Thunderbird launches Thundermail and Pro services to offer an open-source alternative to Gmail and Office365, focused on privacy, freedom, and user control.
I think I’d be pretty pleased with that actually, so long as it’s on my local machine. That’s because I often find myself wanting to locate a particular email that is along certain lines, or on a certain topic, or involves an organisation’s name that kinda sounds similar to this one word but isn’t actually that word or things like “the email where they mention they’ve had a kid” but I can’t actually recall either what they called their child, or what gender they were, or when the email was received. Or actually, even better, in that last example “What’s Dave’s kid’s name again?” and just getting a 1 word, correct response, with the ability to open the email it found where this was mentioned for additional context if I want it. Or things like “how long has it been since we moved out of that house?” and instead of finding the earliest email I can on the topic of moving house and reading emails to surmise when we discussed leaving and then finding which one might have mentioned that actual date we moved out, I could just get an answer, in English again hopefully with a link to the email or emails that provided the rationale for how the answer was arrived at.
Often in those simpler search situations I mentioned where I just need to find a specific email, keyword searches don’t always cut it. I have an absolutely appalling memory so figuring out pertinent details to things happening now based on what was going on in my inbox at some point in the past are a very important way that I get by. If I could achieve this more easily by asking relatively vague, English language questions that will help direct search efforts that are being done for me would be really helpful. Sure, theoretically all existing means of filtering and searching email should eventually find me that message but they’d likely be more effort than just asking directly like you’d ask a person tasked with digging through a filing cabinet for you, and sometimes even after extensive filtering by all kinds of clues: date, senders, keywords, labels, subject lines, emails I remember around the same time that I can find; I just for whatever reason can NOT dig up that email only to discover it later when it’s too late to be useful to me anymore and get to see what obscure reason it was none of my clever search methods caught it…
“AI” or as they were called for the longest time machine learning algorithms can do things like spell check and help with grammar.
The more modern algorithms that they started really calling AI can help format your ideas, can fix sentence structure, and can even translate into foreign languages
Email is probably the most useful place for AI as most of the ones we talk about today are really good at language formatting but don’t really have any intelligence
For example you can write an email cursing out your boss saying “as I fucking told you yesterday” and then ask the AI to rewrite your email in a professional tone so that it says “per my previous email” like sure you can obviously do that yourself but it’s a lot faster to word vomit your thoughts into a computer especially when it’s trivial work related garbage and save your mental energy for your personal time
Trying real hard not to be old man yelling at clouds, but have things gotten so bad people can no longer write a simple email without help with sentence structure?
Probably benefits grow when you shift from simple emails to more complex ones. If you have to send quite a few emails per day and if you can do that quicker and/or better then there’s benefit in using the tools.
After all someone came up with an idea to do away something as simple as us writing ’BR, my name, my company’ in the end of the email - and pretty sure no one would give up that simple feature.
I’m a software developer, not a writer or a salesperson, but I have to do sales to sell my software.
I can write a first draft of a sales email to get my ideas across and then have the AI look at it from a specific perspective I don’t have the skills in.
I dont just take whatever it says and hit send though, I have a conversation with it to tweak things i don’t like, remove things that I don’t think are needed or add things it missed.
Do this for 15 to 20 minutes and I end up with a much more polished email that won’t come across as AI slop with all the personal touches I did want to add.
Just a question on the value of time: If you can’t be bothered to write it, why should anyone bother to read it? Is it really that valuable of a message?
I can spend 10-20 min writing an email that basically says “no your idea is dumb and won’t work” to customers in such a way where by the end of it they agree with me.
It can take a bit of effort but with high stakes communication it’s needed.
If you’re just sending an email to your teacher or whatever it doesn’t really matter.
Just about everyone can use help with sentence structure, like can you convey your point without help? Sure, but your point can be conveyed clearer and with less effort on your part.
It’s like the benefit of autocorrect you can reread your whole email a few times and double check a few questionable words to make sure everything is spelled perfectly or we can have this integrated tool that highlights words that should be fixed and lets you quickly fix those words.
For bullshit corporate emails I personally see very little negative in using a chatbot to make your words sound more professional besides just more of a brain rot
You still have to double check for mistakes. But even that takes less time than writing a 3-4 sentences semi-formal email from scratch.
In any case, your emails aren’t safe either, mate. Even if you don’t use AI, the person on the other side most likely will and your emails will be scanned just the same. Nobody is safe. Which is why this Thunderbird feature doesn’t excite me in the least.
Please signature the email with “Sincerely, <your name> and <name of the AI you used to write this email>”. Otherwise people get very suspicious when they meet you in persona and you come along differently than in your email.
You absolutely do not need AI in order to sound different in one context versus another. I mean, I highly doubt most people on Lemmy speak to their bosses in the exact way that they write their comments here.
Hell, I’d be surprised if they spoke to their friends and family the same way all the time (yes, I’m aware that you can generally be more lax around friends - but there’s a time and place for it, whereas comments on message boards tend to just be lax all the time).
That very concept has been around far longer than “AI” has.
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.
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.
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
Other guy covered it decently. I think it’s also remember to have a little bit of humility and remember that just because you don’t have a use for something doesn’t mean others don’t either. In addition, just because you can’t think of a use for something doesn’t mean there isn’t any. I say this as a huge critic of AI/LLM’s and how they’ve been deployed.
AI audio tools have allowed me to restore audio that five years ago I would’ve said had to be re-recorded or is otherwise unsalvageable.
AI transcription has been one of the greatest gifts to the disabilities community we have seen in decades. It is borderline as significant as screen readers for the visually impaired.
Again, just because you don’t know about applications doesn’t mean there aren’t any. You need to stop speaking out of turd about things you don’t understand. Again, I say this as somebody who is harshly critical of LLM‘s and the theft that trains these systems. There are a lot of different forms and tools that this technology takes.
I appreciate your letting me know that I am wasting my time actually explaining the potential uses of these tools i’m sorry you’re so myopic about this.
Why on earth would I want AI integrated in my email?
I would love a daily digest if it was actually trustworthy.
Eh. You might not, but the “normies” might. Expanding the userbase is always a good idea for open source projects.
I think I’d be pretty pleased with that actually, so long as it’s on my local machine. That’s because I often find myself wanting to locate a particular email that is along certain lines, or on a certain topic, or involves an organisation’s name that kinda sounds similar to this one word but isn’t actually that word or things like “the email where they mention they’ve had a kid” but I can’t actually recall either what they called their child, or what gender they were, or when the email was received. Or actually, even better, in that last example “What’s Dave’s kid’s name again?” and just getting a 1 word, correct response, with the ability to open the email it found where this was mentioned for additional context if I want it. Or things like “how long has it been since we moved out of that house?” and instead of finding the earliest email I can on the topic of moving house and reading emails to surmise when we discussed leaving and then finding which one might have mentioned that actual date we moved out, I could just get an answer, in English again hopefully with a link to the email or emails that provided the rationale for how the answer was arrived at.
Often in those simpler search situations I mentioned where I just need to find a specific email, keyword searches don’t always cut it. I have an absolutely appalling memory so figuring out pertinent details to things happening now based on what was going on in my inbox at some point in the past are a very important way that I get by. If I could achieve this more easily by asking relatively vague, English language questions that will help direct search efforts that are being done for me would be really helpful. Sure, theoretically all existing means of filtering and searching email should eventually find me that message but they’d likely be more effort than just asking directly like you’d ask a person tasked with digging through a filing cabinet for you, and sometimes even after extensive filtering by all kinds of clues: date, senders, keywords, labels, subject lines, emails I remember around the same time that I can find; I just for whatever reason can NOT dig up that email only to discover it later when it’s too late to be useful to me anymore and get to see what obscure reason it was none of my clever search methods caught it…
“AI” or as they were called for the longest time machine learning algorithms can do things like spell check and help with grammar.
The more modern algorithms that they started really calling AI can help format your ideas, can fix sentence structure, and can even translate into foreign languages
Email is probably the most useful place for AI as most of the ones we talk about today are really good at language formatting but don’t really have any intelligence
For example you can write an email cursing out your boss saying “as I fucking told you yesterday” and then ask the AI to rewrite your email in a professional tone so that it says “per my previous email” like sure you can obviously do that yourself but it’s a lot faster to word vomit your thoughts into a computer especially when it’s trivial work related garbage and save your mental energy for your personal time
Trying real hard not to be old man yelling at clouds, but have things gotten so bad people can no longer write a simple email without help with sentence structure?
Probably benefits grow when you shift from simple emails to more complex ones. If you have to send quite a few emails per day and if you can do that quicker and/or better then there’s benefit in using the tools.
After all someone came up with an idea to do away something as simple as us writing ’BR, my name, my company’ in the end of the email - and pretty sure no one would give up that simple feature.
I’m a software developer, not a writer or a salesperson, but I have to do sales to sell my software.
I can write a first draft of a sales email to get my ideas across and then have the AI look at it from a specific perspective I don’t have the skills in.
I dont just take whatever it says and hit send though, I have a conversation with it to tweak things i don’t like, remove things that I don’t think are needed or add things it missed.
Do this for 15 to 20 minutes and I end up with a much more polished email that won’t come across as AI slop with all the personal touches I did want to add.
Just a question on the value of time: If you can’t be bothered to write it, why should anyone bother to read it? Is it really that valuable of a message?
I do write something, and then work to refine it. Like I said, I spent 15 to 20 minutes on it after writing it.
Don’t tell that you need so much time to write an email 😳
Depends on the email. Sometimes it’s needed.
I can spend 10-20 min writing an email that basically says “no your idea is dumb and won’t work” to customers in such a way where by the end of it they agree with me.
It can take a bit of effort but with high stakes communication it’s needed.
If you’re just sending an email to your teacher or whatever it doesn’t really matter.
But that is the reason for templates, no?
A sales email in a tricky situation due to how the potential client responded or writing a personalized cold call email? Of course!
Edit: As I learn and get better at sales I imagine it’d get quicker, but I’m learning while working with the AI.
Just about everyone can use help with sentence structure, like can you convey your point without help? Sure, but your point can be conveyed clearer and with less effort on your part.
It’s like the benefit of autocorrect you can reread your whole email a few times and double check a few questionable words to make sure everything is spelled perfectly or we can have this integrated tool that highlights words that should be fixed and lets you quickly fix those words.
For bullshit corporate emails I personally see very little negative in using a chatbot to make your words sound more professional besides just more of a brain rot
We probably never sent as many emails as we do today, and there are bigger priorities. Wanna blame someone, blame the overly pompous corporate world.
Well I can’t wait for AI to write an email for a coworker that’s full of misinformation. I can’t wait to waste my time with that!
You still have to double check for mistakes. But even that takes less time than writing a 3-4 sentences semi-formal email from scratch.
In any case, your emails aren’t safe either, mate. Even if you don’t use AI, the person on the other side most likely will and your emails will be scanned just the same. Nobody is safe. Which is why this Thunderbird feature doesn’t excite me in the least.
Please signature the email with “Sincerely, <your name> and <name of the AI you used to write this email>”. Otherwise people get very suspicious when they meet you in persona and you come along differently than in your email.
You absolutely do not need AI in order to sound different in one context versus another. I mean, I highly doubt most people on Lemmy speak to their bosses in the exact way that they write their comments here.
Hell, I’d be surprised if they spoke to their friends and family the same way all the time (yes, I’m aware that you can generally be more lax around friends - but there’s a time and place for it, whereas comments on message boards tend to just be lax all the time).
That very concept has been around far longer than “AI” has.
Do you want a serious answer or are you just being flippant?
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 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.
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
Serious. I can’t think of what good slapping AI in there does. Is speech to text that’s existed for decades considered a LLM and therefore AI?
Other guy covered it decently. I think it’s also remember to have a little bit of humility and remember that just because you don’t have a use for something doesn’t mean others don’t either. In addition, just because you can’t think of a use for something doesn’t mean there isn’t any. I say this as a huge critic of AI/LLM’s and how they’ve been deployed.
No, I don’t think humility is the problem. It’s just a bullshit idea that nobody needs.
AI audio tools have allowed me to restore audio that five years ago I would’ve said had to be re-recorded or is otherwise unsalvageable.
AI transcription has been one of the greatest gifts to the disabilities community we have seen in decades. It is borderline as significant as screen readers for the visually impaired.
Again, just because you don’t know about applications doesn’t mean there aren’t any. You need to stop speaking out of turd about things you don’t understand. Again, I say this as somebody who is harshly critical of LLM‘s and the theft that trains these systems. There are a lot of different forms and tools that this technology takes.
You’re going to do all that in your emails?
I appreciate your letting me know that I am wasting my time actually explaining the potential uses of these tools i’m sorry you’re so myopic about this.
The thread is about email though.
You don’t, neither do I. why the hell are they pushing this?
It the jingl8ng of the keys that may sound good to some investors?