> It’s like my whole computer is a toddler screaming “LET ME DO IT!” every time I try to create something.<p>Every autocorrect or auto suggestion ever has felt like this to me, but the volume has been turned up to 11. The otherwise drab Adobe Reader is covered with colorful sparkly buttons and popups suggesting I need not even <i>read</i> the document because it can give me “insights.” First, no you may not ready my proprietary document, nor do I suspect most people using this particular software - I only have it for digital signatures - have permission to share IP with a third party. But mostly, it can sometimes be a useful tool, and the fact everyone is shoving it in my face reeks of desperation.<p>The tech industry is in real trouble.
Obviously the AI version is bland and terrible, but arguably more importantly it has also completely changed the meaning of the message. The AI version:<p>- apologizes<p>- implies the recipient was "promised" this email as a "response" to something<p>- blames a hectic schedule<p>- invites questions<p>None of this was in or was even implied in the original. This is not a "polished" version, it's just a straight-up different email. I thought that style transfer while maintaining meaning was one of the few things LLMs can be good at, but this example fails even that low bar.
<i>There is no way in hell anyone who knows me would get that email and not think I’d been abducted</i><p>This person cares about not putting up a fake identity. That's pretty cool, but social media has exposed that a large number of people are perfectly fine presenting an illusion. People will have no shame passing off well written things as an output of their talent and hard work. Digital makeup has no bounds.
I've only recently started using AI, and have discovered my use or rejection of it is predicated on my feelings for the task. This argument of "authenticity" really resonates.<p>I'm a manager, so when I'm sending emails to a customer or talking with one of my reports, I care deeply - so you might get some overwrought florid prose, but it's <i>my</i> overwrought florid prose.<p>On the other hand, I have to lead a weekly meeting that exists solely to provide evidence for compliance reasons, something out of the CIA's sabotage field manual that David Graeber has probably written about. But is now a thirty second exercise in uploading a transcript to ChatGPT, prompting for three evidentiary bulletpoints, and pasting the output in a wiki no human will ever read.
AI "polishing" tools are essentially a form of anti-compression. Lets take some information represented concisely and needlessly pad it with formalities and waffle so it appears more "professional" (whilst also throwing away useful "metadata" like message tone).<p>No doubt the recipient will also be using some form of AI summarization that strips away all that added "polish" - making the whole exercise entirely redundant!<p>It just feels absurd.
Digital culture was fake and performative and insincere enough before Turboclippy: fuck that with something sharp.<p>It feels like the whole world is turning into an HR department premised on the ideological axiom that killing one man is a murder but killing a million is a statistic.
I think LLMs are transformative but it's incredible to me how unimaginative most product managers have been. It reminds me of the 90s when people discovered GIFs can be put on web pages so every page had to have a hundred of them. It was tacky, as is most embedded AI.
> Kill me if I ever write "Regards" non-irnoically.<p>One time, I couldn't remember the name of the album I wanted SIRI to play, so it kept picking the wrong one. After the fifth or so time, I told Siri, "you're killing me Siri" and it called 911.<p>The future sucks.
I actually use LLMs to <i>unpolish</i> dictation results from MacWhisper[0] to match the way I write in chats. MacWhisper lets you set a prompt to automatically post-process your transcribed output. Here is my prompt:<p>'You are a professional proofreader and editor. Your task is to rewrite this dictation with more casual capitalization and punctuation so it can be used in a chat setting.<p>- Always capitalize "I" and derived words like "I'm"<p>- Sentences should start with lower case letters unless they start with “I”<p>- Replace explicit punctuation callouts with the actual punctuation<p>- No period at the end of the message, but leave periods between sentences<p>- Do not remove commas<p>- Do not change sophisticated words to more common ones<p>Return only the result. Do not add any explanations or comments about your edit.'<p>[0]: <a href="https://goodsnooze.gumroad.com/l/macwhisper" rel="nofollow">https://goodsnooze.gumroad.com/l/macwhisper</a>
I need an AI detector which just straight up sends any generated emails to /dev/null. If you can't be arsed to write something, why should I waste my time reading the slop?<p>Yes yes, languages and translations are a potentially valid use case, but irrelevant for the vast majority of people I communicate with.
The AI polish feels like it was written by someone with only an elementary schooler's understanding of how to write a letter.<p>Even in stuffy institutions like banks and insurance companies, corporate email style is very straightforward and, idk, undecorated? You learn pretty quick that people only skim emails and every word beyond your core message creates opportunity for your core message to be skipped over. NOBODY is writing salutations or 'i hope this finds you well' or whatever other garbage chatgpt thinks the first paragraph should be.<p>When I read historical items on lettersofnote I find that even super old business messages are pretty streamlined and only have some crunch because some runner has to physically find the dude you are writing to.
AI takes the personality out of written communication, and swaps it with a bland corporate persona. I want to know that I am working with actual human beings. It reassures me to know that if something goes wrong, I can appeal to those human beings, and not to soulless corporate automatons working off of a flowchart.
I get the frustration, but I think there’s a hidden assumption in this discussion: that everyone can write well in English.<p>Only about 5% of the world’s population are native English speakers, but more than twice that number use it daily. For many, AI rewriting isn’t about losing personal style—it’s about making sure they can communicate clearly in a language that isn’t their first.<p>It’s fair to dislike how AI flattens unique voices, but for a huge part of the world, it’s not erasing personality—it’s making participation possible.
Is there anyone like me out there who has yet to use AI? I think it's interesting but I have no strong feelings for it. Aside from a few images generated with early image generators I have not used anything else, not even chatgpt. AI search results I mostly scroll past are an exception.
A quick glance suggests that, because the site is pretty far afield of usual HN fare, folks here don't realize that Lawson is the author of several books.<p>I personally do not want you -- for any value of "you" -- to use an AI to "polish" any writing sent to ME. I want the author's actual thoughts, not their thoughts massaged by an LLM.
Why is the author mad? The "polish" button does exactly what you would expect it to do if you understand "polish" as "make polite". If you want to keep your words true and "unpolished", maybe at the risk of sounding rude, then don't use that feature.<p>It is actually one of the first things I used LLMs for, and I still am. Latest example, I received an email from an administration asking me to sign some document, but it contained some incorrect information. I used a LLM to write a nice letter telling them to fix it. I could have just replied "it is not A, it is B", but without some formalism, it sounds rude, and I didn't want to sound rude, I also didn't want to make efforts for that formalism. It may be one of the things LLMs do best, they are like supercharged model letters.<p>Of course I don't do that in informal situations or when I want some emotional connection. By the way, no LLM touched this comment, I don't consider posting on HN a formal situation.<p>EDIT: typoes, but maybe I should have let them in, to show that it wasn't the work of a LLM ;)
The obsessive need for AI developers to make everything into the most banal, inoffensive version of said thing will probably end up being the biggest roadblock for AI taking over human jobs.
My mother is a first-generation immigrant. Her writing isn’t ideal, but AI allows her to communicate articulately in a way, where before she might have been discriminated against
AI creep is like a leaky sewage pipe oozing gray water into everything you'd want to keep it out of. Disabling it is increasingly difficult on every app.
I’m pretty close to wildly unprofessional raging at coworkers sending me LLM-written emails/Slack messages.<p>So far the 21st century seems to be a mad dash to see who can turn off their brain the most.
Yes amusing, since unsolicited polishing, but I sincerely doubt this was forced on our fine humorist. English to English editing or “translation” from snarky to suave is straightforward to understand and fix.<p>But what about translation by professional human translators between languages? is it really any better at preserving the intent and sub-text?<p>Kundera has an amazing essay—- “The Sentence”—-in his collection of essays “Testaments Betrayed” on the woes of translation of, yes, a single sentence from Kafka’s “The Castle”.<p>As he (or his translator Linda Asher) say: The sentence “describes the coition of K. and Frieda”.<p>Under the bar too ;-)
Not a topic I tend to associate with Franz Kafka.<p>When AI systems can match Milan Kundera (translated from the French) then we will have definitely gotten to Pro level. “Write me a brilliant essay in the style of xxxx, on topic yyyy in French, and translate it into Mandarin for grins. I would be a wreck if I had to translate Kundera.
I ran into this exact situation when I went to post something on reddit, thought it was too "rude" and ran it through chatGPT to make more polite<p>After I posted I immediately regretted it. It sounded too structured and should have been more whine-y. Weird, but it would have been more like-able.
What's really annoying is how its idea of "polishing" is just making the email worse. Who could possibly benefit from the recipient needing to sift through more boilerplate to find the actual content of the email?<p>15 years ago I might have imagined that an email sent by a robot would be extremely efficient, including only the relevant information, in order of importance. In 2025 it's apparently the opposite; we're trying our best to communicate effectively and an AI is nagging us to include an extra paragraph of flirtation.
While I find AI to be quite useful in many contexts, I 100% agree with this assessment, and I loath all these SV bubble-dwellers who think our lives should be airbrushed and "polished" for presentation.<p>I think a bunch of Google's Gemini ads highlighted how clueless they were on this subject. Like one of their very first Gemini announcements highlighted how you can get AI to write a caption for <i>your social media photos of your dog</i>. God forbid you actually use your own brain to write an actual human caption (flaws and all) for photos of your dog. Google also highlighted how their Pixel camera AI features can "correct" photos of your kids making funny faces in family photos, because how awful would it be if you didn't look like some sort of Stepford family.<p>I was glad Google finally got a ton of pushback against their ad about using AI for a young girl to write a fan letter to her Olympic idol. Seriously, fuck off with that. Makes me wonder if these marketing folks are actual humans in the first place.
Soon everyone will be texting, emailing etc with an AI secretary doing it all.<p>"AI take a letter and polish it for me..."<p>Maybe even video conferences will use "Polish" to portray a recreated lifelike sophisticated avatar with real time grammar correction. When folks finally do meet in real life, they discover a socially awkward, an illiterate or tactless boor instead of the suave intellect portrayed by the AI.<p>Please forgive my comment, I didn't have any polish for it. LOL
Soon everyone will be texting, emailing etc with an AI secretary doing it all.<p>"AI take a letter and polish it up for me..."<p>Maybe even video conferences will use 'Polish' to portray a recreated lifelike sophisticated avatar with real time grammar correction. When folks finally do meet in real life, they will discover slobs, socially awkward or tactless idiots instead of the suave intellect portrayed by the AI. LOL
Since the standard thing for the marketing side of the industry is to promise blatant absurdities, I'm sure the next big thing will be "Let us maintain your authentic voice by learning from your messages!"<p>Oops, probably too late.
I want a tool that would reverse the content to the original prompt.<p>> "Write a thank you note that sounds sincere to that ahole"
> "Some deep musing on the meaning of life tied to b2c marketing for a LinkedIn post"
I'd be interested in a "polish" feature if it had a drop down where I could select which of my aliases it makes me sound like. It's too easy to use the wrong one's voice here or there.
Even though I am not a fan of it, I can see how some people might want to use AI to improve their grammar, maybe because they are afraid to leave a bad impression.<p>But why would anyone put AI generated images into an Email?
Good news is that AI is equally adept at turning long polite business speak emails into short, blunt, and sweary emails, so you can choose what you prefer.
As a tangent, the other day I read a post of a person who used to be close to Elon Musk and was giving their account of that relationship, and it was translated to Polish via DeepSeek.<p>It was not idiomatic Polish - very far from it really, so I guess depending on the model used here, the result could have been equally disappointing if it was really trying to Polish that email.
I simply do not understand the end game of these sorts of features.<p>Presumably, the idea is to make the other person think you've written the email yourself, and you're a "better"/more corporate/more professional writer than you actually are.<p>But once everyone starts using this kind of transformer, so nobody assumes that anyone else is actually writing the content they're sending out -- what's the point?! Who benefits?
I’d rather get the bland polished version than the “I’m so silly/sarcastic/eccentric” version. Although ideally there’d be an AI setting that makes it both polished and terse.
OneNote now shows the Copilot icon right where I start writing on a blank page. That's infuriating (as much as I see some uses for AI). Fortunately you can turn it off in the 'connected experiences' setting.
I think a lot of people miss the point.<p>If you're already an effective writer, obviously AI will usually only make things worse.<p>But for people where English is not their first language (or whatever language you're writing in), polish is a <i>godsend</i>. It fixes your grammatical errors, vocabulary errors, spelling errors, punctuation errors, and all the rest.<p>Obviously it can go overboard in changing your meaning (as any flesh-and-blood editor also might), and presumably over time these tools will get more refined.<p>But for most people who write intelligent comments here on HN, you are not the target audience for this feature. Well, until you have to dust off your high-school French or Spanish or whatever for an e-mail exchange.
AI does not want to do anything, whatsoever.<p>It's <i>owners</i>, however, definitely want you to fall into lockstep that cooking the Earth for their billion$ is perfectly fine and that waking up to a life of low-impact, serviceful compassion to the Earth and its peoples is just virtue-signalling when, in fact, it is simply virtuous in the face of demented psychosociopaths.<p>Note that this all started with all that digital coin-mining. Just more burning the Earth for fakeass money so callous bastards can get richer.
I had the same initially confusing experience as the author, confusing "polish" for the language "Polish". The product manager should have used AI to get feedback on this feature...<p>I put the following into chatGPT: "I am a developer for an email client. I want to incorporate some AI features to help users write more polished emails. I'm thinking I will have an option that appears under the email body where a user can click "Polish". Can you see any issues with this UX?"<p>ChatGPT: There are a few potential issues or points of confusion with a button labeled “Polish”:<p>Ambiguity:<p>Some users might confuse “Polish” (as in “to make shiny or more refined”) with “Polish” (the language). If your product is used internationally or by non-native English speakers, that label can be unintentionally confusing.
Even among English speakers, “Polish” may not be immediately clear as a writing enhancement feature—people might wonder, “What exactly does it do?”
Lack of Context:<p>If users don’t already know what the feature does, they won’t know what to expect when they click “Polish.”
You may need a tooltip, hover text, or short description like “Improve your text with AI suggestions” so users understand it’s about refinement, grammar, tone, etc.
User Control:<p>How much will it change their text? Will it rewrite in a new style or just fix grammar?
If it makes heavier changes, users might worry about losing their personal style or voice. Be clear about the scope of the changes.
Trust & Consent:<p>Users may have privacy concerns if their email content is being sent to an AI for processing. Even if that’s already in your privacy policy, the feature’s label (just “Polish”) doesn’t convey what happens behind the scenes.
You might consider adding a “What will happen to my text?” link or a discreet explanation about how data is handled.
Alternative Wording:<p>Using a label like “Improve,” “Refine,” “Enhance,” or “Polish Text” might provide clearer expectations.
You might also consider dynamic or contextual labeling like “Improve Grammar & Clarity.”
How to address these concerns:<p>Add clarity in the UI: A short descriptive text or tooltip under the “Polish” button can briefly explain what the feature does: “AI-powered text improvements.”
Offer user choice: Present a preview of the changes before they commit. Let them accept or reject individual suggestions so they feel in control.
Signal the feature’s AI: Some users will want to know that an AI is involved, especially if they’re concerned about style changes or privacy. Labeling it as “Polish with AI” or something similar can help set expectations.
Overall, the idea of a quick “one-click to refine” feature is appealing, but make sure the button’s purpose and functionality are crystal clear—both to avoid confusion and to build user trust.