I posted in the Mac apps forum about a browser I build, and I was told — reasonably enough — that it reads like it was written by a machine, and that the whole thing looks rigged. I answered that where it was asked. This is the part that did not belong in that thread.
Nobody asked me why I do this. I think the absence of an answer is part of what made it look wrong, so here it is, and it is short.
My grandfather was deaf and mute from birth. My grandmother was left disabled after typhus. This was the Soviet Union, where that meant a great deal more than it would now — not because they suffered more nobly, but because the state simply had no place for them, and the weight of that fell on the people around them. Mostly on my mother.
I want to be exact about what this does and does not give me. It gives me no insight into being blind. I have not lived it, and I am not going to claim a share of something that is not mine. Deafness is not blindness, and a grandson is not a witness.
What it gives me is the reason I do not stop. I grew up knowing that whether a person gets to take part in ordinary life is mostly decided by whether anyone bothered to build the thing properly. Usually nobody bothered.
That is all. I am not asking for anything here and there is nothing in this to buy. It was a fair question and it deserved a plain answer instead of silence.
Dmytro Liesniak
Comments
The issue isn't your intent - it's the generated prose
Tragic family history aside, the core criticism remains unaddressed.
You state you want plain, honest feedback, yet every update, bug response, and personal explanation is written in the exact same distinct, highly stylized LLM-generated prose. Using an AI to polish a personal post about your family creates a jarring disconnect between the claim of transparency and the medium being used.
Automated tools can fix markup, but when human-to-human communication is run through a text generator, it looks like an attempt to simulate empathy rather than offer it.
People are so ungrateful for hard work
And you wonder why decent suggestions and decent apps in these features don’t come because people are ungrateful when people try how about constructive positive feedback instead of being jerks to people
Tell Us: How Good Is Your Russian?
@DaniilGusev, how good is your Russian?
Are you offering to translate for all of us? If not, why complain?
If using AI allows him to communicate with us, isn't that a good thing overall? Near real time translation was something out of science fiction not too long ago. If he was a native English speaker using this tech out of laziness, then sure, I would probably pile on with criticism as well. But if he finds English difficult, why not use whatever tools we can to bridge the communication gap?
My take
I know it's a hot topic, using LLMs to write. Maybe for those of us who do need to use it, labelling it as such might be a good practice. Written with assistance from LLM, or something similar. I think people, quite rightly, get upset when others attempt to pass off generated text as their own work. The ideas are still their own, it's just that language is precious, and how we say something is almost as important as what we say. Automating this removes a portion of the credibility.
can't agree more
I am severely disabled myself on top of my blindness, and I am quite frankly sick of seeing posts where people find nothing better to do than to pile on someone's words just because it is llm generated.
Sometimes, but not always, I will resort to using llm to convey what I am trying to express in writing because I genuinely couldn't otherwise. This is not about laziness. This is not about struggling with a language I do not know. But in the end, the result is the same.
There is no need to treat us like we're less of a being than you are because we have to use llm to communicate correctly.
There is a big difference between translating and generating
My native language is Russian, and I use LLM tools to help translate and refine my messages into English as well. There's nothing wrong with using AI to bridge a language gap or improve grammar.
But using AI to translate your own thoughts is very different from posting raw, prompt-generated filler.
The issue here isn't English proficiency. It's the unedited, distinct LLM tropes and melodrama left completely unchecked. When someone claims total transparency while posting unedited bot-prose pretending to be a heartfelt confession, it just feels disingenuous.
My thoughts
I'm in the camp of either do it well or don't bother trying. That's probably why I abandon all my personal projects, that and because I have lots of ideas and the required experience to build almost anything that comes to my mind. I only work well in an environment where someone else accepts the responsibility of telling me to push forward because it's already good enough. I'm a perfectionist, not for fear of being judged, but because I am completely unsatisfied with the quality of software these days, especially cross-platform or vibe coded software.
I feel that if the user interface is such a huge chunk of your project that it requires a cross-platform framework, then your project should not exist as it lacks a useful business logic. Browser engines are somewhat exempt from this rule since browsers are all about user interfaces, but for other kinds of applications, there are no reasons to not go native. Rust is a native language that's perfectly suited for the business logic; it doesn't integrate well with the Swift Package Manager so it cannot be integrated properly with Swift libraries, but it does integrate with Xcode's support for external build systems so there's absolutely no reason to not write the cross-platform business logic in Rust and the UI in whatever happens to be the native language of the platform's frameworks for user-facing applications.
Then there's AI. I'm personally against using AI for writing code, not for fearing competition but because the code generated by AI is generally subpar compared to what I write. There are lots of good use cases for AI in development, like reviewing, debugging, and even learning, but generating code is not one of them. AI is terrible when it comes to structuring code, learning implicit conventions, reusing existing implementations in the codebase, and even deep thinking beyond what was in its training corpus, because it cannot do one thing that humans are good at which is to apply knowledge from one area into another, and that is because it lacks the deep pattern recognition abilities currently only present in the human brain. Even if AI was good at coding, current models are still totally unsustainable in terms of economical and power resources. I don't know if you used AI to generate any code for this project, but if you did that's one more reason for me to avoid it. The simple fact that you did not know what user agent string was being announced leads me to believe that you don't really know much about the codebase and thus its likely largely vibe coded.
Finally, a web browser is an extremely critical product that exposes a huge attack surface, so security should not be taken lightly. This means that I simply don't feel comfortable trusting anything other than a major battle tested browser. Modern browsers deal with way too much personal information and authentication to be taken lightly.
Regarding using LLMs for translation
I personally look down on anyone who uses LLMs to generate anything at all, and that includes translation or even just grammar. The existence of LLMs should not be an excuse to not learn proper English, which is not my native language either, but that doesn't stop me from constantly trying to improve my normative US writing and speech. Mental laziness is what bothers me about most people. If you don't want to put the effort into studying a subject, then don't try to project yourself as an expert when you are, in fact, on your toes.
Judgmental
I can't believe I just read, basically "I look down on you" and "just learn English".
By the same token I would say "just learn good manners". If you can't write with respect, then maybe ask ChatGPT to rewrite it for you. I would rather read something generate by an LLM than someone who has managed to be rude all on their own.
I'm sorry that Dmytro felt the need to come in here and justify himself given that he isjust trying to do something positive. And from what I can gather he seems very open to constructive criticism. So maybe if we can stop with the snobbery and personal attacks we might be able to have a proper discussion.
Completely agree with you
I completely agree. I couldn’t believe the attitude I was seeing on here. No wonder why people are hesitant to develop things for us. It was somebody that I read that was genuinely trying to help. You genuinely cared to know what we have to say. now we can do is be completely rude on here really what is wrong with this Community sometimes. I’ll never understand that. I would say the same thing if this recited people by the way, this has nothing to do with the blind people being nice to everybody it’s just a general common courtesy, regardless of disability or not it’s called human being nice to other humans. Who’ve been doing nothing but trying to be helpful to you.
Sorry
I do hope my comments weren't taken too harshly. I think, as an author, I do feel threatened by LLM writing which results in my dislike of it. It's a tool. If people need to use it to achieve their ends, not a problem at all. I think it is good practice and polite to mark it as such.
(This was written by a plonker.)
That's just
That’s generally just how some people are. Some people cant help but be judgmental, prejudice, etc., what have you, it’s in their nature. me? I much prefer to use the philosophy of, if you don’t have anything worthwhile to say? Wizer to keep your mouth shut. that said, it’s not surprising that people leave the community after seeing attitude like this? Can’t say I’m surprised, but its, not gunna be the last time we see things like this, i'm sure.
Regarding artificial intelligence? I don’t care. why would I care if somebody writes using artificial intelligence or otherwise? Frankly, it’s unimportant in the larger scheme of things, of course, if you’re secure in your writing, which I am. If you’re not? OK, I guess I can start seeing how this would bother people, although i disagree; getting your pants in a wad just because, oh somebody wrote with AI! Come on. There’s better things to waste your energy on. Tbh seeing the insecurity of some here as far as oh AI bad etc of some here... Interesting. Very, very interesting but, I digress. Granted everyone has their own opinion, I just don’t see why everyone has turned this into such a big deal; its, really not. The browser? That I’d get, because that’s way more complex, and it has way more vulnerabilities. I myself don’t think I would have any need for this, but again, that’s just me. However, this seems pretty neat, so I’m glad someone made it even if I don't have need for it in this very moment.
@Oliver I mean fair, But, I’m an author as well, and I couldn’t care less or feel threatened by the use of AI. Again, my 2 sents, But, no use feeling threatened, yes, AI can produce good results, but as well as a human? No, not with the same level of creativity etc.
Nice one
Isn’t it lovely these days How critical people Love being? Why, advice, if you don’t like the product, don’t use it and get on with your days. Genuinely, you’re not forced to use it or even to engage with the developer. Also a lot here of looking down on a project. Its a working release so I mean, if you’re that angered by it, make one better
@ mr grieves
One of the best replies I have read in 2026. Well written!
For god's sake
You created an app for a target group who didn't like your app for various reasons. An AI generated text won't make people like it more unfortunately.
It's called brutal honesty
I demote mental laziness with criticism, because that's one kind of behavior that I totally loathe in humans. I mean if you don't want to spend the time learning something, then why would you want to pretend to be an expert? It's fine to not know, I don't look down on ignorance, I look down on pretense. The problem with promoting pretense is that we are promoting a society without substance that's increasingly at risk of crumbling. The promotion of pretense is the reason why we elect bad politicians, it's the reason why our fundamental rights are quickly getting eroded, it's the reason why we are currently regressing as a civilization for the first time in human history.
When it comes to coding, I only reach for AI to learn math, which I find it exceptionally good at teaching. I have a very good spatial awareness and thus geometric explanations work the best for me, so being able to ask a tireless teacher to explain things in geometric terms helps a lot. Since I'm blind, I also have a problem reading math notation, so as part of my questions to AI, I also ask it to express math formulas in Python code, because to me it's important to know exactly how everything works so that I can confidently innovate by improving what already exists or even rebuild it if it ever becomes necessary.
When I was in middle school, my English was terrible, mostly because I saw no use in learning it, but then in 1996 a game called Duke Nukem 3D came out with the Build engine's map editor, and lots of kids my age were publishing maps to the Internet. Back then I was yet to have Internet access at home, but gaming magazines were shipping those maps in CDs, and the documentation for the Build engine came with a template to describe the maps that people published. It was at that point that I realized the importance of learning English and started trying to put real effort into training myself by writing essays. I also think that we should all put an effort into learning a common language, and English is at the best position to be that language for historical reasons. This puts native speakers at an advantage, but I have no problem with that, the world is not fair, and it won't be until we we decide to put some real effort into overcoming the barriers currently keeping us from evolving as a species.
Lastly I think that it's fine to use technology as a scaffold for learning, but not to grow dependent on it. As a blind individual, I take advantage of technology to guide me to places that I'm not familiar with, but I also make sure to learn as much as possible about the landscape to break my dependence on technology as soon as possible. A couple of months ago I even learned how to navigate completely by echolocation, no cane, no guide dog, no human guide, no nothing, just me with my exceptionally good spatial awareness, hands and mouth to make noises, ears to pick back sound cues and reflections, and feet to walk and feel the floor. These days I can walk around my neighborhood without aids so confidently that some people simply refuse to believe that I'm absolutely blind with no light perception. This is the kind of society that I wish to promote, a society where no matter the odds, everyone is able to fend for themselves, and depending on technology, especially technology that requires us to be constantly connected to a network, is not the way to get there, because it's not guaranteed to be always available.
Editing to correct the spelling of ears.
Editing to switch the text format to Markdown.
Joao
Your points are valid, and I do see them. I feel though, like some people may not be great at writing things How they’re meant to come across. Example being that if you’re not great at writing things, and english isn’t something you’re competent in, maybe it’s a mix of being able to express yourself. I know for me, I’m not great at explaining what I mean, while I don’t use AI to write stuff for me, I know sometimes I’m miles off of what I mean. I can explain things face to face, but can’t always word them when typing, and that’s from me, and english is the only language I know. So your points are totally valid, I’m just doing what I’m famous for and looking deeper, maybe even too deep
Unrelated but a side note about language learning and llm
But llm is great at language learning, especially english for the obvious reason that virtually all major datasets are english first. That being said, I believe that tutor are necessary at the beginning and llm are the most useful tool ever for intermediate and above language questions.
I fully agree with @João Santos about browser security and such, but we also have great example of actual developers using vibe coding to just expedite their work. The first example that comes to mind is the teamtalk new mac client. But again, if you are a good developer, llm will only drive you upward, not down, unless you become lazy along the way which is a real risk (experience! Just from a bad student, me. :) )
Also agree on math and geometric description from llm, very helpful.
HTH
And this is how
And this, ladies and gentlemen is how we steer developers away from not developing for us or making their apps accessible. I swear the community acts so entitled and rude! If you don't like the product then don't use it!
Tell Me I Did Not Just Read That?
I did not just read the exact words "look down on"?
My thoughts
I'm sorry this post ever needed to be written, but, Dmytro, I commend you for writing it, LLM or not. I'll begin by saying that if you would like to have an open discussion with a blind developer, you are more than welcome to reach out to me directly via my profile here and I will gladly assist you in any way I can.
I did see the post about the browser and in full transparency I didn't try it personally, because I don't have a problem with the browsers I use, and therefore am not seeking an alternative. Unfortunately some contributions to this thread, the the app thread, and other threads by certain individuals further highlight the issues with some members of the blind community. Those who have said in this thread and others that this behaviour will discourage developers building apps for the community, or with community involvement, are absolutely right. i wouldn't go out of my way to develop an app for the blind community, and I myself am blind!
On the subject of AI. I am not wholely against vibecoding, when it is used sensibly and when the output is checked by a developer. I wouldn't choose to use a vibecoded app without checking it first. There are plenty of vibecoded apps being produced by the blind community especially, but many if not most of them are open source, so you are free to review the code and determine whether you wish to use it as-is, refactor it to meet your personal standards, or pass it by. I do believe that anybody interested in coding to the extent that they will put the effort into a vibecoded app should also take the time to learn the basics of their chosen programming language, or at least some general multi-language concepts, so they can check their work. I am happy to contribute my own code to vibecoded applications, or assist vibecoders in fixing issues with their apps providing they show some willingness to learn.
Ai models can in fact produce excellent, if not exceptional code under the right direction. It isn't the norm, but it isn't impossible. I am not a vibecoder but I do use AI as part of my workflow, as do the vast majority of developers. The tools we use are evolving and if you refuse to learn the latest tools, AI included, you will only be left behind.
One thing that troubles me is the immediate accusation that something is vibecoded or written by an LLM. It may be because it isn't perfect, because the product copy isn't refined, or even the feature count. I had this early on when I released the beta of Simulcast. Just because code doesn't meet your standards, just because an app looks unfinished, just because iterative work happens quickly, it does not mean an app is vibecoded. To inform a developer that their app was produced by an LLM without the facts is a slap in the face. By all means ask the question, but if you write me and say "how did you vibecode this?" or a variant of, prepare yourself for the impolite response you are likely to receive unless you catch me in an unusually tollerent mood.
I have no issue with somebody using LLM for language translation. I am ignorant when it comes to learning languages other than English, and I'll freely admit that even English fails me often. An LLM is a tool. If it helps you communicate your point, use it. Otherwise, by all means, speak your native language. Translation is only a click, tap or keyboard shortcut away, and you have as much right to use your native language as we do English. I'll happily make the effort to write you back in your native language, providing you excuse any translation mishaps!
It ultimately comes down to respect, and treating others with respect regardless of how you perceive their work or their actions. Unfortunately I'm seeing across online blind communities, not just on Applevis, a shift towards negative, petty, entitled, personal and destructive behaviour.
You can be honest and constructive, without being unkind. You have every right to dislike an app, and you have the right, especially when asked, to advise any app developer how they could improve their product. There is no place for rudeness, personal attacks, or looking down on those you consider beneath you in skill or talent. There is no place for entitlement, this life owes you nothing and being blind doesn't change that.
There is no excuse for some of the disgusting behaviour displayed by some of the keyboard warriers in the community. If you're one of them, get off your high horse and make something of your own. Make something of value to contribute to teh community rather than putting down others who try to do the same. Show us your work and let us criticise your efforts.
I've wanted to write a thread on this for some time with examples. Unfortunately this subject I find maddening and it requires great restraint which is something i don't usually possess.
People are too free these days
As said earlier, if you don’t like the product, don’t use it. There’s no need to appoint yourself guardian of the world’s languages. Unfortunately, the blind community seems much the same everywhere, gossip and and endless criticism, as though some people have nothing better to do.
Re: People are too free these days
Unfortunately some really don't have anything better to do. Unemployment is high in the blind community, and to be honest, it's something i've never understood. I get that employers are often hesitatnt or refuse to employ disabled people, I've experienced it first-hand and it's why I'm self-employed. But if you can use a computer sufficiently to test an app, or even to visit a website and spout the nonsense some of them do, you are perfectly capable of finding or making work for yourself and contributing in a positive way to society. I don't subscribe to the "I can't work" attitude, especially given the number of blind people who are skilled beyond the norm in coding or technology out of necessity. If you have a skill, any skill, it likely has value. Whether you choose to use that skill to contribute, to achieve anything meaningful and productive, or for financial gain, is a choice.