh your grammar is terrible.” Of course no one should expect perfect grammar on Lemmy or similar platforms.
(Unless I’m just missing a giant ‘whoosh’ moment here - in that case, I’m sorry)
Yes you got it! The person I replied to was talking about those inline grammar checkers you have in word processors, which are pretty limited in value so I wanted to show what you could do with an LLM, and how it can go beyond just correcting but also helping learning.
I did think about adding a sentence to say to imagine writing in some important official context e.g. a letter to a government agency rather than a comment on Lemmy, but decided in the end it would probably be obvious.
I took no offense to the message anyway :-)
I see the point of the message. I still dont plan to use AI though. English is my 3th language, people who take offense to my spelling errors… Well thats their problem, not mine.
I took no offense to it ;-) I see the point of the poster. But i also don’t think i’ll be using AI to fix some minor mistakes i make because english isn’t my first language ;-)
I only capitalize things when my phone autocorrects me or I’m using voice to text like right now
AI really has come a very long way hasn’t it. It was not that long ago that you had to train the computer on your own voice and even then accuracy was annoyingly bad. Now it can transcribe speech from just about anyone at much better levels of accuracy.
It’s reasonably good although it has gotten worse lately weirdly. Sometimes it just completely ignores what I say or hilarious sound alikes come from what I’m saying. It is a lot better than it was about 5 years ago though.
Yeah I’ve noticed it sometimes seems to get worse. Don’t know what phone you use, but when I use Google’s voice-to-text on Android, I often have to correct mistakes, because it tries to do it word-by-word, but sometimes what I actually intend is not clear until I’ve spoken the whole sentence - and for whatever reason, Google very rarely goes back and changes a word it’s already transcribed. For instance, if I say, “I think your speaking” it’s not yet clear if that should be a “your” or a “you’re”, and it won’t become clear until I complete the sentence/clause.
If I want to dictate a long piece of text, I will use OpenAI’s text-to-speech, which is almost flawless (it doesn’t start transcribing until you’ve finished everything you’re going to say). I appreciate some people don’t like OpenAI, but to be honest, Google isn’t much better, and likewise Apple is not a lot better than Google.
And with the exception of the first, commonplace for a long time.
I would also argue the first use is actually a process flaw if implemented. That’s a great way to make sure no one reads emails, and all kinds of information is lost