You can put a lot of thoughts while using LLMs.
You are equating manual coding with more thinking, which has proven to be not the case given that it is mostly automated.
You are equating manual coding with more thinking, which has proven to be not the case given that it is mostly automated.
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.
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.
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.
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.
> 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.
That is not say there are really mindlessly produced apps out there. But the comment made it sound that anything LLM-aided is negative.
Take a step back and think about your question in the context of privacy and software security.
For a few example answers, look at:
- https://en.wikipedia.org/wiki/Adware
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.
Sorry I don't understand your argument.
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.
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.
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.
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 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.
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.
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.
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.
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.
"The speed alone doesn't translate to productivity and productivity alone doesn't translate to quality."