Hacker News Reader

Yeah, as a primarily backend engineer dealing with either weird technical problems Claude can't get quite right or esoteric business domain problems Claude has no idea about (and indeed, it may be only a few people in one company could help with) - Claude isn't that useful.

But random stuff like make a web app that automates this thing or make an admin panel with auto complete on these fields and caching data pulled from this table.

It is like infinity times faster on this tedious boilerplate because some of this stuff I'd just have never done before.

Or I'd have needed to get some headcount in some web dev team to do it, but I just don't need to. Not that I'd have ever actually bothered to do that anyway...

One thing I'd recommend for weird business domain projects as a starter is getting it to create a "wiki" of markdown files of all the logic (I suspect this may have been on your to-do list anyway!). You may be pleasantly surprised at how well it does it, and then you can update your claude.md file to point to them (or even put it in there, but it is maybe overkill).

Asking for documentation is good. I had a data structure in Java that was a bunch of nested Map<String, Object>(s) that I partially understood and asked my agent to write me some sample JSON documents and... it just did it and it was a big help for manual coding against that structure.

When I can't figure out something about a library I have often loaded the git repository into my IDE and checked out the version I was using, then used the IDE to study the code. Now I do that and ask the agent questions about the code like "How do I do X?" (often it sees the part in the doumentation that I missed) or "Where is the code that does Y?" It greatly accelerates the process of understanding code.

Agreed - LLMs are great at reading and synthesising docs. At various points I've gotten pushback when I ask people to document because no-one will look at the docs, but now we have LLMs to read and link to docs for us. And traditional search still works, of course, but worse.

I've found that it's mainly good at doing coding work that basically anyone who's memorized the content of the relevant docs could do. So I mostly only use it as glorified scaffolding, as it crashes and burns on complex stuff in big legacy codebases.

> This took less than an hour while I was watching TV.

I certainly could not review all of those changes in an uninterupted hour. I'd need to test the design changes on multiple browsers, check they respond to zoom and window sizing. I'd have to read through the tests and check that they were not just nonsense and returning true to pass. There's no way I could do all that while watching TV in 1 hour.

This is for a janky backend admin panel, not a customer facing product. If it’s way better than it was before, which likely wasn’t responsive either, it’s a win. Understanding the context of a project is important.

And the tests? To me, if it was something important enough to have tests for in which case it's important to check the tests are valid so I'd have to review them

It takes me 5 mins to review e2e UI tests and watch it go through them. It's literally filling fields and making sure certain things happen.

I think you’re overestimating the complexity of the tests required here. But I take it from the rest of your comment that you understand my point.

I'm convinced the vast difference in outcome with LLM use is a product of the vast difference in jobs. For front end work it's just amazing. Spits out boilerplate and makes alterations without any need of help. For domain specific backend, for example robotics, it's bad. Tries to puke bespoke a-star, or invents libraries and functions. I'm way better off hand coding these things.

The problem is this is classic Gell Mann Amnesia. I can have it restyle my website with zero work, even adding StarCraft 2 or NBA Jam themes, but ask it to work in a planning or estimation problem and I'm annoyed by its quality. Its probably bad at both but I don't notice. If we have 10 specializations required on an app, I'm only mad about 10℅. If I want to make an app entirely outside my domain, yeah sure it's the best ever.

If there is an abundance of medium / stack overflow articles it does well.

Frontend dev for 13+ years here. In my experience it’s pretty bad at anything but basic frontend stuff. I’ve tried all the models, editors, Claude code etc.

It’s constantly wrong about the simplest things. Just now it was hallucinating about CSS grid properties.

I’m convinced that how good AI seems is inversely correlated to someone’s knowledge in that domain, as you also mentioned.

Still super useful in my day to day but I have to hand hold and correct it constantly.

I am very bad at frontend and I know frontend peeps keep saying claude/llms are bad at it, but now, for the first time in my 40 year career, I deliver frontend that are looking better and functioning better than whatever I see in hip products people 'designed with love in blah'. And our clients agree. If the css is correct or not, I don't know as I never really found the energy to learn it and now I don't need to and can focus on the business logic. The endresults look and work phenomenal: not sure why I would care if the css is the best. Especially nice when I have been using something for a long time and some things I always found lacking: now I add them in in minutes: auto completion here, move creation inline there, add drag and drop: ah but on mobile make it like that. Everything just works and in hours vs days or weeks it was before.

I agree to a point. But I also would like to point out how alarming your take is.

I mean you can easily compare this to trades and construction. Would you want a house that's built in a week by cheap foreign workers that don't know what they're doing? The end result looks great on the outside, and you can always let some other cheap worker fix some issues you're having! The electricity works! Until it doesn't and a fire breaks out.

I get it - the hype is based around the quick gains you can absolutely have. The gains are insane, I have been able to be more productive at boilerplate and repetitive tasks too. But just building software isn't hard. Building software that lasts, building software that is rock solid, efficient and maintainable, that's hard!

It's sickening to me how quickly people want to throw that in the garbage. All because it saves a few $ in development time, quality is suddenly a metric that is completely ignored, rather than weighed in.

It's going to bite people in the ass.

Nah, I specifically said HTML/CSS; I don't think crap CSS (if it works and is fast) will make the world a worse place. I don't include any logic/code into this take, just design/layout/ux. And in my workplace that's also the markup stuff that gets rewritten the most, so it's throw-away anyway compared to the backend stuff (we have code running that's well over 20 years old on the backend; frontend is 1-3 years).

I agree with you we should have quality standard, but I also think it's 100% inevitable that this will all go out the window, in most companies and if that happens, our asses will be bitten.

Design/layout/ux have value (and I don't think you're saying they don't!) - when it's done by somebody who knows what they're doing, the result is perceivably better than when it's done by somebody like me who learned HTML for her myspace blog. Stuff like accessibility, "responsive design," theming, and stuff I probably haven't even heard of, all make websites easier and more intuitive to use.

As a silly example, an LLM will happily add all sorts of animated gifs to the screen for me, even if it makes the page take three times as long to load and more difficult to use.

It's a shame to lose well-crafted experiences in favor of the lowest-common-denominator that LLMs put out, just because they're cheaper.

I guess the main takeaway is that you don’t care about the quality of the generated code. The end result is all that matters.

If I ask it to “add drag & drop”, I already know in my mind what the correct code should look like, because I’ve implemented it many times in the past. LLMs just never deliver the -code- that I want. The end result might look ok and the drag & drop will work, but the code will be atrocious and on first glance I can pick out 10-20 mistakes that I’ll have to ask it to fix. And even if I ask for a fix, I’ll never get the same code quality as hand written code. And how can I push this kind of sub-par code to an employer’s repo when I know that I can (and should) write better quality code myself. This is what I’m being paid for right?

> This is what I’m being paid for right?

That's a good question. Because developers can sometimes have a bit of an unhealthy love affair with their own code.

Does your employee actually care as much about code quality as much as you do?

They would probably ask what is the downside of accepting this lower quality code, given the upside you presented:

> The end result might look ok and the drag & drop will work

Which you did quickly, saving them money (in theory).

Well said.

No, you’re being paid to deliver the product to the _company’s_ chosen standards, not yours. And in my experience, fast and cheap and cheerful is often exactly what they want. They’ll have changed their minds next week and want it all ripped out for something else anyway.

Exactly. _So much_ software dev is "throwaway" in my experience. Of course some isn't. Landing pages, A/B tests, even a lot of feature work is very speculative and gets put in the trash.

I do wonder if this is why there is such a gulf in LLM experience. If you're doing hardcore huge scale distributed systems then I can (maybe?) see why you'd think it is useless. However, that is very niche imo and most software dev work is some level (unfortunately) of virtually throwaway code. Of course, not all is - of all the ideas and experiments, some percentage is hopefully very successful and can be polished.

Indeed. And you get some engineers who only want to code perfect bespoke code all the time and sometimes that’s useful and sometimes it’s not. It depends on the requirements of the client, just as it would in any other trade. We need to be flexible to both the clients time and money budget, and also make code that suits the criticality of the task at hand. If you can’t lower your standards to fit a use case, I think it’s actually a bad thing.

Are you implementing designs that were given to you or having AI generate the design as well? I could see it being better at the latter.

I don't think it's correct to generalize front-end work like this. I've found it very underwhelming for the kind of front-end stuff I do. It makes embarrassing mistakes. I've found it quite useful for a lot of the braindead code I need to write for CRUD backends though.

It's good at stuff that most competent engineers can get right while also having the sort of knowledge breadth an average engineer would lack. You really need to be a domain expert to accurately judge its output in specific areas.

Well I wasn't intending to generalize front end work as "easy enough for LLM" what I meant to say was that, since I have no experience with it, its output good enough for me. Classic Gell-Mann amnesia

This rings true to me, but I'm not a frontend dev. So I'm not a good judge if what makes good frontend code. Where I do know my stuff, I'm not at all impressed by LLM code.

So perhaps LLMs are just entry level devs in general. Who can't learn. Who won't ever gain seniority. It would make sense, after all, they were trained on the Internet and Stack Overflow, which is mostly filled with entry level questions and answers.

> while I was watching TV

This to me is one of the real benefits. I can vibe code watching TV. I can vibe code in bed. I can vibe code on the plane waiting for takeoff with GitHub Copilot Agents.

To me this is sad. I love programming. It was always a fun job. I don’t want to watch TV instead of programming.

Then don't. You'll likely outperform those who do. Not making any value judgements; both have their place. Sometimes I want to be locked in and sometimes I want to let Claude spin while I take a walk.

Do you love finding every weird CSS important hack, every RBAC refactor, or marching through the codebase to put a key where every piece of text is when i18n comes along?

Lots of coding work is interesting, but plenty is just tedious.

Then code personal projects while you vibe code your job. The thing about having more free time, is you can use it on whatever you want.