Live data from Hacker News

Web development is fun again

ma.ttias.be

361–370 of 658 posts

Re: Web development is fun again

#361

Earlier quoted context omitted.

Wait till the VC tap gets shut off. You: Hey ChatGPT, help me center a div. ChatGPT: Certainly, I'd be glad to help! But first you must drink a verification can to proceed. Or: ChatGPT: I'm sorry, you appear to be asking a development-related question, which your current plan does not support. Would you like me to enable "Dev Mode" for an additional $200/month? Drink a verification can to accept charges.

Just you wait until the powers that be take cars away from us! What absolute FOOLS you all are to shape your lives around something that could be taken away from us at any time! How are you going to get to work when gas stations magically disappear off the face of the planet? I ride a horse to work, and y'all are idiots for developing a dependency on cars. Next thing you're gonna tell me is we're going to go to war f…

The reliance on SaaS LLMs is more akin to comparing owning a horse vs using a car on a monthly subscription plan.

Re: Web development is fun again

#362

Earlier quoted context omitted.

Wait till the VC tap gets shut off. You: Hey ChatGPT, help me center a div. ChatGPT: Certainly, I'd be glad to help! But first you must drink a verification can to proceed. Or: ChatGPT: I'm sorry, you appear to be asking a development-related question, which your current plan does not support. Would you like me to enable "Dev Mode" for an additional $200/month? Drink a verification can to accept charges.

Calling it now: AI withdrawal will become a documented disorder.

We already had that happen. When GPT 5 was released, it was much less sycophantic. All the sad people with AI girl/boyfriends threw a giant fit because OpenAI "murdered" the "soul" of their "partner". That's why 4o is still available as a legacy model.

Re: Web development is fun again

#363

Earlier quoted context omitted.

That sounds reasonable to me. AI is best at generating super basic and common code, it will have plenty of training on game templates and simple games. Obviously you cannot generalize that to all software development though.

> That sounds reasonable to me. AI is best at generating super basic and common code I'm currently using AI (Claude Code) to write a new Lojban parser in Haskell from scratch, which is hardly something "super basic and common". It works pretty well in practice, so I don't think that assertion is valid anymore. There are certainly differences between different tasks in terms of what works better with coding agents, bu…

I'm sure there is plenty of language parsers written in Haskell in the training data. Regardless, the question isn't if LLMs can generate code (they clearly can), it's if agentic workflows are superior to writing code by hand.

Re: Web development is fun again

#364

Earlier quoted context omitted.

Wait till the VC tap gets shut off. You: Hey ChatGPT, help me center a div. ChatGPT: Certainly, I'd be glad to help! But first you must drink a verification can to proceed. Or: ChatGPT: I'm sorry, you appear to be asking a development-related question, which your current plan does not support. Would you like me to enable "Dev Mode" for an additional $200/month? Drink a verification can to accept charges.

Just you wait until the powers that be take cars away from us! What absolute FOOLS you all are to shape your lives around something that could be taken away from us at any time! How are you going to get to work when gas stations magically disappear off the face of the planet? I ride a horse to work, and y'all are idiots for developing a dependency on cars. Next thing you're gonna tell me is we're going to go to war f…

I mean, they're taking away parts of cars at the moment. You gotta pay monthly to unlock features your car already has.

Re: Web development is fun again

#365

My problem is that code review has always been the least enjoyable part of the job. It’s pure drudgery, and is mentally taxing. Unless you’re vibe coding, you’re now doing a lot of code review. It’s almost all you’re doing outside of the high-level planning and guidance (which is enjoyable). I’ve settled on reviewing the security boundaries and areas that could affect data leaks / invalid access. And pretty much scan…

Worse, you’re doing code review of poorly written code with random failure modes no human would create, and an increasingly big ball of mud that is unmaintainable over time. It’s just the worst kind of reviewing imaginable. The AI makes an indecipherable mess, and you have to work out what the hell is going on.

> The AI makes an indecipherable mess

Humans are perfectly capable of this themselves and in fact often do it...

Re: Web development is fun again

#366

Earlier quoted context omitted.

I think it depends what you are doing. I’ve had Claude right the front end of a rust/react app and it was 10x if not x (because I just wouldn’t have attempted it). I’ve also had it write the documentation for a low level crate - work that needs to be done for the crate to be used effectively - but which I would have half-arsed because who like writing documentation? Recently I’ve been using it to write some async rus…

Mmm, I do a lot of frontend work but I find writing the frontend code myself is faster. That seems to be mostly what everyone says it's good for. I find it useful for other stuff like writing mini scripts, figuring out arguments for command line tools, reviewing code, generating dumb boilerplate code, etc. Just not for actually writing code.

I’m better at it in the spaces where I deliver value. For me that’s the backend, and I’m building complex backends with simple frontends. Sounds like your expertise is the front end, so you’re gonna be doing stuff that’s beyond me, and beyond what the AI was trained on. I found ways to make the AI solve backend pain points (documentation, tests, boiler plate like integrations). There’s probably spaces where the AI can make your work more productive, or, like my move into the front end, do work that you didn’t do before.

Re: Web development is fun again

#367

> Even with refinement and back-and-forth prompting, I’m easily 10x more productive Developers notoriously overestimate the productivity gains of AI, especially because it's akin to gambling every time you make a prompt, hoping for the AI's output to work. I'd be shocked if the developer wasn't actually less productive.

One of my favorite engineers calls AI a "wish fulfillment slot machine."

Re: Web development is fun again

#368

Earlier quoted context omitted.

People do realize that, which is why such frameworks have first appeared decades ago. It's just that you can't fully paper over the network gap and pretend that it doesn't exist; eventually, the abstraction leaks.

Have they? I assume you are talking about PHP, which is not that kind of framework, because you would still have to write JavaScript. It lacks type safety too.

I'm talking about stuff like GWT from 2006.

Re: Web development is fun again

#369
post #7

Something I like about our weird new LLM-assisted world is the number of people I know who are coding again, having mostly stopped as they moved into management roles or lost their personal side project time to becoming parents. AI assistance means you can get something useful done in half an hour, or even while you are doing other stuff. You don't need to carve out 2-4 hours to ramp up any more. If you have signific…

Now we ALL be project managers! Hooray!

Re: Web development is fun again

#370

Earlier quoted context omitted.

> That sounds reasonable to me. AI is best at generating super basic and common code I'm currently using AI (Claude Code) to write a new Lojban parser in Haskell from scratch, which is hardly something "super basic and common". It works pretty well in practice, so I don't think that assertion is valid anymore. There are certainly differences between different tasks in terms of what works better with coding agents, bu…

I'm sure there is plenty of language parsers written in Haskell in the training data. Regardless, the question isn't if LLMs can generate code (they clearly can), it's if agentic workflows are superior to writing code by hand.

There's no shortage of parsers in Haskell, but parsing a human language is very different from parsing a programming language. The grammar is much, much more complex, and this means that e.g. simple approaches that adequate error messages don't really work here because failures are non-actionable.
Post reply on HN