Rendered at 07:30:53 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
chanux 4 hours ago [-]
> For better or worse, React is heavily overrepresented in the training weights, and “agent experience” is starting to matter more than developer experience.
Another winner takes all situation. This and the other post on agent tool use[1] makes me think we are in a period of great homogenization. I'm sure there's a group that's delighted about this but for me, it just makes me feel a little uneasy.
I wonder if this is overstated. Anecdotally, we use Vue at work and Claude and Codex handle it just fine. I'd expect Vue to be the third best-represented after React and Angular, but even then, we feel absolutely no need to change things up to get better results.
Vue's reactivity is quite similar to Solid's, AFAIK, so I wonder why there would be so many issues with Solid.
We have also started to have success getting LLMs to create custom lints for us to handle tricky edge cases. For example, discovering deep watches or tricky interactions - you can get a fair way asking an LLM to create a lint using a codemod library (in our case, vue-morph) that fires on this example but not on that example.
zmmmmm 43 minutes ago [-]
Vue had a good tenure as a solid #2 to React, so I think it probably has got a lot of representation in training data. Things really splitered after that but it got a good foothold.
gunalx 20 minutes ago [-]
The problem I see with vue is what vue patterns are you using. And the llms may be trained on more outdated ones more than current practices.
Wasn't that true for tech in general though? I mean I have heard developers bitching about React for years now and every year I saw it get more adopted at the same time. Of course some obviously do not like it but the decision was usually driven by business and not coders. I feel its a simillar thing happening with AI code taste being primarily developed by big tech firms which ofc love homogenization. But its not all bad, I don't think people will just give up working on what they like because agent expeirenxe got better but who knows though
cookiengineer 2 hours ago [-]
> period of great homogenization
It's called alignment. And that's the correct word for it in my opinion.
The most important part is that we have to find a way to tackle the knowledge enshittification problem.
Because now that slopcode and slopposts are everywhere, the average quality level will decrease. We had the peak internet knowledge, and it's now gradually getting worse.
That's not a personal opinion, that's how attention matrixes and their keys/values computation works.
skew-aberration 2 hours ago [-]
It was once called 'natural monopoly'
bluefirebrand 2 hours ago [-]
> It's called alignment
Alignment is such a polite term for "a giant boot that is crushing all of the uniqueness out"
Once it is done crushing, congrats! Everything is aligned.. by being flattened
bhawker 1 hours ago [-]
Does the world need the "uniqueness" of 40 similar web frameworks?
sznio 46 minutes ago [-]
the world certainly needs novel ideas. maybe eventually we'll come up with a web framework that doesn't suck - or rather we'll realise that Django had it right all along for all these years.
gmac 36 minutes ago [-]
Perhaps not if the one framework we ended up with was a good one …
camillomiller 1 hours ago [-]
As long as there are standards, yes, why not.
In Italian we have a saying: il mondo è bello perché è vario.
The world is beautiful because it’s varied.
jansan 54 minutes ago [-]
Since a good LLM can handle any of those 40 web frameworks, I think having 40 web frameworks is becoming less of a problem than it used to be. Actually, implementing ideas in an individual manner will become easier. Remember the Bazaar and the Cathedral? The Bazaar kind of failed on the client side, but LLMs may revive it.
comrade1234 12 hours ago [-]
My wife's experience is managing teams and has been involved in creating corporate websites using contractors. She doesn't know anything about html at all. She just manages people.
She's now working on a biotech start-up pre-funding. They have pretty much zero money. They want to redesign their website.
I set her up with my deepseek key and she's been using flash-v4 with image detection (I think deepseek says it's still experimental). She just provides the current website, tells how she wants it to look and it works great. I mean it's obviously ai generated but she gets quick results and is able to tweek things to look better by just telling deepseek what to do. She was even able to change the text in one of their images to its new product name without having to contact the graphic designer.
This is a simple example. Basically it's one of those earlier jobs that you could get someone to bid on for $x but now you can do yourself for $20.
jonathanlydall 11 hours ago [-]
My mother has a psychology practice and wanted to update her 20 year old website.
I did the first few prompts (single static page, basically a brochure, don’t worry about hosting) into ChatGPT to get her started and a few days later she sent me a .zip which I uploaded.
Only took a while because she wasn’t paying for ChatGPT so had to wait for the free limit to reset quite a few times.
But overall it was super empowering for her.
Wowfunhappy 11 hours ago [-]
Not that I'm in favor of spending money unnecessarily, but I find it kind of surprising she didn't just spend the $20, given this was a website for her professional money-making business.
jonathanlydall 2 hours ago [-]
Wow, it’s fascinating after waking up to see all this conjecture here on why she didn’t pay for the subscription.
The short version, wasn’t for wanting to save money, but simply a matter of it not being worth the hassle to any of us to subscribe and then later cancel for such a small scope of work. If it was too frustrating I would have let her use my Claude sub.
Also, she’d been meaning to have it updated for years, a few extra days was nothing.
She did short sessions in spare time between other things, the wait between was maybe a little frustrating, but also gave the benefit that she would have had better clarity develop between sessions.
Website is not key to her business where it’s mostly word of mouth at this point (she’s been practicing for >20 years). Goals of website were:
- Findable in Google by “psychologist/therapist <area name>” (she also has a Google. Business profile so is findable on Google Maps).
- Minimal copy. A comforting sentence or two to state philosophy, qualifications, therapy types offered, where located, how to contact.
- Doesn’t feel dated.
Essentially it’s meant to complement the word of mouth aspect and maybe bring in the occasional completely new patient.
4 hours ago [-]
georgemcbay 6 hours ago [-]
> I find it kind of surprising she didn't just spend the $20
If it because the poster's mother dislikes the idea of subscriptions, then I totally get it. (Though I admit I have no idea if this has anything to do with the poster's mother's decision.)
I'll go out of my way as much as I can to avoid signing up for anything that is a subscription because of how horrible the entire corporate world has abused subscription dark patterns over the past couple of decades.
These days just the packaging of anything into a subscription makes me assume there is intent to screw people out of money.
While signing up for LLM usage is fairly low risk as far as subscription lock-in goes, someone non-technical might not be aware of that fact.
jonathanlydall 2 hours ago [-]
See my more detailed sibling comment, but was more that the scope and urgency were so small that it wasn’t worth the hassle to set up the subscription and have to cancel it after.
thaumasiotes 10 hours ago [-]
Does updating the website bring in additional money?
2 hours ago [-]
Wowfunhappy 10 hours ago [-]
Presumably a nicer website could lead to more customers. Otherwise why update the website at all?
jonathanlydall 2 hours ago [-]
She had no shortage of patients from word of mouth, but old website was minor liability in its datedness potentially putting off prospective patients.
People already knew about her and website is essentially just “this is what I do, where I am and how you can contact me”.
the_other 32 minutes ago [-]
> but old website was minor liability in its datedness potentially putting off prospective patients.
Anecdata: I’d be more likely to use the services of a company with a good, old-style site than a bad, new style site. Things like pop-overs, text that animates in as you scroll, banner images that take up most of the “abive the fold” are all red flags for me.
Oh, and the most common one: “Read more”.
A modern site that avoids all those can be great. But those are rare, IMO.
ElProlactin 10 hours ago [-]
> Presumably a nicer website could lead to more customers.
It depends what "nicer" means. Paying a web designer/developer to create a bespoke website doesn't guarantee that said website will have a better UI/UX and, most importantly, "convert" at a higher rate. Not every web designer/developer understands IA, content, performance optimization, etc.
The popular AI tools produce websites that are clearly AI-produced if you know the patterns, but that doesn't mean they can't be usable and quite effective at converting. And if you have a bit of skill with prompting, AI can be really good at working through performance bottlenecks, etc.
bayindirh 10 hours ago [-]
Changing office address? New qualifications? Better copy?
bryanrasmussen 10 hours ago [-]
so. if website does not lead to customers - why do any of that? actually why have website? Once you say yes to website you imply having one is somehow valuable, so in that case why not spend 20 dollars.
jonathanlydall 1 hours ago [-]
After 20 years, her new business is mostly word of mouth, but website was very dated and potentially a minor liability.
Scope of work and urgency were so minimal that it was simply not worth the hassle to actually subscribe and then have to unsubscribe later.
If there was no free option we could have done it on my Claude sub or she would have just paid.
bayindirh 10 hours ago [-]
Just because websites can exist. Sometimes things are done for fun, or just for the sake of it.
This perspective declares all the personal websites of people worthless, however, they are priceless.
Because people's curiosity and creativity is priceless as well.
Similarly, why create art and share it around if it doesn't bring in customers? Why make music, take photos, dance? Do we live to serve customers, or do customers' existence serve us to live a better life?
Questions, questions...
Wowfunhappy 9 hours ago [-]
Of course, those are all great reasons to make a website. But this website was for a woman's psychology practice. I don't imagine she made it for fun or to express her creativity. The purpose of a psychology practice's website is to tell people about your psychology practice, so they will either sign up ($) or find information they need more easily (higher satisfaction → $).
If OP's mother runs a donation-funded pro-bono psychology practice then you can translate the dollar signs to units of happiness or whatever (which I would imagine is her real goal regardless).
This person is spending her time to create the website (with ChatGPT's help). How much is that time worth? Of course when it's your business hourly pay is tricky, but I imagine she values her time highly enough that $20 is not worth very much of it.
bayindirh 9 hours ago [-]
I know an accountant, who has a respectable amount of customers and enough income to live comfortably. Their company has a website which only provides a logo, address and contact information, in a 23 line HTML file, complete with all the white space.
If their company can do well with this website, her psychology practice can do as well.
Some of the best services I got was from professionals with no or mundane online presence. Instead, their abilities and expertise moved them to the top in their respective fields, and the whole community knows how and when to reach them.
So, maybe a shiny website is not a hard-requirement for a good psychology practice, IDK.
So, the thing is, maybe this was her way to explore new things and decompress while doing some mundane thing from her perspective for free. Sometimes it's not that $20 which you can pay without any negative side-effects, but the desire to see how far the thing goes without the token, or just because you don't feel any urgency to do the task, so that $20 looks like an unnecessary waste.
I have been in both places.
Wowfunhappy 9 hours ago [-]
Yes, presumably that's why she did not update the website for 20 years!
If once she's decided to update the website—surely it's worth more then $20 at that point? Otherwise, she probably shouldn't be spending any time on it herself either, given the opportunity cost.
Obviously she decided otherwise, I just find it kind of surprising.
Like, in general, I'm always kind of surprised at what people are and aren't willing to pay for. People will suffer through horrible full screen ads in mobile games instead of paying $5 one time to turn them off. And they'll do this on a phone that costs $1,000+. I don't know their financial situation, but I would buy a cheaper phone and get rid of the ads...
bryanrasmussen 46 minutes ago [-]
>If once she's decided to update the website—surely it's worth more then $20 at that point?
the problem here really, from both sides of the argument, is the assumption that humans are rational economic actors.
One side assumes that it is not worth 20 dollars to update the site quickly thus she does not do it, but really for that to be true (given costs of psychologists sessions etc.) then it would not even be worth updating the site, or paying for the site hosting or the domain at all.
The other side assumes that given that she is updating the site it must be worth paying 20 dollars to do so quickly and asks why she does not, given that it is worth updating the site.
If humans are rational economic actors she should be updating her professional site because it has some professional benefit to her that she is aware of, but this creates the two problems stated above.
This problem, and the examples you give, are resolved by understanding that humans are not really rational economic actors and the reason that she is updating the site and not paying the extra 20 dollars at the same time cannot be resolved to a non-contradictory answer.
We are at best, partially rational economic actors. Rational-like.
bayindirh 9 hours ago [-]
From what I have seen, people's perspective on value lies on a very wide spectrum. My mom won't buy a YouTube premium subscription, because she said she likes the ads. It's a kind of discovery platform for her. It's not that I share the same perspective, but I respect her about that.
I know people who won't subscribe to a service, but go through great pains to get the thing the service offers (another brand, similar yet inferior service, etc.).
For example, if an application I use has ads (i.e. a game), and it needs a subscription to remove these ads, I'll simply won't install it, or get the paid version of it from the start. For me, playing a game with no end and paying monthly to "hide" advertisements doesn't worth it.
card_zero 4 hours ago [-]
These things are very subtle and are sometimes about ethos, and not about value at all. For instance:
* You propose I buy your ¤4 overhyped toothbrush. If I spend 10 minutes digging around, I could find a sub-¤1 toothbrush. Effectively I'm doing 10 minutes of work at less than minimum wage in order to avoid owning the premium toothbrush. Do I do this? I might! The reason is that I want no part in your hype.
* You offer me a loyalty scheme that will genuinely save me money if I participate. I only have to pay attention to your offers and routinely identify myself and I might get 10% savings, all the time. I decline this because you don't get to use my brain cycles for your profit, even if I profit too.
* You offer me a free thing that happens to track me and funnels data to data brokers. I decline it even though it does me no actual harm at all, because I don't want you to make money from personal facts about me, even when the facts are robotically aggregated and anonymised. Ethics are at stake: ethically speaking, you can just piss off. That is worth more than a free gadget, and it's not even an equation.
thaumasiotes 6 hours ago [-]
> but I imagine she values her time highly enough that $20 is not worth very much
Did you notice that this is completely unrelated to the idea that the $20 would turn a profit for the business?
It's just the argument "$20 isn't very much money, so why not spend it?".
thaumasiotes 10 hours ago [-]
> Otherwise why update the website at all?
Because you have it.
jonathanlydall 2 hours ago [-]
Only minimally, after 20 years of practicing word of mouth does 99% of the work.
King-Aaron 7 hours ago [-]
There is an entire industry built around this premise, yes.
technion 10 hours ago [-]
Every static HTML pages built this way with ai is another WordPress site that wont get built by contractors just to be neglected, compromised, and used to launch phishing and ransomware attacks.
kajman 8 hours ago [-]
Maybe, but what about when "Claude do this" picks WordPress for someone that doesn't know what a reverse shell is?
oefrha 5 hours ago [-]
Still a win. Claude loves to write code from scratch instead of searching the web and pulling in dependencies, so you’ll likely end up with fewer garbage tier plugins written by people whose average skill level is put to shame by bootcamp grads; those people don’t know what a reverse shell is either.
reaperducer 10 hours ago [-]
Every static HTML pages built this way with ai is another WordPress site that wont get built by contractors just to be neglected, compromised, and used to launch phishing and ransomware attacks.
You mean the very web sites that the "AI" trained on?
If you think AI can't make buggy code, there are several dozen thousand comments on HN that disagree.
technion 7 hours ago [-]
Ai cant make a static HTML page sitting on something like cloudflare pages have an rce bug.
adamredwoods 7 hours ago [-]
The key is you're doing it yourself, so it takes your time away from something else. And if something doesn't quite work out, who's the backup?
For small shops and startups, this probably doesn't matter. For mission critical sites, who's more dependable? AI is a tool, that's all it is.
dostick 8 hours ago [-]
She wouldn’t be able to do any of that without you setting it up first. She would not know anything about deepseek, meaning of a folder with index.html file. Would not know even what to ask ChatGPT, “I need a website”?
You make it sound like easy task anyone can do, when you provided 99% of otherwise impossible for them to easily obtain key knowledge needed.
oefrha 5 hours ago [-]
Any idiot can spend one minute now to acquire this amazing knowledge that you can just ask ChatGPT “I need a website”. If they don’t know now, sooner or later they’ll know from a short TikTok or something in the next couple of months/years. Not to mention AI companies are spending $$$ on ads to raise awareness; professionals already know they can create slides with LLMs, literally nothing’s different when it comes to most content websites. Yes, it’s an easy task any idiot can do. Head in sand, pretending it’s some sort of $10k for knowing where to hit situation isn’t going to reverse the trend.
nozzlegear 4 hours ago [-]
You're not accounting for how deeply unpopular AI is with the general public. Would anyone be making those TikTok videos in the first place? Would OP's wife want to use AI if he wasn't there to advocate it?
oefrha 3 hours ago [-]
Given that my nontechnical coworker has shared quite a few of these TikToks/Google Shorts with me, yes tons of people are making them. I don’t know what kind of alternative reality you live in, you can just go to any social media site and search for “create website with ChatGPT” etc. and check the view counts.
Plus the context here isn’t any random person, but people who intend to pay for website development for their businesses.
mplewis 8 hours ago [-]
you can literally do that to chatgpt
theendisney 5 hours ago [-]
Haha, yes. Can have it code a webserver from scratch on a disposable vape. Should be quite theraputic.
snakeboy 10 hours ago [-]
> She was even able to change the text in one of their images to its new product name without having to contact the graphic designer.
Is that legal... ? I admit I don't know much about graphic design is contracted.
comrade1234 10 hours ago [-]
Just like if you're a programmer the company paying you owns the work.
dijksterhuis 7 hours ago [-]
will not not necessarily be true for AI generated works in all territories
That's only true if the picture was specifically commissioned by the company.
If it's a stock image or a licensed image, they need a license to alter the original image.
Chaosvex 7 hours ago [-]
It's generally a little more complicated than that. Not up to writing paragraphs about it so I'll just leave this as a note so anybody that's interested can do their own research.
xyst 11 hours ago [-]
show us these "corporate websites"
comrade1234 10 hours ago [-]
That was just part of her work. She was employee #11 at a now $4.5B biotech company so everyone that early on had to do everything. She worked for Novartis, for booz allen, and others. She usually hired McKinsey consultants for projects but the web stuff was for smaller companies. She managed a team in India for one of her companies that took care of the web stuff. Basically just look at any top-10 Pharma or government website and you might see what she managed.
patcon 9 hours ago [-]
I choose to imagine that you guys are like a cute "opposites attract" Marxist x capitalist power-couple :)
latchkey 12 hours ago [-]
i started a web development business in 1995 and have been coding web stuff for decades.
like the OP, all those years of learning how it works under the covers gives me a distinct advantage since i can easily tell what is slop and what is going to perform. as well as how to get AI to iterate and fix the things it isn't good at (yet). i feel like now i have super powers. i love it and can't get enough.
the fact that your wife can be productive at lower cost means that more products will be built and more opportunities will be made. instead of spending money on website design, her business can spend money developing biotech.
i welcome that, even if it means that things will change from the past and those that have made a career out of charging thousands will get replaced by a $20/month subscription.
throwayay4929 12 hours ago [-]
Would you say this is a similar but perhaps bigger change to frontpage/Dreamweaver/web app frameworks? Those all drastically cut down tub development time for web pages and at the same time opened up new possibilities. I wonder how it'll pan out with AI
Gualdrapo 11 hours ago [-]
FrontPage, Dreamweaber and co seemed to fell into obscurity when HTML5 & CSS3 came up and from that point web development went much more complicated than that.
Granted, it seems it is easier now to give prompts to an LLM so it will spit things out than back then where you had to know the tool and fiddle with menus and thingies to sort of try to produce a result.
But the drawback seems to be the same for both - lots of unreliable and unoptimized code that will go live if you don't know what they're doing under the hood and can potentially cause issues in the future. Remember that all this tools do are sorts of interpolation. I've seen lately lots of "modern" websites with tons layers of !important in their CSS and who knows the monstrosities that they have with their JS.
Meanwhile I and all people like me still don't have a job because all of this and the alleged "thousands" I was getting for doing this things.
latchkey 11 hours ago [-]
the thing you haven't come to terms with is that it is more important to ship than it is to worry about the issues in the future. i thought RoR taught everyone that.
the beauty of what's happening today is that AI might produce slop on the first try, but you can also refactor just as easily too. "clean up all !important and optimize the code for speed", is just as easy of a prompt and it'll go off and do a fantastic job at that. that is what the OP was talking about in his article.
you don't have a job because you're not adapting to this new world order quickly enough. i predict that there will be insane demand for porting existing applications off these over priced SASS contracts and building tailored products for businesses. as much as they are trying to convince people, you don't need a $5m/yr salesforce / servicenow contract when you understand the business model and can envision a better solution to the actual problem out of thin air.
i'm burning 500m+ tokens a day on a $200/mo subscription. it is creating 10000x more value for me. it is no longer how much you know HTML/CSS, it is how well you know how to get AI to do what you want it to do and the only way to develop that skill, is to do it.
toyg 10 hours ago [-]
> you don't need a $5m/yr salesforce / servicenow contract when you understand the business model
I'm sure many people will think that; and I'm also fairly confident that 5 years later they'll take their obscure, bug-ridden, vibecoded monstrosity that nobody really understands, throw it out, and get a salesforce contract. Technical debt doesn't disappear just because you have agents working for you; in fact, it is exploding right now, and I would bet good money that 2-3 years for now there will be a flourishing cottage industry of consultancies specialized in dealing with such monstrosities.
latchkey 10 hours ago [-]
Context is important in a response like this. Giacomo is a Sr. Presales consultant at a SaaS company that sells "The AI operating system for modern Finance." Of course you're adverse to things because it is a direct threat to what your business offers today.
If I can vibe code up a solution that fixes my problems for $200, it doesn't matter what happens in 5 years. The rate of change that's happening today in the increase in quality of the output of the models, I can just tell it to fix whatever we have and make it better.
toyg 8 hours ago [-]
Spoken with the true arrogance of someone who has no idea about the real world of finance.
When your software has to produce legal documents, satisfy auditors, and certify a bunch of things to shareholders and governments, I'm sorry but your $200 vibecoded hack is not going to cut it. You will have to get it certified, to get it audited, to get it secured according to this and that legislation, to prove where it gets each and every number and how it modifies it, and then you will have to maintain it because standards and laws change every other day. Sure, get an agent to cook you up a full consolidation solution, see how quickly you get laughed out of the room by grown-ups.
Btw, I am not "adversed to things" - the stuff we do has agents built-in, that do all sorts of wonderful things. The difference is that we can demonstrate that they do them right, with financial intelligence standardized and battle-tested across thousands of customers all over the world. Our customers don't have to worry about rewriting their pile of vibed hacks, or about being humiliated by auditors, because we take care of all that stuff for them. That's worth more than the pennies you save by having cousin' Vinnie vibe up a multidimensional financial engine that takes 3 days to calculate trillions of useless intersections before falling over.
pocksuppet 1 hours ago [-]
Ha! you think anyone cares about regulatory compliance? no, they only need the appearance of regulatory compliance
latchkey 8 hours ago [-]
You sound like someone who was adversed to cell phone cameras taking over film.
Get ready. AI is coming for every single industry, full steam.
thelastgallon 6 hours ago [-]
> Get ready. AI is coming for every single industry, full steam.
But more real... Giacomo fails to take into account the concept of when OpenAI decides to create an audited financial service that guarantees that their output is valid. ChatGPT Work is already a beginning of that future.
toyg 6 hours ago [-]
That's like saying Google offering GMail ended webmail - there are still plenty of webmail services around: some better, some worse, some more specialised. The same will be true of most sectors.
AI is another tool in the toolbox, not magic. It's not about being pro or against it, it's here already (hey, we sell it!) and obviously it will continue to get better; but it won't magically solve everything for $2.
latchkey 5 hours ago [-]
i've written smtp servers.
it has the best spam control on the planet.
i'd never use anything else.
toyg 5 hours ago [-]
That's great to know, Jon. I suspect non-US governments have a different opinion. Heck, even the US government likely has a different opinion. Not to mention Google competitors in any other sector.
latchkey 5 hours ago [-]
one out of 10000000 customers.
toyg 5 hours ago [-]
Have you any idea of how many businesses need a financial consolidation tool, out of the total number of businesses out there?
No, of course you don't, you write email servers.
Sure, your local garage will now do their accounting in vibed apps instead of vibed Excel files. I suspect multinationals will choose not to.
latchkey 5 hours ago [-]
I can see I'm under your skin as you're trying to make this personal. I have a long history of being early and correct with many things. What is transforming under your nose, faster than anything ever before, will take you for surprise, unless make a conscious decsion to wake up. Do yourself a favor and listen to what he's saying... https://youtu.be/NYFGCESmikA?t=2883
toyg 5 hours ago [-]
I was not the one who brought personal qualifications into a public argument, Jon. I guess you don't like it when your lack of specialized knowledge becomes evident.
As I said, I already know what AI is doing - I already use it just fine, I even help building and selling it. The impact it is having is obvious. But like recipe books did not turn everyone into Michelin chefs, it won't turn hacks into rigorous builders of trusted systems.
latchkey 4 hours ago [-]
So you think AI will only ever be a recipe book? That's the disconnect we have in opinion.
bigstrat2003 5 hours ago [-]
Bro, "AI" can't even program decently. It's still, to this day, worse than every human I've ever worked with. The idea that it's going to take over every industry is laughable.
latchkey 5 hours ago [-]
it is funny having some anon tell me something that is 100% different from my own experience and i've been coding for 30+ years now.
latchkey 11 hours ago [-]
no, those tools sucked in comparison to what ai is doing.
i just built a financial dashboard for my business. in realtime, i'm sucking in all the data from quickbooks, mercury, stripe, deel APIs and presenting it to myself, and my investors. it does all that sitting in cloudflare as a worker, for $5/month. took me a couple weeks of iteration, not a single line written.
from that i just told ai... "i'd like to get rid of quickbooks because yesterday it was down and i couldn't log into it. figure out what i'm using there and present me an interface that allows me to do whatever i'm doing in quickbooks, but with my existing data from stripe, deel and mercury."
it then dutifully went off and built me that app and now i'm running it in parallel and synchronized with quickbooks, until i feel that i can just turn that off. it is customized exactly to my business workflow and easily maintained with full unit tests. it costs me nothing but a $200/mo codex subscription and a few hours of work.
etoxin 7 hours ago [-]
I was originally a Flash developer, when that died when Steve Jobs banned it from iPhones, I pivoted to frontend. I got to see web evolve over the next decade or so and loved every part of it.
Now, still as a frontend engineer albeit much more senior. The writing is on the wall, again. It's time to reskill for AI.
It's not bad news.
We as experienced engineers are needed to help build in the guardrails, frameworks, the new tooling, etc. There is a lot of work that is needed that requires actual engineers with technical experience.
Like the early internet, I see this as a new beginning and we get to decide how it evolves.
livinglist 3 hours ago [-]
I think that is the nature of being a software engineer, even before AI you had to keep learning new libraries/SDKs/APIs/languages to keep up with the industry trend. I think it will remain the same in the age of AI, good engineers will adapt.
josefrichter 14 minutes ago [-]
You can pivot to design systems. I believe they’re 80% development problem and just 20% design problem really.
thelastgallon 6 hours ago [-]
I can't wait for the asteroid to hit C-Suite and senior execs. These are the most meaningless jobs and easiest to automate, with the most cost savings.
derekdahmer 6 minutes ago [-]
You would prefer the company that employs you be run by AI rather than humans?
seydor 1 hours ago [-]
The csuite has the power to keep AI away from it or make itself mandatory.
rk06 2 hours ago [-]
beware! using AI for middle management is how you speedrun to dystopia. Bad Managers can be fired, good managers can manage up. on other hand, "bad" AI will remain and continue to be dystopic, and "good" AI will be killed by higher management for being not being a doormat.
rickbergfalk 7 hours ago [-]
> Meanwhile, Cursor and Viget have blogged about migrating their codebases from Solid and Lit, respectively, to React.
That was maddening to read. Here I was thinking we should all be migrating to better performing frontend solutions. Does it really take an agent that many more tokens to write Lit or regular HTML and HTMX?
ramraj07 4 hours ago [-]
At least last year most agents wrote materially worse code in htmx.
owebmaster 4 hours ago [-]
> Does it really take an agent that many more tokens to write Lit or regular HTML and HTMX?
Definitely not. That's skill issues. The shadow DOM can be a bit tricky.
CqtGLRGcukpy 4 hours ago [-]
There is going to come one day that companies (and any website owner) will wish they didn't use AI and instead used a simple (maybe even plain-text) website. That will come when people really need information from that website but can't get to it.
Heck, you can have your information as clear and concise as possible, but the moment I sense that "AI-generated" texture, I am immediately closing the tab. This is just extrapolating from how I feel about the bevy of obviously AI-Generated flyers and banners that have been gaining a lot of traction in real life.
flyingshelf 12 minutes ago [-]
Doubtful. This is just the cost of doing business. 99.9999% uptime for a fraction of the cost is totally fine for all businesses. Government should be the exception though.
tommica 2 hours ago [-]
Absolutely this. Although I like the shiny and polished looks, getting the info out is the most important, and it is hard yo beat pure black-on-white text
hexapus 4 hours ago [-]
I wish that was the answer to all of these people setting their spouse, their grandmother, their boss loose with LLMs to build sites. It should just be acceptable to have a simple site that conveys information well, and then we wouldn't need to boil the seas to generate pages of shiny slop.
4petesake 56 minutes ago [-]
Looking forward to that entry level laptop with 128GB RAM
Supermancho 10 hours ago [-]
> The frontend is less risky to just hand to an agent.
The smaller the problem, the less risky it is to do this, regardless of the nature of the problem. This is not a frontend-specific issue today.
josephg 10 hours ago [-]
Frontend development - perhaps more than any other kind of software development - is “what you see is what you get”. There aren’t a lot of ways a website can be invisibly broken.
Systems engineering isn’t like that. Vibe coders beware: A database could silently corrupt data, or have latent security vulnerabilities. It might have a badly designed query language that will be difficult to change later. But frontend code can be rewritten at will. It’s a perfect target for LLMs.
Gigachad 8 hours ago [-]
At the same time I have found LLMs far less competent at frontend because they don't seem to have any visual understanding of what a good website looks like.
wiseowise 16 minutes ago [-]
> Systems engineering isn’t like that.
Whatever lets you sleep at night man. If you really think you’re better than the machine at spotting arcane Unix incompatibilities, or that you’re somehow more “safe” than frontend jockeys, I’ve got really bad news for you.
bluefirebrand 2 hours ago [-]
> There aren’t a lot of ways a website can be invisibly broken
Any website that has any UI state management or does any kind of network calls can be invisibly broken in many, many ways
owebmaster 8 hours ago [-]
The UX is what makes the users use the apps, systems, games, their phones.
atomicnumber3 7 hours ago [-]
"There aren’t a lot of ways a website can be invisibly broken."
??? Have you never debugged weird react state before??? Have you never used a nontrivial SPA before? Even the most simple react SPA has about a trillion states.
I don't really know how to respond to your statement than "no, they can definitely be invisibly broken."
josephg 4 hours ago [-]
React state bugs are usually not invisible failure modes.
Other kinds of software - for example, the backend of a website - have far more invisible failure modes. Security. Correctness. Performance. Bad API design leading to overfetching. Etc. Software works great on your machine and when you demo it, but it falls apart at scale. Endpoints that aren't secured properly. Race conditions cause silent data corruption. Memory leaks. And so on.
If claude messes up writing a react frontend, we're more likely to find the problem quickly. And frontend bugs usually don't continue to cause problems after they've been fixed. Silent bugs in the backend are more dangerous and more expensive.
Supermancho 3 hours ago [-]
No need to engage with bad faith premises. You cant convince someone who is invested in their own FUD.
etoxin 7 hours ago [-]
When done properly, yes. But AI agents are doing a lot of data logic in the frontend that should be in the backend behind secure api's. When this happens, the frontend becomes a massive risk.
cube00 5 hours ago [-]
> If you write a React component with an agent, though, then the risk of just yolo’ing it into production is (typically) much lower.
If your state management gets out of sync with the form controls your users are working with it can become pretty high risk because now users see one thing and something else actually gets sent to the backend.
ramraj07 5 hours ago [-]
If your coding agent screwed up so bad that wrong data is being shown to the user, in August 2026, thats more on the prompter than anything else.
geraneum 1 hours ago [-]
But the prompter is supposed to be someone who doesn’t know web dev. That’s their selling point.
tuesdaynight 8 hours ago [-]
In my useless opinion, most people are not aware of how big AI is and how bigger it will be in 3~5 years. It's not worthy to be worried about it, because it will be a global problem, but there are people who are completely blind about it
cromka 7 hours ago [-]
Nobody is aware, but neither are you. We may as well have plateaued already. You don't know that.
flyingshelf 10 minutes ago [-]
I don’t think we're anywhere near the plateau. AI is still expensive and slow. Make it realtime, local and nearly-free and you got a problem.
tuesdaynight 5 hours ago [-]
Even if that is the case, the current models are already revolutionary. We would spend years discovering all the capabilities of these things. And that is considering that the plateau would last for years. And I didn't say that nobody is aware. There are some people that follows the breakthroughs and model releases (in my life), and they agree with me
iAMkenough 8 hours ago [-]
> It's not worthy to be worried about it, because it will be a global problem
Like hunger and diseases are global problems not to be worried about.
dsiegel2275 7 hours ago [-]
I think they meant more along the lines of "This narrow problem today is not worth worrying about, because soon it will be a larger and bigger problem. "
bluefirebrand 2 hours ago [-]
That's still a silly argument though
How about we worry about this smaller problem today so the bigger problem tomorrow is less big. Or doesn't materialize at all?
Do we have to sleepwalk off this cliff?
5 hours ago [-]
Insimwytim 8 hours ago [-]
Prompt: Answer without searching the internet:
Woah! Must it discard all pre-training as well?
It already slurped "the internet". You can't seriously say it doesn't count!
jareklupinski 6 hours ago [-]
there seems to be at least one service that your LLM can find if it searches the internet (e.g. in my case "best rental API") that poisons your context into thinking that that one service is the definitive and only available API for that data
gedy 5 hours ago [-]
Maybe I'm an outlier here but I moved into front end to steer products and the resultant architecture into making sense from the incomplete or contradictory "requirements" we got from product and even UX. I've been doing this for over 20 years and every company has needed good engineers to make the product a logical reality.
LLMs piping out UIs from PM prompts aren't solving that imho.
leptons 3 hours ago [-]
I spent 2 years developing and polishing a front end web application, and then some other engineers at my company pointed Claude at it to try to reproduce it. The slop it crapped out would make most if not all our users leave for the competition. Then they had the nerve to ask me to explain what was bad about the sloppified version. I'm looking for a new job.
atomicnumber3 7 hours ago [-]
"Note I’m not saying there are zero risks: the agent could mess up accessibility, it could cause an infinite loop that blocks users, etc. But in general, frontend code is a lot more ephemeral and replaceable than other types of code. So I expect many AI coders will feel comfortable just letting their agent handle it unsupervised (for better or worse)."
This is a weirdly reductive take on frontend correctness. Just for the record, I'm a backend dev. So I don't have much stake in this game.
This idea is, of course, not uncommon. "If the backend has to treat the frontend as adversarial anyway, and has all this cool stuff (constraints etc) for guaranteeing consistency of the system, then the frontend can just do whatever, right?" It plays into a lot of biases around typical frontend devs, typical backend devs, language stereotypes, etc. So it _sounds_ good.
Let me tell you for a moment about one of the spookiest bugs I've seen. It was an app for sorting personal photos. You'd upload pics/vids off your phone, they appear in the UI, you click a folder for them to go into (or click delete to discard), etc. Simple app, right?
Well, naturally, pics from even vaguely modern phones are regularly 5MB or more. Not really something you want to sling around while a user is browsing and their main activity is going to be looking at said pic to decide what folder it goes in (or if it gets deleted). So we thumbnail. And the main app only ever shows the user the thumbnails. The backend organized things quite simply: it gets a list of images from the frontend, it assigns each of them a zero-based index, and generates a thumbnail you'll also access via index. Imagine a URL scheme like `images/0` and `images/0/thumbnail` serving the real assets and the thumbnail.
Well, this app had a bug at one point. The backend was indexing by the arbitrary order the user uploaded them in. The frontend was mostly doing this too. Unfortunately the logic for thumbnails was incorrectly indexing by the "taken time" (which was a post-upload timestamp constructed by looking at basically every available timestamp and picking the "best" one. i.e. hopefully the one the iOS camera app adds, but obviously pics come from other places too and you never know what a user will upload). The end result being users would upload pics, see a thumbnail of an accidental pic they took of their shoe, hit delete. But actually they were deleting a pic of their baby or similar.
Literally none of the testing caught this for 2 main reasons: headless tests don't look at images, and you can't write an assertion like ("does this image look like a downscale of this other image") (at least not easily... i guess image models could do it now? but probabilistic? not a word i like in my unit tests? I digress, this predated the current crop of "AI").
Now let me generalize: your frontend isn't just a weird way to call RPCs on your backend. It's part of the application. I don't think you can just hand-wave. And as we saw above, you can't even say "well the frontend is stateless! any bug is 1 deploy away from fixing!" - deploying the frontend didn't get anyone their baby pictures back.
bluefirebrand 2 hours ago [-]
> you can't write an assertion like ("does this image look like a downscale of this other image"
You can though. Maybe not exactly what you are thinking but there are some pretty good image similarity algorithms like dhash out there that do stuff like this. Mostly they get used to check for duplicate uploads, copyright materials, or "does this look like porn" style filters
This isn't something that needs image models to accomplish really.
gridspy 58 minutes ago [-]
The actual problem is that no-one had considered that this (desync between front and backend) COULD happen. Once it was realized that it was possible (and worth testing) the bug was practically solved already.
Such is true for many bugs. Even if you have unit tests, they only test on things you've thought of. It's usually the stuff you haven't thought of that gets you.
No reason not to unit test of course, but don't get a false sense of complacency or assume testing is easy either. That's why it's great to do things very carefully (and probably not with AI Agents).
3 hours ago [-]
rudi-c 11 hours ago [-]
In a related but less public way, I've found myself less motivated to write internal documentation at work. It feels like in a lot of cases, it'd be better for the reader to throw Claude at the codebase to explain things.
A separate document explaining how a system works can go out of date. While I'm quite good at highlighting the most important insights and non-obvious traits of a system, I'd still be guessing what the reader needs from my doc at the end of the day. Claude can answer questions based on what the reader is curious about and wants to learn.
Some types of document are still useful, namely higher-level directional or philosophical topics about the intention of a codebase. e.g. "we would like to eventually move X system to Rust for Y reason", "we chose mutable data structures over immutable in this part of the system because Z". But fewer than before.
patcon 9 hours ago [-]
Yeah, I feel similarly, and kinda grieve how this is not longer a valued skill... I think I've cultivated my taste in many important social dimensions through thinking about what is important to leave in docs and in a note. It's a little strange to know that rarely will people do this work of honing this sense anymore...
AdieuToLogic 6 hours ago [-]
> A separate document explaining how a system works can go out of date.
Good documentation does not explain "the how", it captures "the why."
kolinko 10 hours ago [-]
Even the latter can be done automatically from meeting notes, tickets etc.
stickfigure 7 hours ago [-]
I offer this, as someone who is heavy into AI development (as a coding assistant, not vibe-coding). I was pretty fast before and now I'm easily an order of magnitude faster.
* I scrutinize every line of backend code and frequently make revisions.
* I pay just barely enough attention to the frontend code to make sure it's not doing anything dumb.
* I pay zero attention to the CSS.
Either our expectations for UI interaction are going to go up a lot, or FE devs should start looking at product management roles. I think the asteroid metaphor is apt.
leptons 3 hours ago [-]
>But in general, frontend code is a lot more ephemeral and replaceable than other types of code.
Tell that to Digg.
If you slop oit a front-end, your users will leave. It's that simple. The front-end is the part the users use the most, nobody cares how "elegant" your APIs are, or what kind of database the system uses. The front-end matters to users, a lot.
I've seen AI take a perfectly good front-end and slop out a piece of crap that will make the users leave in droves. And when nobody raises their hand (or in my case, everyone else is in the grip of AI psychosis) then bad times are ahead.
rglover 2 hours ago [-]
Yep. I don't know why this is so hard for teams to understand: if the part your customers pay you to interact with (the UI/UX) doesn't fucking work, your customers are going to leave.
We need to kill this two-party-system-brain crap and siloing front end and back end. Learn both. It isn't difficult. It allows you to design much better systems that avoid complexity and unreliability.
kypro 7 hours ago [-]
As someone who loves FE the slop people are pushing where I work is really quite upsetting to me.
I reviewed some code earlier which clearly wasn't intended for consumed by humans and I know with certainty this dev wouldn't have understood 90% of what that code did. It looked like hours of Claude trying to force square into a round hole tbh, but it worked.
Was I going to reject the PR because of my code preferences? No, of course not. Ultimately it doesn't matter anymore. If Claude can maintain it then who cares... Even if it's broken (which it didn't seem to be) it's just FE anyway so not the end of the world.
I wish it did matter of course, but like most of coding these days, it just doesn't.
bigstrat2003 5 hours ago [-]
> Was I going to reject the PR because of my code preferences? No, of course not. Ultimately it doesn't matter anymore.
You absolutely should've rejected it. Putting slop into production is a huge trap, because now the humans can't understand it and the LLM is just going to make it worse and worse over time.
sci_prog 3 hours ago [-]
I think what OP is saying is that the fact that a human can't understand it won't matter as the code will only ever be read by AI.
paulpauper 12 hours ago [-]
Being a programmer in the era of AI now means configuring the AI and run environments to produce the sought result, than manipulating the code itself. It's like how C runs on top of assembly.
chowells 10 hours ago [-]
It's nothing at all how like C runs on top of assembly. C has semantics. Code means something without ever being run. You can check in your source code and (assuming it actually follows the C standard and your compiler's documented extensions, which almost no real C code does - C was a horrible example) it will work just as well in a year as it does today.
Try checking in only your prompts and nothing else. Just the parts you actually typed. See how well it works to regenerate the same application next week, let alone next year. Prompts are fundamentally a different sort of thing from code. Do not mix them up.
wredcoll 5 hours ago [-]
> (assuming it actually follows the C standard and your compiler's documented extensions, which almost no real C code does - C was a horrible example) it will work just as well in a year as it does today.
> See how well it works to regenerate the same application next week, let alone next year. Prompts are fundamentally a different sort of thing from code
I mean... yes, but also no. C is actually a great example. So much of the code we wrote is about manipulating the specifics of that specific computer system we happen to be using at that exact moment. Everything from cpu specific instructions to how the ram behaves or how much of it there is all the way up to how library functions operate at any given point in time.
And in relatively short amounts of time, it can all change out from underneath you.
j4yav 12 hours ago [-]
Being a programmer in the era of AI means not being a programmer
shostack 10 hours ago [-]
Being a programmer has always meant dealing with abstraction layers and climbing up the abstraction ladder.
You are simply learning a new language, whose syntax happens to look like English (or whatever language you speak), but with new, undiscovered, and constantly changing design patterns and best practices.
josephg 9 hours ago [-]
It depends how much you outsource to the llm.
If you outsource everything to a llm, I just don’t think you get very good results right now. Language models aren’t great at remembering all the little design decisions that are needed in medium to large projects. The code ends up riddled with semi-conflicting design choices, which have been slammed together and maintained by context inertia. For a lot of projects this is more than fine - sometimes higher quality work simply isn’t worth my time. But for a lot of projects, you will pay for that slop later.
But I think there is a useful middle ground. If you carefully review all the decisions an llm makes, I think you can often be more productive than just programming everything by hand. But it’s a very different way to do engineering. I think I learn more this way than if I program by hand - if only because I’m touching more code. My mind roves around the design space a lot more. I don’t lock in as much as when I’m programming each piece individually.
If you work with an llm like this, your engineering skill matters more than ever.
chpatrick 10 hours ago [-]
Typing the code was never the interesting part.
adamredwoods 7 hours ago [-]
>> Typing the code was never the interesting part.
Code is fascinating! An abstract language to compile to program a CPU. So many ways to do this!
Now we're using natural language, which at times is extremely verbose. "[{}]" versus "array of objects", for example.
qalmakka 10 hours ago [-]
For me it definitely was
jplusequalt 10 hours ago [-]
>Typing the code was never the interesting part.
But solving hard problems and developing systems intuition was. If you're trying to tell me that people working on code bases predominantly written by AI are still solving hard problems themselves, or understand the systems the AI is building, I think they're lying to themselves.
chpatrick 6 hours ago [-]
I work on a codebase with a lot of math and I've both learned and implemented a bunch of things that were beyond my level before I could iterate on it with AI. Same for binary reverse engineering. On the other fixing tedious bugs by hand and typing the code in is not something I miss at all.
kolinko 10 hours ago [-]
From what I’ve seen they get to the level of understanding of systems way faster than we did because they iterate and experiment with this from day one. We had to spend years understanding code syntax, and other minutia.
Also, you need a different kind of toolset/skillset to grok a system that was vibe coded all the way - different failure scenarios. Older devs tend to just say “see, I told you, it’s just spaghetti underneath, you need to clean it up”, and the newer gen learns to work with that spaghetti.
avgDev 10 hours ago [-]
I have a blazor app in poduction, Codex made errors which it could not fix and it required me reading documentation. I won't argue that it didn't make my life simpler, tasks which would take me days are done in hours, sometimes without touching code.
unshavedyak 10 hours ago [-]
Yea, i still deal with a ton of code in AI heavy workflows. If anything the frustrating part is absorbing the code quickly enough. AI (Claude for me) writes in cryptic text and the code flows can often be non-obvious.
I need (and am exploring) custom review tooling to improve this AI->Human code flow. Reviewing PRs were always the hardest part for me in programming. They were often full of the developers decisions and you have to rediscover those as you're reading code for it to make sense[1]. However i find this even more difficult to discover these decisions from AI.
However unlike human PRs we can ask more of AI. Rarely have i had a developer put on a presentation for a PR - but AI could right? AI could produce a guided walkthrough of the code. Not sure if it will help of course, but my thought is we're all stuck in the old "PR review flow" but instead of PRs it's AI - and the volume of them is far greater than anything prior. So i expect we need to tweak how we review, how we get information from LLMs.
[1]: I'm speaking generally, and about larger PRs. Not some small func where you can easily see what it does. Business logic and complex code can be difficult to decipher in PRs, imo.
othmanosx 1 hours ago [-]
I'm building https://pyor.review to fix this problem, try it out and let me know what you think.
hirvi74 11 hours ago [-]
That is why I am very thankful for my job. We are not really allowed to use LLMs for much of anything.
bigstrat2003 5 hours ago [-]
That sounds like an absolute dream.
12 hours ago [-]
whateveracct 12 hours ago [-]
thanks i hate it
sitzkrieg 12 hours ago [-]
luckily there are still some people who know and care about actually understanding what is happening. but dwindling. market correction needed to wash larpers out
pmestha 10 hours ago [-]
[dead]
jdw64 11 hours ago [-]
[dead]
sitzkrieg 12 hours ago [-]
writing about your dates with an ai prompt are not that interesting
Another winner takes all situation. This and the other post on agent tool use[1] makes me think we are in a period of great homogenization. I'm sure there's a group that's delighted about this but for me, it just makes me feel a little uneasy.
[1] https://armature.tech/blog/which-tools-coding-agents-install
Vue's reactivity is quite similar to Solid's, AFAIK, so I wonder why there would be so many issues with Solid.
We have also started to have success getting LLMs to create custom lints for us to handle tricky edge cases. For example, discovering deep watches or tricky interactions - you can get a fair way asking an LLM to create a lint using a codemod library (in our case, vue-morph) that fires on this example but not on that example.
It's called alignment. And that's the correct word for it in my opinion.
The most important part is that we have to find a way to tackle the knowledge enshittification problem.
Because now that slopcode and slopposts are everywhere, the average quality level will decrease. We had the peak internet knowledge, and it's now gradually getting worse.
That's not a personal opinion, that's how attention matrixes and their keys/values computation works.
Alignment is such a polite term for "a giant boot that is crushing all of the uniqueness out"
Once it is done crushing, congrats! Everything is aligned.. by being flattened
She's now working on a biotech start-up pre-funding. They have pretty much zero money. They want to redesign their website.
I set her up with my deepseek key and she's been using flash-v4 with image detection (I think deepseek says it's still experimental). She just provides the current website, tells how she wants it to look and it works great. I mean it's obviously ai generated but she gets quick results and is able to tweek things to look better by just telling deepseek what to do. She was even able to change the text in one of their images to its new product name without having to contact the graphic designer.
This is a simple example. Basically it's one of those earlier jobs that you could get someone to bid on for $x but now you can do yourself for $20.
I did the first few prompts (single static page, basically a brochure, don’t worry about hosting) into ChatGPT to get her started and a few days later she sent me a .zip which I uploaded.
Only took a while because she wasn’t paying for ChatGPT so had to wait for the free limit to reset quite a few times.
But overall it was super empowering for her.
The short version, wasn’t for wanting to save money, but simply a matter of it not being worth the hassle to any of us to subscribe and then later cancel for such a small scope of work. If it was too frustrating I would have let her use my Claude sub.
Also, she’d been meaning to have it updated for years, a few extra days was nothing.
She did short sessions in spare time between other things, the wait between was maybe a little frustrating, but also gave the benefit that she would have had better clarity develop between sessions.
Website is not key to her business where it’s mostly word of mouth at this point (she’s been practicing for >20 years). Goals of website were:
- Findable in Google by “psychologist/therapist <area name>” (she also has a Google. Business profile so is findable on Google Maps).
- Minimal copy. A comforting sentence or two to state philosophy, qualifications, therapy types offered, where located, how to contact.
- Doesn’t feel dated.
Essentially it’s meant to complement the word of mouth aspect and maybe bring in the occasional completely new patient.
If it because the poster's mother dislikes the idea of subscriptions, then I totally get it. (Though I admit I have no idea if this has anything to do with the poster's mother's decision.)
I'll go out of my way as much as I can to avoid signing up for anything that is a subscription because of how horrible the entire corporate world has abused subscription dark patterns over the past couple of decades.
These days just the packaging of anything into a subscription makes me assume there is intent to screw people out of money.
While signing up for LLM usage is fairly low risk as far as subscription lock-in goes, someone non-technical might not be aware of that fact.
People already knew about her and website is essentially just “this is what I do, where I am and how you can contact me”.
Anecdata: I’d be more likely to use the services of a company with a good, old-style site than a bad, new style site. Things like pop-overs, text that animates in as you scroll, banner images that take up most of the “abive the fold” are all red flags for me.
Oh, and the most common one: “Read more”.
A modern site that avoids all those can be great. But those are rare, IMO.
It depends what "nicer" means. Paying a web designer/developer to create a bespoke website doesn't guarantee that said website will have a better UI/UX and, most importantly, "convert" at a higher rate. Not every web designer/developer understands IA, content, performance optimization, etc.
The popular AI tools produce websites that are clearly AI-produced if you know the patterns, but that doesn't mean they can't be usable and quite effective at converting. And if you have a bit of skill with prompting, AI can be really good at working through performance bottlenecks, etc.
Scope of work and urgency were so minimal that it was simply not worth the hassle to actually subscribe and then have to unsubscribe later.
If there was no free option we could have done it on my Claude sub or she would have just paid.
This perspective declares all the personal websites of people worthless, however, they are priceless.
Because people's curiosity and creativity is priceless as well.
Similarly, why create art and share it around if it doesn't bring in customers? Why make music, take photos, dance? Do we live to serve customers, or do customers' existence serve us to live a better life?
Questions, questions...
If OP's mother runs a donation-funded pro-bono psychology practice then you can translate the dollar signs to units of happiness or whatever (which I would imagine is her real goal regardless).
This person is spending her time to create the website (with ChatGPT's help). How much is that time worth? Of course when it's your business hourly pay is tricky, but I imagine she values her time highly enough that $20 is not worth very much of it.
If their company can do well with this website, her psychology practice can do as well.
Some of the best services I got was from professionals with no or mundane online presence. Instead, their abilities and expertise moved them to the top in their respective fields, and the whole community knows how and when to reach them.
So, maybe a shiny website is not a hard-requirement for a good psychology practice, IDK.
So, the thing is, maybe this was her way to explore new things and decompress while doing some mundane thing from her perspective for free. Sometimes it's not that $20 which you can pay without any negative side-effects, but the desire to see how far the thing goes without the token, or just because you don't feel any urgency to do the task, so that $20 looks like an unnecessary waste.
I have been in both places.
If once she's decided to update the website—surely it's worth more then $20 at that point? Otherwise, she probably shouldn't be spending any time on it herself either, given the opportunity cost.
Obviously she decided otherwise, I just find it kind of surprising.
Like, in general, I'm always kind of surprised at what people are and aren't willing to pay for. People will suffer through horrible full screen ads in mobile games instead of paying $5 one time to turn them off. And they'll do this on a phone that costs $1,000+. I don't know their financial situation, but I would buy a cheaper phone and get rid of the ads...
the problem here really, from both sides of the argument, is the assumption that humans are rational economic actors.
One side assumes that it is not worth 20 dollars to update the site quickly thus she does not do it, but really for that to be true (given costs of psychologists sessions etc.) then it would not even be worth updating the site, or paying for the site hosting or the domain at all.
The other side assumes that given that she is updating the site it must be worth paying 20 dollars to do so quickly and asks why she does not, given that it is worth updating the site.
If humans are rational economic actors she should be updating her professional site because it has some professional benefit to her that she is aware of, but this creates the two problems stated above.
This problem, and the examples you give, are resolved by understanding that humans are not really rational economic actors and the reason that she is updating the site and not paying the extra 20 dollars at the same time cannot be resolved to a non-contradictory answer.
We are at best, partially rational economic actors. Rational-like.
I know people who won't subscribe to a service, but go through great pains to get the thing the service offers (another brand, similar yet inferior service, etc.).
For example, if an application I use has ads (i.e. a game), and it needs a subscription to remove these ads, I'll simply won't install it, or get the paid version of it from the start. For me, playing a game with no end and paying monthly to "hide" advertisements doesn't worth it.
* You propose I buy your ¤4 overhyped toothbrush. If I spend 10 minutes digging around, I could find a sub-¤1 toothbrush. Effectively I'm doing 10 minutes of work at less than minimum wage in order to avoid owning the premium toothbrush. Do I do this? I might! The reason is that I want no part in your hype.
* You offer me a loyalty scheme that will genuinely save me money if I participate. I only have to pay attention to your offers and routinely identify myself and I might get 10% savings, all the time. I decline this because you don't get to use my brain cycles for your profit, even if I profit too.
* You offer me a free thing that happens to track me and funnels data to data brokers. I decline it even though it does me no actual harm at all, because I don't want you to make money from personal facts about me, even when the facts are robotically aggregated and anonymised. Ethics are at stake: ethically speaking, you can just piss off. That is worth more than a free gadget, and it's not even an equation.
Did you notice that this is completely unrelated to the idea that the $20 would turn a profit for the business?
It's just the argument "$20 isn't very much money, so why not spend it?".
Because you have it.
You mean the very web sites that the "AI" trained on?
If you think AI can't make buggy code, there are several dozen thousand comments on HN that disagree.
For small shops and startups, this probably doesn't matter. For mission critical sites, who's more dependable? AI is a tool, that's all it is.
Plus the context here isn’t any random person, but people who intend to pay for website development for their businesses.
Is that legal... ? I admit I don't know much about graphic design is contracted.
https://news.ycombinator.com/item?id=49382041
If it's a stock image or a licensed image, they need a license to alter the original image.
like the OP, all those years of learning how it works under the covers gives me a distinct advantage since i can easily tell what is slop and what is going to perform. as well as how to get AI to iterate and fix the things it isn't good at (yet). i feel like now i have super powers. i love it and can't get enough.
the fact that your wife can be productive at lower cost means that more products will be built and more opportunities will be made. instead of spending money on website design, her business can spend money developing biotech.
i welcome that, even if it means that things will change from the past and those that have made a career out of charging thousands will get replaced by a $20/month subscription.
Granted, it seems it is easier now to give prompts to an LLM so it will spit things out than back then where you had to know the tool and fiddle with menus and thingies to sort of try to produce a result.
But the drawback seems to be the same for both - lots of unreliable and unoptimized code that will go live if you don't know what they're doing under the hood and can potentially cause issues in the future. Remember that all this tools do are sorts of interpolation. I've seen lately lots of "modern" websites with tons layers of !important in their CSS and who knows the monstrosities that they have with their JS.
Meanwhile I and all people like me still don't have a job because all of this and the alleged "thousands" I was getting for doing this things.
the beauty of what's happening today is that AI might produce slop on the first try, but you can also refactor just as easily too. "clean up all !important and optimize the code for speed", is just as easy of a prompt and it'll go off and do a fantastic job at that. that is what the OP was talking about in his article.
you don't have a job because you're not adapting to this new world order quickly enough. i predict that there will be insane demand for porting existing applications off these over priced SASS contracts and building tailored products for businesses. as much as they are trying to convince people, you don't need a $5m/yr salesforce / servicenow contract when you understand the business model and can envision a better solution to the actual problem out of thin air.
i'm burning 500m+ tokens a day on a $200/mo subscription. it is creating 10000x more value for me. it is no longer how much you know HTML/CSS, it is how well you know how to get AI to do what you want it to do and the only way to develop that skill, is to do it.
I'm sure many people will think that; and I'm also fairly confident that 5 years later they'll take their obscure, bug-ridden, vibecoded monstrosity that nobody really understands, throw it out, and get a salesforce contract. Technical debt doesn't disappear just because you have agents working for you; in fact, it is exploding right now, and I would bet good money that 2-3 years for now there will be a flourishing cottage industry of consultancies specialized in dealing with such monstrosities.
If I can vibe code up a solution that fixes my problems for $200, it doesn't matter what happens in 5 years. The rate of change that's happening today in the increase in quality of the output of the models, I can just tell it to fix whatever we have and make it better.
When your software has to produce legal documents, satisfy auditors, and certify a bunch of things to shareholders and governments, I'm sorry but your $200 vibecoded hack is not going to cut it. You will have to get it certified, to get it audited, to get it secured according to this and that legislation, to prove where it gets each and every number and how it modifies it, and then you will have to maintain it because standards and laws change every other day. Sure, get an agent to cook you up a full consolidation solution, see how quickly you get laughed out of the room by grown-ups.
Btw, I am not "adversed to things" - the stuff we do has agents built-in, that do all sorts of wonderful things. The difference is that we can demonstrate that they do them right, with financial intelligence standardized and battle-tested across thousands of customers all over the world. Our customers don't have to worry about rewriting their pile of vibed hacks, or about being humiliated by auditors, because we take care of all that stuff for them. That's worth more than the pennies you save by having cousin' Vinnie vibe up a multidimensional financial engine that takes 3 days to calculate trillions of useless intersections before falling over.
Get ready. AI is coming for every single industry, full steam.
It is, indeed. The C-Suites at every company are making plans: https://www.youtube.com/watch?v=DmU9uovmT2A
But more real... Giacomo fails to take into account the concept of when OpenAI decides to create an audited financial service that guarantees that their output is valid. ChatGPT Work is already a beginning of that future.
AI is another tool in the toolbox, not magic. It's not about being pro or against it, it's here already (hey, we sell it!) and obviously it will continue to get better; but it won't magically solve everything for $2.
it has the best spam control on the planet.
i'd never use anything else.
No, of course you don't, you write email servers.
Sure, your local garage will now do their accounting in vibed apps instead of vibed Excel files. I suspect multinationals will choose not to.
As I said, I already know what AI is doing - I already use it just fine, I even help building and selling it. The impact it is having is obvious. But like recipe books did not turn everyone into Michelin chefs, it won't turn hacks into rigorous builders of trusted systems.
i just built a financial dashboard for my business. in realtime, i'm sucking in all the data from quickbooks, mercury, stripe, deel APIs and presenting it to myself, and my investors. it does all that sitting in cloudflare as a worker, for $5/month. took me a couple weeks of iteration, not a single line written.
from that i just told ai... "i'd like to get rid of quickbooks because yesterday it was down and i couldn't log into it. figure out what i'm using there and present me an interface that allows me to do whatever i'm doing in quickbooks, but with my existing data from stripe, deel and mercury."
it then dutifully went off and built me that app and now i'm running it in parallel and synchronized with quickbooks, until i feel that i can just turn that off. it is customized exactly to my business workflow and easily maintained with full unit tests. it costs me nothing but a $200/mo codex subscription and a few hours of work.
Now, still as a frontend engineer albeit much more senior. The writing is on the wall, again. It's time to reskill for AI.
It's not bad news.
We as experienced engineers are needed to help build in the guardrails, frameworks, the new tooling, etc. There is a lot of work that is needed that requires actual engineers with technical experience.
Like the early internet, I see this as a new beginning and we get to decide how it evolves.
That was maddening to read. Here I was thinking we should all be migrating to better performing frontend solutions. Does it really take an agent that many more tokens to write Lit or regular HTML and HTMX?
Definitely not. That's skill issues. The shadow DOM can be a bit tricky.
https://sparkbox.com/foundry/helene_and_mobile_web_performan...
Discussion regarding that post: https://news.ycombinator.com/item?id=46494734
The smaller the problem, the less risky it is to do this, regardless of the nature of the problem. This is not a frontend-specific issue today.
Systems engineering isn’t like that. Vibe coders beware: A database could silently corrupt data, or have latent security vulnerabilities. It might have a badly designed query language that will be difficult to change later. But frontend code can be rewritten at will. It’s a perfect target for LLMs.
Whatever lets you sleep at night man. If you really think you’re better than the machine at spotting arcane Unix incompatibilities, or that you’re somehow more “safe” than frontend jockeys, I’ve got really bad news for you.
Any website that has any UI state management or does any kind of network calls can be invisibly broken in many, many ways
??? Have you never debugged weird react state before??? Have you never used a nontrivial SPA before? Even the most simple react SPA has about a trillion states.
I don't really know how to respond to your statement than "no, they can definitely be invisibly broken."
Other kinds of software - for example, the backend of a website - have far more invisible failure modes. Security. Correctness. Performance. Bad API design leading to overfetching. Etc. Software works great on your machine and when you demo it, but it falls apart at scale. Endpoints that aren't secured properly. Race conditions cause silent data corruption. Memory leaks. And so on.
If claude messes up writing a react frontend, we're more likely to find the problem quickly. And frontend bugs usually don't continue to cause problems after they've been fixed. Silent bugs in the backend are more dangerous and more expensive.
If your state management gets out of sync with the form controls your users are working with it can become pretty high risk because now users see one thing and something else actually gets sent to the backend.
Like hunger and diseases are global problems not to be worried about.
How about we worry about this smaller problem today so the bigger problem tomorrow is less big. Or doesn't materialize at all?
Do we have to sleepwalk off this cliff?
It already slurped "the internet". You can't seriously say it doesn't count!
LLMs piping out UIs from PM prompts aren't solving that imho.
This is a weirdly reductive take on frontend correctness. Just for the record, I'm a backend dev. So I don't have much stake in this game.
This idea is, of course, not uncommon. "If the backend has to treat the frontend as adversarial anyway, and has all this cool stuff (constraints etc) for guaranteeing consistency of the system, then the frontend can just do whatever, right?" It plays into a lot of biases around typical frontend devs, typical backend devs, language stereotypes, etc. So it _sounds_ good.
Let me tell you for a moment about one of the spookiest bugs I've seen. It was an app for sorting personal photos. You'd upload pics/vids off your phone, they appear in the UI, you click a folder for them to go into (or click delete to discard), etc. Simple app, right?
Well, naturally, pics from even vaguely modern phones are regularly 5MB or more. Not really something you want to sling around while a user is browsing and their main activity is going to be looking at said pic to decide what folder it goes in (or if it gets deleted). So we thumbnail. And the main app only ever shows the user the thumbnails. The backend organized things quite simply: it gets a list of images from the frontend, it assigns each of them a zero-based index, and generates a thumbnail you'll also access via index. Imagine a URL scheme like `images/0` and `images/0/thumbnail` serving the real assets and the thumbnail.
Well, this app had a bug at one point. The backend was indexing by the arbitrary order the user uploaded them in. The frontend was mostly doing this too. Unfortunately the logic for thumbnails was incorrectly indexing by the "taken time" (which was a post-upload timestamp constructed by looking at basically every available timestamp and picking the "best" one. i.e. hopefully the one the iOS camera app adds, but obviously pics come from other places too and you never know what a user will upload). The end result being users would upload pics, see a thumbnail of an accidental pic they took of their shoe, hit delete. But actually they were deleting a pic of their baby or similar.
Literally none of the testing caught this for 2 main reasons: headless tests don't look at images, and you can't write an assertion like ("does this image look like a downscale of this other image") (at least not easily... i guess image models could do it now? but probabilistic? not a word i like in my unit tests? I digress, this predated the current crop of "AI").
Now let me generalize: your frontend isn't just a weird way to call RPCs on your backend. It's part of the application. I don't think you can just hand-wave. And as we saw above, you can't even say "well the frontend is stateless! any bug is 1 deploy away from fixing!" - deploying the frontend didn't get anyone their baby pictures back.
You can though. Maybe not exactly what you are thinking but there are some pretty good image similarity algorithms like dhash out there that do stuff like this. Mostly they get used to check for duplicate uploads, copyright materials, or "does this look like porn" style filters
This isn't something that needs image models to accomplish really.
Such is true for many bugs. Even if you have unit tests, they only test on things you've thought of. It's usually the stuff you haven't thought of that gets you.
No reason not to unit test of course, but don't get a false sense of complacency or assume testing is easy either. That's why it's great to do things very carefully (and probably not with AI Agents).
A separate document explaining how a system works can go out of date. While I'm quite good at highlighting the most important insights and non-obvious traits of a system, I'd still be guessing what the reader needs from my doc at the end of the day. Claude can answer questions based on what the reader is curious about and wants to learn.
Some types of document are still useful, namely higher-level directional or philosophical topics about the intention of a codebase. e.g. "we would like to eventually move X system to Rust for Y reason", "we chose mutable data structures over immutable in this part of the system because Z". But fewer than before.
Good documentation does not explain "the how", it captures "the why."
* I scrutinize every line of backend code and frequently make revisions.
* I pay just barely enough attention to the frontend code to make sure it's not doing anything dumb.
* I pay zero attention to the CSS.
Either our expectations for UI interaction are going to go up a lot, or FE devs should start looking at product management roles. I think the asteroid metaphor is apt.
Tell that to Digg.
If you slop oit a front-end, your users will leave. It's that simple. The front-end is the part the users use the most, nobody cares how "elegant" your APIs are, or what kind of database the system uses. The front-end matters to users, a lot.
I've seen AI take a perfectly good front-end and slop out a piece of crap that will make the users leave in droves. And when nobody raises their hand (or in my case, everyone else is in the grip of AI psychosis) then bad times are ahead.
We need to kill this two-party-system-brain crap and siloing front end and back end. Learn both. It isn't difficult. It allows you to design much better systems that avoid complexity and unreliability.
I reviewed some code earlier which clearly wasn't intended for consumed by humans and I know with certainty this dev wouldn't have understood 90% of what that code did. It looked like hours of Claude trying to force square into a round hole tbh, but it worked.
Was I going to reject the PR because of my code preferences? No, of course not. Ultimately it doesn't matter anymore. If Claude can maintain it then who cares... Even if it's broken (which it didn't seem to be) it's just FE anyway so not the end of the world.
I wish it did matter of course, but like most of coding these days, it just doesn't.
You absolutely should've rejected it. Putting slop into production is a huge trap, because now the humans can't understand it and the LLM is just going to make it worse and worse over time.
Try checking in only your prompts and nothing else. Just the parts you actually typed. See how well it works to regenerate the same application next week, let alone next year. Prompts are fundamentally a different sort of thing from code. Do not mix them up.
> See how well it works to regenerate the same application next week, let alone next year. Prompts are fundamentally a different sort of thing from code
I mean... yes, but also no. C is actually a great example. So much of the code we wrote is about manipulating the specifics of that specific computer system we happen to be using at that exact moment. Everything from cpu specific instructions to how the ram behaves or how much of it there is all the way up to how library functions operate at any given point in time.
And in relatively short amounts of time, it can all change out from underneath you.
You are simply learning a new language, whose syntax happens to look like English (or whatever language you speak), but with new, undiscovered, and constantly changing design patterns and best practices.
If you outsource everything to a llm, I just don’t think you get very good results right now. Language models aren’t great at remembering all the little design decisions that are needed in medium to large projects. The code ends up riddled with semi-conflicting design choices, which have been slammed together and maintained by context inertia. For a lot of projects this is more than fine - sometimes higher quality work simply isn’t worth my time. But for a lot of projects, you will pay for that slop later.
But I think there is a useful middle ground. If you carefully review all the decisions an llm makes, I think you can often be more productive than just programming everything by hand. But it’s a very different way to do engineering. I think I learn more this way than if I program by hand - if only because I’m touching more code. My mind roves around the design space a lot more. I don’t lock in as much as when I’m programming each piece individually.
If you work with an llm like this, your engineering skill matters more than ever.
Code is fascinating! An abstract language to compile to program a CPU. So many ways to do this!
Now we're using natural language, which at times is extremely verbose. "[{}]" versus "array of objects", for example.
But solving hard problems and developing systems intuition was. If you're trying to tell me that people working on code bases predominantly written by AI are still solving hard problems themselves, or understand the systems the AI is building, I think they're lying to themselves.
Also, you need a different kind of toolset/skillset to grok a system that was vibe coded all the way - different failure scenarios. Older devs tend to just say “see, I told you, it’s just spaghetti underneath, you need to clean it up”, and the newer gen learns to work with that spaghetti.
I need (and am exploring) custom review tooling to improve this AI->Human code flow. Reviewing PRs were always the hardest part for me in programming. They were often full of the developers decisions and you have to rediscover those as you're reading code for it to make sense[1]. However i find this even more difficult to discover these decisions from AI.
However unlike human PRs we can ask more of AI. Rarely have i had a developer put on a presentation for a PR - but AI could right? AI could produce a guided walkthrough of the code. Not sure if it will help of course, but my thought is we're all stuck in the old "PR review flow" but instead of PRs it's AI - and the volume of them is far greater than anything prior. So i expect we need to tweak how we review, how we get information from LLMs.
[1]: I'm speaking generally, and about larger PRs. Not some small func where you can easily see what it does. Business logic and complex code can be difficult to decipher in PRs, imo.