If the developer can't be bothered to not make it look vibecoded I assume there's a minimal amount of thought and effort put into it. And in that case I'm not going to bother using it.
Maybe this developer didn't bother I didn't even look frankly.
My point was that you can have very well designed and thoughted apps with LLMs. In fact, I'd argue you can go way further and deeper than any manual coded application paired with AI assistance.
But maybe this instance is not the case. But even if it turns out to be not the case, if the app does work and serves the utility you are after, then why not using it? People use many things in everyday life without thinking about what thought was put into it..in fact, most people don't think at all about what it took to build anything, and how it was built..
Do you really know or care if the shoes you wearing was handmade or built by a factory in china using robots? you probably don't know and don't care.
> My point was that you can have very well designed and thoughted apps with LLMs.
If that were the case here, then a user of the app probably would not come away with the impression that it was a "very much LLM-aided app."
You're talking about how LLMs can be used in such a way that they help production of an app but remain invisible to the end user. But the beginning of this thread was someone using the app and coming away with the impression that it was heavily LLM influenced, which suggests that it was not done thoughtfully and did not remain invisible to the user.
I get it, and frankly I don't know about this app.
But the parent comment positioned itself against all "LLM-aided apps", the author didn't say a slop or poorly coded. And even if it looks like LLM coded, we still can't tell about the level of thought that went into it. Developers had many poorly coded UIs and yet the apps functioned well and served it's purpose.
So the entire chain of reasoning is a form stereotype forming. Looking at this specific app, I can see that the author thought about the marketing/business and functionality, more than other alternatives, maybe because they had more mental bandwdith to do so.
To be fair, I personally only said that I'd like a label that indicates whether an app has "had thought put into it". That could involve e.g. another human reviewing the code and architecture and giving it a stamp.
I hand written each one of them, I think they are full of typos and grammatical errors as well since English is not my first language.
I assume you are saying that because I apologized. I apologize for sounding like AI, I assure you it was hand written and I put thoughts into those comments.
I don’t see how this comment is “against all LLM-aided apps.”
> But... I get a "buy merch" popup the moment I open the page, and there seems to be a pro option for what seems to be a very much LLM-aided app? ...IDK, rubs off a bit wrong IMO. Just my personal opinion.”
Again, if the user of the app comes away with the impression that the app “seems to be a very much LLM-aided” then the LLM usage has affected the end product.
I think people are judging mainly the UI of the app. This is closed code app so they don't know, but they are judging by patterns in the UI and/or wording of documentation. And I think it is mainly tech or artists or whoever else is impacted by the AI usage.
That is not say there are really mindlessly produced apps out there. But the comment made it sound that anything LLM-aided is negative.
But what does this has to do with LLM-assisted coding? I wouldn't trust this app even it was manually coded.
In fact, given the recent reports, in terms of security, one is better off consulting LLMs on the exposure surfaces. Something a solo developer can now do cheaply but in the past required a lot of specialized knowledge.
> But what does this has to do with LLM-assisted coding?
What does "LLM-assisted coding" have to do with the question I answered? Here's that question again:
> if the app does work and serves the utility you are after, then why not using it?
Note that this question does not contain any reference to "LLMs". Indeed, an LLM-generated product can contain adware, spyware, or trojan horses just like a human-written one.
For additional context, this app in question seems to actually contain adware and spyware, and has a closed source codebase, so might contain a trojan horse as well.
Those seem like pretty good reasons to not run this totally-vibe-coded software, so I'm sorry, but I don't understand your argument that LLMs make this okay or not okay or whatever.
My comment was about not equating every LLM assisted app as poorly thought of. Your comment is about this specific app, and I personally would not install this app regardless of how it was coded.
But again in terms of security since you brought it, I'd argue that having LLM assisted coded app might be secure than manually coded application given the recent advancements. Again, this is a generic statement, not specific to this app.
The original discussion was not about every LLM assisted app, it was specifically about vibe-coded apps, particularly ones with so little human input that experienced coders can tell they were vibe-coded.
Your later comments generalizing to "every LLM assisted app" seem like a bit of insecurity you might be feeling for using LLM assistance. No need to feel that way. LLM assistance is okay. We're discussing something different from mere LLM assistance.
That is the original comment: " for what seems to be a very much LLM-aided app? "
The author mentioned LLM-aided app, not even AI assisted; nor vibe coded hence my reaction. I don't have insecurity from using LLM nor from coding manually. But I noticed a trend in people thinking and biases and it threw me off hence the comment.
My original comment was heavily downvoted and furthermore some of my comments were accused of being written by AI meanwhile I'm writing it by hand. Again, people are taking tribes/camps, if you speaking of insecurities, it actually the opposite clearly, many programmers are worried of being displaced and automated. And I do understand the concern, I'm just stating the fact that one can have very deeply thoughted LLM-aided app.
It did make it easier to generate thoughtless apps, I agree.
But this process is new, and not every AI assisted app is thoughtless. In fact, I'd argue that if a person put more thoughts and amplify their abilities with AI assisted coding, then the total sum of mental labour exceed that of any manually coded app by huge margins.
I'm not sure about this particular app, haven't looked into it. But I was merely commenting about the mindset of the parent comment.
If one person knows how to code, they don't need an LLM. I've tried using all of them on my job, and I will give them a second chance time by time (to see if the claims made by these big tech hold up) and ALL of the time I've didn't noticed any speedup compared to coding manually.
If you are an experienced programmer (not someone that did an online course and calls like this) with YEARS of experience in coding in multiple languages really, the only real limitation is the speed at which you can type on the keyboard, that is usually way faster than what the even good LLM is able to emit tokens.
This not considering token expense: if we see at the point of view of the company, it's way cheaper an experienced programmer, that in my country costs you 4000 a month tax included, than the tokens that an LLM would use to do the same job.
On top of that there is the environmental impact of all of this, and why they are almost making me not use my car because it's euro 5 and now there is euro 6, these AI companies are emitting tons of CO2 to do stuff that human beings can do with 1/1000 the energy that these AI companies use.
"if one person knows how to code, they don't need an LLM. I've tried using all of them on my job, and I will give them a second chance time by time (to see if the claims made by these big tech hold up) and ALL of the time I've didn't noticed any speedup compared to coding manually."
I mean, have you truly tried? do others thing this is true? I'm truly astonished if that is majority experience, I think we need to get surveys on this.
The entire draw of coding with LLMs is that you can generate programs without knowing how to code. That's literally what "vibe coding" is. Why would it surprise you that people who do know how to code, and don't hate the process the way a lot of AI enthusiasts seem to, might not find them useful?
You'll find plenty of people on HN who have this experience,but they just tend to be ridiculed or told they just haven't used AI correctly or enough. Admitting you don't use LLMs for everything, or god forbid at all, is like telling Christians you don't want to be saved.
Because they can easily get outcompeted by those who care about software/output and use the latest tools? might as well code in assembly and brag about it.
I'm not here condemning people who use or not use. We have a new tech, for anyone who have been in the field long enough, it is nothing short of magic was has been accomplished in the last few years.
I could turn around 10K lines of code per day (I know it's not the best measurement but it does capture size to some extent) when I was not able to pull more than a 100 LOC. Let us say that most of it work, and there are few rough edges, a senior programmer can follow the shape of the code, and understand where to tweak and where the LLM get stuck. So this is basically like having racing engine compared to running.
Companies get outcompeted, individual coders don't. And not everyone wants to be the Thomas Kinkade of coding, just cranking product out as fast as possible. And products that "use the latest tools" don't always "outcompete" those that don't. Most of what gets vibe coded - as demonstrated by what gets posted to Show HN - is qualitatively worse than the equivalent human-written software. It certainly isn't better, and there's no indication that velocity to market leads to market dominance.
To metaquote a recent thread - where is the vibe-coded replacement for Photoshop that outcompetes it? or Word? Why aren't vibe-coded games dominating Steam?
The speed alone doesn't translate to productivity and productivity alone doesn't translate to quality.
Imo it depends on the type of change required. If it involves churning out 1000 line of new boilerplate, an LLM will win every time. If it means tracing a subtle edge-case bug and carefully planning a deep one-line change in a 100k codebase that leaves all other behaviour unaffected, I would still expect an experienced dev who's deeply familiar with the code to do it at least as fast and more correctly first time.
It sounds more like you are equating a totally-vibe coded product with no verified code, with a product thoughtfully written by a human with LLM assistance.
Trivially false. Let P be the set of maths problems and I be the interesting subset of P. If I is finite, then there exists an element x belonging to P\I whose description is minimal among P\I. Then x is interesting. QED.
I think that's a variation on the interesting numbers paradox joke.
Statement: All numbers are interesting.
Proof: Assume by contradiction that there's a non-empty set of uninteresting numbers. Then that set contains the smallest uninteresting number. That property makes it interesting.
Yeah, I've seen this before as well. I guess I've just become old and grumpy and can't appreciate jokes like these anymore. Also taking jokes seriously is peak HN so..
Edit: actually, forget about the above. I just find it very annoying when people dismiss good conversations with not-so-good jokes.
I mean, there's some truth to that joke in this case, so I wouldn't agree that it's dismissing. The point of it is that what matters is how we define "interesting", because by the joke's definition in particular, there can't be uninteresting problems. That seems to be a very subjective concept that can also change with time. Mathematics is so specialized that there can be 3 people in the world who find one specific problem interesting. If they solve it, they'll move on to something else.
I find it curious that you've protested against that joke but not against the statement that "it seems likely that there's a finite number of interesting math problems". It doesn't seem likely to me personally and I haven't seen proof of that, even in a joke form. There's a finite number of problems at any given time, obviously, because mathematicians are finite, but it would require a very good understanding of the whole of our mathematical knowledge to declare that if we keep expanding it we'll hit some kind of wall, of "interestingness" or whatever else.
Firstly, I'm very happy we're having this conversation. It's so pointless, yet pedantic it warms my heart in the best way possible.
Secondly, I stand by the statement that there is no merit to this joke. This is because the way it defines interesting is very hand-wavy. There are interesting and non-interesting problems, but by a sleigh of hand you can turn the non-interesting problems interesting, thus proving that basically everything in the universe is interesting. At least in the mathematically describable universe. When everything is interesting, nothing is interesting. So we can dismiss the proof as a silly joke.
What mathematicians find interesting is a different story. However, we can almost certainly say there is only a finite number of problems mathematicians as physical beings can solve. If we have 200 mathematical symbols at our disposal, and we consider all strings of these symbols of length 1000,000, we have captured all the descriptions of problems that fit to 1M symbols. But that's a finite number. Going beyond that starts to be difficult for a human to grasp (if 1M is not too much already), so all mathematical problems that are solvable by a physical mathematician are in that set of strings. And that's not even saying anything about whether or not they're interesting..
I still don't quite agree with the approach to mathematics as enumerating problems of a certain size, but to be honest I'm not prepared or motivated to keep this conversation going without turning to handwavy arguments based on my imperfect idea of what mathematics is and how it works. However, it's certainly given me something to think about, so it hasn't been completely pointless. Thank you for the discussion.
By the way, if I'm not completely mistaken, Gödel's argument to show the incompleteness of mathematics relies on encoding all mathematical statements as numbers. So I'm certainly not being very original here.
An interesting problem must have a description that fits in a brain, at least for now. Your description-length argument assumes arbitrarily large storage.
Sorry, I assumed the inductive construction was implied; you can indeed describe properties of that particular interesting problem (though of course you can’t hold its definition in your head), so it goes in the list. Keep going. At some point you’ll hit problems where the process of constructing the problem doesn’t even fit in a brain, etc. There are at least countably many problems, but finitely many problems which any algorithm-which-fits-in-the-brain can describe given finitely many inputs-which-fit-in-the-brain.
This isn’t an enormously important point - the actual question at issue is an empirical one, “in a steady state, can we produce interesting problems at a rate that exceeds our ability to solve them and integrate our understanding” or something like that - but I did rankle at a “trivial” proof which is invalid due to equivocating between multiple definitions of the word “interesting” (which should really take an object, “interesting to me” vs “interesting to something smarter than me”).
Yes, this is an exception to the rule in British English, although possibly old-fashioned and becoming obsolete. Some British people put "an" before any word starting with "h" and longer than three syllables.
EDIT
I'm wrong here - I don't think anyone ever says "an Halloween celebration" for example. But I was sure there were other "h" counterexamples than historic.
I asked Claude and it showed me various examples of other words that may well be preceded with "an", such as heroic, habitual, and hereditary. It's to do with how strongly the "h" is pronounced.
The idea of the brain having a primitive layer and more refined layers is much more than ten years old [0]. The new finding here is that distinct layers have different progenitor cells.
Interesting, thanks for the insight! According to your Wikipedia link, the Truine brain theory is not widely recognized.. maybe this will change that to some extent.
I'm no expert, but my understanding is that modern neuroscience has moved away from the idea that specific areas of the brain control specific behaviours.
Judaism evolved out of earlier Canaanite polytheistic beliefs with a pantheon of deities, some of whom had malevolent or destructive aspects. As the Israelites transitioned to monotheism, Yahweh - previously one of many gods - took dominance and absorbed personas and aspects of the other gods. The written texts continued to refer to other deities ("El" and "Elohim") but reframed them as other names for the same god. That feels to me a more satisfying explanation for the "fear" of god in the Torah.
This is probably a reference to Hume's problem of induction, i.e. that observing a regularity in the past cannot justify assuming that it will hold in the future. It's vaguely related to the article, but talking about "time windows" and "Mathers" muddles the point.
Is it vaguely related? He wondered why measuring anything even works. Why wouldn’t the measurement disappear, thus making all this measuring pointless? Because, apparently the measurement(s) are true each time-step, and it will be true for that time, until it’s not true. Why it reasonably works well for us? Well, God , I guess. Same way the Sun doesn’t burn our skin off (God, I guess, but some have issues with that).
Sorry, I had to critique that immediately because I could already see that other second paragraph I quoted coming, as in, this author probably worships Math, Science, and those that do it, certainly not God, because he was unable to characterize the phenomena of it as related to God.
Yes, vaguely related. Dirac is not wondering why measurement itself works, but why mathematical reasoning applies so effectively to the measurement results.
I think it's valid to be surprised that all observations of a physical phenomena up until this point have obeyed a beautiful and (relatively) simple mathematical relationship, without even thinking about predicting the future.
Measurement works because universe moves in a simple way. As Hume indicates, you need very complex motion for irregularity, maybe even sentient, but sentient universe is fairy tale.
Ehhhhh.... this is actually a much bigger claim than you realize and to immediately dismiss it leads to some problematic issues in the continuum of reality.
Without a rigorous falsifiable definition of sentient at all scales it can apply at best the problem is undefined. Are brains sentient? Are neurons sentient? Are the actual algorithms these structures run sentient? Without those answers we can really only say "The universe is probably not sentient".
For a regularity to be broken, the phenomenon causing this regularity should be sentient to break the regularity in an intelligently chosen way. It doesn't matter how sentient are neurons, they don't affect anything and might as well be absent. See https://en.wikipedia.org/wiki/Discovery_of_Neptune - what neurons did there?
Randomness/Chance itself is amenable to laws by which we can estimate its bounds. In one sense everything is chance since the deterministic laws themselves operate within approximation bounds. When the approximation bound in the effect is similar in magnitude to that in the cause and both are very small, we call it "deterministic" whereas when the approximation bound in the effect is much larger than that in the cause for no discernible reason we say "chance" is operating.
I wonder if you're reading too far into one example. Hume's original example was of the sun rising every day - nothing to do with sentience or arguably even complexity. The chicken/farmer example is one that Russell came up with to make it easier to imagine.
reply