What if English is my second language? Undoubtedly being well spoken is associated with higher class. Your arguments will come of as stronger to the reader.
What you really have to ask is will this community be less inclusive because English isn't your first language, I'd say "no" and I hope most would agree.
> Your arguments will come of as stronger to the reader.
That is persuasian, not authenticity, to the OP's point.
That's fine. Your arguments will not come of stronger to the reader, they are strong or they are not and we're all clever enough to read through the occasional grammar error.
And that's where I think the guidelines could be expanded a bit more to restore the balance. Something along the line of 'HN is visited by people from all over the world and from many different cultural and linguistical backgrounds. Please respect that and realize that native English and Western background should not be automatically assumed. It is the message that counts, not the form in which it was presented.'.
Do the best that you can unassisted. There is a chasm of difference between someone coming into English from another language, and someone using Google Translate to submit a post originating another language. French aphorisms are a stellar example of this: I’d rather read “A bird in the bush may not fly into oven” and have to parse out the meaning, than have some AI translate it as “Don’t count your chickens before they hatch”; sure, there’s an iffy [the] grammatical moment at ‘fly into oven’, but it’s such a distinct phrase and carries a lot more room for contextual nuance than having an AI substitute in an American aphorism with machine translation allows for.
(For example: If I’m trying to express a point about how we shouldn’t assume that dinner isn’t “her duty” but is instead “our duty”, a French-like aphorism expressed in English literally as “the chicken won’t fly into the oven unprompted” could plausibly be AI-translated instead as “don’t count your chickens before they hatch”, doing catastrophic damage to the point. To a machine translator those two aphorisms are not distinctive; but they are, even if it’s a weird expression in common U.S. English.)
You make errors and weird constructiona like we all non-native do and maybe eventually learn a bit more of English in the process. Or not. English dominance as the world's... lingua franca (ahem) deserves to have it bastardized ;)
> Humans have a tendency to ascribe intelligence to how well spoken a person or thing is
That’s true. I’m fluent in German, but there’s still a difference between me and a native speaker. I’ve often seen my ideas dismissed, only for the exact same point to be praised later when a native speaker expresses it more clearly.
Most native English speakers consider 'speaking plainly' to be a better indicator of knowledge and expertise than the alternative.
I can understand the sentiment though, as I am learning a second language and in many of our writing assignments we are expected to use (from my perspective) overly formal and complex grammatic structures when writing simple letters. I have come to accept, or at least hope, that this is simply an exercise to ensure that students have fluency with the grammar.
Then it’s even more likely the LLM will change your words to something you don’t intend. And you will never get better at writing English if you turn it over to an LLM.
Honestly I saw a similar answer on a post talking about AI Translation in github comments.
Post the translation as best you can manage, and below it put the same comment in your original language. If someone has qualms with your comment having broken english/mistranslations they are welcome to run bits of original language themselves.
We're all here to talk about tech, and we aren't all perfect little english robots.
Broken and true is more authentic than polished and approximately so. When I see an AI-generated comment or email, I catch myself implicitly assuming it is—best case—bullshit. That isn’t the case if the grammar is off. (If anything, it can be charming.)
Personally, I enjoy reading through comments that are obviously from non-native English writers. They often include idioms or sentence constructions from their native language, which is fun to see.
Besides, this isn't an English poetry forum. Language here is like gift wrapping for an idea: pleasant if pretty, but not the most important thing.
Well... for myself personally, that works, but only up to a certain level of broken. Past that I quit reading.
That may be a defect in me. Maybe I should make a stronger effort on such comments. But I suspect I'm not the only one who does that, and at that point it becomes an issue that affects the community as a whole.
> Broken and true is more authentic than polished and approximately so.
From the perspective of someone reading the comment, I'll take “inauthentic” but actually comprehensible over “authentic” but incomprehensible any day.
Also, using bad grammar as a heuristic for humanity will just end with LLMs being prompted to deliberately mess up their grammar, and now we're back to square one, with the state of the written word even worse off than it was before.
This is an angle for people who default to AI-edited written speech that I've tried to be more empathetic to. I think it depends on your audience, but in professional writing that isn't published publicly (i.e. communication with your colleagues, design docs, etc.), or even the "rough draft" form of something that will be published, I think starting with your own words comes across as way more authentic.
I've seen enough GPT-generated slop that I find its style of writing very off-putting, and find it hurts the perceived competence or effort of the author when applied in the wrong context. I'm not sure if direct translation tools serve a better purpose here, but along with the other commenters, I personally find imperfect speech that was actually written "by hand" by the author easier and more straightforward to communicate with despite the imperfections. Also, non-ESL speakers make plenty of mistakes with grammar, spelling, etc. that humans are used to associating with "style" as authentic speech.
It can also become a crutch for language learners of any age / regardless of their primary language, that inhibits learning or finding one's own "style" of speech
This effect is very rapidly vanishing. Well written English is starting to be seen as snobbish and AI-slop especially with younger generations growing up with AI.
The human touch of someone’s real voice myself, rather than a false veneer will carry more weight very soon.
I think you're right, and I don't know what to think about it. I enjoy writing, aim to write clearly - a skill or discipline that took a lot of time to learn, and ongoing effort to maintain.
I've never sent or posted anything AI-written, beyond a pro-forma job description - because I don't know the domain-specific conventions, and HR returned my draft to me with the instruction to use ChatGPT, which I think amusing, but whatever: the output satisfied them, and I was able to get on with my day.
I occasionally experiment with putting something I've written through an LLM, and it's inevitably a blandifying of my original, which doesn't really say what I intended. But maybe that's good? My wife thinks I'm sometimes too blunt, and colleagues don't always appreciate being told technical details.
I also appreciate individuated writing - including the posts by people on this board are not native speakers. Grammatical mistakes seldom inhibit understanding when the writing has been done with care.
I'm rambling at this point, but it's because I'm truly uncertain how these cultural changes will turn out, and (an old man's complaint, since time immemorial!) pretty sure I'll end up one of the last of the dinosaurs, clinging to my manually written "voice" long after everyone else in the world has come to see my preferences quaint.
The "L" in LLM stands for "language". If they are unable to express themselves in English (or whatever their native language is) fluently, they won't be able to prompt LLMs fluently and will be, in the debased patois of modern youth, "cooked". It's a self-correcting problem.
Trust me, it won't last because I've seen the cycle a couple of times. People pay lip-service to being accepting of variant grammar, but then the downvotes show up.
> written English is starting to be seen as snobbish and AI-slop especially with younger generations growing up with AI
This is tragic. I write English well and will employ grammar and word choice effectively to make an argument or get a point across. English was my best subject at school 45 years ago despite a career in tech. In fact, I’d suggest that my career as an architect and the need to convey concepts and argue trade-offs with stakeholders of varying backgrounds has honed that skill. Should I now dumb down my language or deliberately introduce errors in order to satisfy the barely literate or avoid being “detected” as an AI? (as if the latter were possible. It’s an arms race).
> Should I now dumb down my language or deliberately introduce errors
Language is a tool. If it wins the argument, yes. I’ve absolutely gone back through drafts to tighten up language and reduce word complexity. And if I’m typing with someone who frequently typos, I’ll sometimes reverse the autocorrect. Mostly as a joke to myself. But I imagine it helps me come across as less stuck up. (Truth: I’m a bit stuck up about language :P.)
While this is true, it is not just a tool. Or, I should say it’s a tool with far greater utility than just winning an argument or making a localised point. Language is how we think, and the ability to reason well is absolutely dependent on our skill with language.
Language is the mark of humanity in the sense that how else can I convey to you a fragment of my inner state? My emotions, my feelings, my desires. The language of poetry and literature. That which sparks an emotional response in another.
I agree. But I don’t always see it as dumbing down. James Joyce’s Portrait starts out with a lot of nonsense, that doesn’t mean it’s dumb or dumbed down. It’s just communicating something that is best described that way. Even to an erudite audience.
I have expertise in some topics. I don’t think of communicating that in lay terms to be dumbing down. The opposite, almost: finding good analogies and expressing them clearly is a lot of fun, even if what comes out the other end isn’t particularly sophisticated.
Totally agree. But I’m seeing (or more sensitive to) increasing cohorts that can’t string two words together to express a single thought coherently. There’s a difference between adapting language and use of linguistic tools (such as metaphors) versus semi-coherent blathering.
EDIT: spread > express
Which may be a segue to a point regarding using corrective tools as a form of preemptive editing?
Luckly, something with the English language makes it that especially native speakers quite often have atrocious grammar: They're - their - there mistakes, who/m, the list goes on.
Funnily enough, I've noticed myself getting worse with they're/their the more is use English (which is my third language).
That'd be a "style-over-substance" fallacious argument. Or one could be hoping for a halo-effect to cloud the reader's opinion of their comment because some piece of software made it read like Enron-marketing-hogwash-speak.
That's not substance. That's style being all there is, trying desperately to cover up the lack of substance. Rhetoric works best when it gives wings to strong ideas, not when it tries to fly by itself.
"We pay for 10000 AI bots and it makes awesome software, which is invisible and undetectable by anybody except me. It gives me a sense of pride and accomplishment."
I've build 10+ games which I am ashamed to show :)
Straight JS/html/css front-end with zero dependencies works well.
Ask for a node.js backend and can be instantly deployed as client/server or straight to html - multiplayer feels trivial.
C# Monogame works well for something heavier.
You can actually edit Unity scenes directly using the LLM as they're a readable text file which works ok, but Unity is bloatware when you can code it all yourself (it's an absolute nightmare of inexplicable bugs, do not use it. After updating to 0.62f from 0.48f my clang compiler now segfaults while building Webgl - luckily my team mate can do the builds)
The key is building exactly and only what you want and need. Make your design lean, suit the game as you are actually building it not a theoretical overengineered masterpiece - refactors are cheap later, but bloat will kill your project.
I've had my own rollercoaster relationship with Unity over the past decade, but telling people to roll their own game engine so that they can finally make a game is almost universally terrible advice.
People who want to build game engines should build game engines; people who want to build games should absolutely use Unity, Unreal or Godot in no particular order.
It's no different than needing to build a web framework so that you can make a website. The people who do it are often not even aware that they are procrastinating.
People who are making a simple 2D web game don't need an engine, with rare exceptions. Chrome's 30 million lines is plenty of bloat to build on ;)
Besides, in this context you're already outsourcing all the code to Claude or Codex or whatever. i.e. a "programmer" who has no problem handling the engine side of things.
That being said, most enginedev is creative procrastination. Randy's recent video on this is very illuminating — "I thought if I made a really good engine, making the game would be the easy part!" So he avoided actually making a game for like ten years...
Most 2D games don't even need an engine: you can just make the game "directly", on top of SDL or Canvas or what have you. (That being said, noob friendly stuff like Processing and Kaboom is great and highly recommended!)
--
Source: made lots of 2D games and a few engines. The engines were a complete waste of time. (Even ready made engines often did more harm than good!)
If I was making 3D games, then I would probably need an engine (but js13k begs to differ!), and it would probably not be a great to roll your own (unless you're going for something 90s themed :)
--
Edit: Most of my games are very "programmer art", or very retro. If I were an artist or working with artists, then an engine would be useful for that, for the visual side of things. Flash was probably unmatched in that regard
That being said, it's not that hard to roll your own level editor, so... ;) even that argument is questionable.
Edit 2: Also the web APIs are unfortunately kind of ass, so using a library (or engine) has the advantage of letting you avoid dealing with them directly for the most part.
Problems I've had with unity in my last 3 installs. All LTS default installations on windows. (I have delivered professional projects in Unity in the past):
1. Inspector for lists/arrays works once, crashes editor, must be restarted each time.
2. Race conditions in the basic animator functionality making animation events useless, killed a project because we couldn't edit the underlying code, didn't have time to redo animator-based functionality which should have worked in theory.
3. Segfaults in compiler -> 6 hours of debugging, gave up, still can't build reliably.
Each of these killed the workflow and therefore the ability to deliver the project dead, and were completely out of my control.
Vibe code your engine, at least you'll die on your own terms.
Unity is also just a fundamentally hostile organization waiting to pull the rug, as evidenced by their past behaviour.
Big plus for html/css/js, mostly Pixi 8 or around (I also have a couple threejs). Vanilla JS. I did this by hand before, but having the LLM tweak around the code and styling while I handle more gameplay related things makes this doable (otherwise I just would not have enough free time)
Im using UE5 which is arguably GUI heavier than Unity.
You can get around a lot of the GUI-heavy stuff by using C++ in preference to Blueprint, and/or developing some tools to help you decompile/recompile Blueprints.
It has a pretty cool remote control plugin you can install which can be used to simplify a lot of test cases through automation.
I have a relatively large amount of experience with UE4/UE5 and C++ though, so it's probably not for the absolute beginner or the faint of heart.
I wish that people would just stop with the "vibe coding" thing.
If you want to get quality results from an LLM use a quality frontier model (I recommend Opus 4.5 thinking) in an agentic Plan -> Agent -> Debug loop inside of Cursor. Roughly 90% of the hate that gets assigned to AI anything is a direct result of the absurd notion that taking the human completely out of the loop is a valuable goal. In reality, it's expensive and almost guaranteed to produce crap.
If you treat LLMs as pair programmers and split your implementation into a set of sequential tasks of a reasonable scope, you can use Unity or Unreal or any number of JS engines built on ThreeJS to produce things that are worth playing.
I would strongly argue that pairing with Opus to write your controller code while you take primary responsibility for interacting with the UI sounds exactly like how you should proceed if you care about the end result.
I want to try one to be a bit of a personal coach. Remind me to do things and check in on goals. The memory / schedule / chat thing is enough and it wont need emails or anything more dangerous.
Have you ever seen anyone changing transaction isolation levels in code? I think pessimistic or optimistic locking is preferred way to handle transaction concurrency.
I have recommended that various teams drop down to READ-COMMITTED (MySQL) for various actions to avoid gap locks being taken, but AFAIK no one has done so yet.
For me it is the simplicity of it (transparent minimal system prompts and harnest), you can extend it the way you like, I don't have to install a (buggy) Electron app (CC or Codex app), it integrates where I work, because it's simple (like in a standard terminal on VS code). I'm not locked in with any vendor and can switch models whenever I want, and most importantly, I can effectively use it within apps that are themselves using it as coding agent (the meta part - like a chat UI for very specific business cases). Being in TypeScript, it integrates very well with the browser and one can leverage the browser sandbox around it.
I cannot directly answer your question, because I am looking into this topic myself currently, but I found this HN discussion from two weeks ago, which should give you more insights about pi: https://news.ycombinator.com/item?id=46844822
reply