Live data from Hacker News

What AI coding costs you

tomwojcik.com

191–200 of 206 posts

Re: What AI coding costs you

#191
post #177

Earlier quoted context omitted.

When you let compiler generate code for you, you're not a real programmer... That's what opcode coders was ranting in early 60s about FORTRAN programmers. Product managers can't produce viable programs ready to be deployed in production (yet). But maybe the will able to do it in the future. We don't know how far or close this future is. But I don't think it's not a bad idea in general.

The assumption behind the discussion is that they will be able to produce viable programs. And if you’re letting the LLM own the code, that’s what your job function will be: product manager.

Fair. But I'd change a title a bit to Product Engineer or System Designer. Still a lot of engineering judgement is/will be required to deliver production-ready systems.

Re: What AI coding costs you

#192
post #3

Hi HN, I've been using Claude Code heavily for the last year. Recently I've noticed a shift in sentiment among peers, here on HN, and over on /r/ExperiencedDevs. I wrote down some thoughts on the hidden costs of using AI too much that are not obvious, yet there's no concrete data yet. I tried to pull together data from a few different places to articulate something I think a lot of us are experiencing right now. I'd…

Fun read. Audience can see Xeno's Arrow emerging on your "we're on the way to AGI!" timeline, a nice visual representation of "the trajectory is real, but the timeline keeps slipping." But I'm gonna say I've always seen "[retail software] is just a tool" as an odd statement. I've heard it a lot over the last 20 years. "Just" a tool. Why always phrased like that? How can we be overthinking the role of a tool while you…

didn't even take 24 hours: https://news.ycombinator.com/item?id=47190947

Re: What AI coding costs you

#194

The hell with with whatever speed boost I might get. I still write all my code by hand every day, and own what it does. I know it. And I don't have to worry about atrophy. Could've outsourced a long time ago to humans, if I wanted to deal with reading code most of the time instead of writing it.

Am I alone in thinking atrophy might not happen? I use a keyboard all day but it doesn't mean I can't write by hand anymore. Predictive text didn't make me forget how to spell. If i buy coffee it doesn't mean I forget how to make it

Counterpoint: my handwriting is way harder to read and my hand tired faster than when I was in high school. And I am worse at spelling and my vocabulary has stopped expanding much since I started typing more and reading less

Re: What AI coding costs you

#195
I was recently analyzing a TypeScript module in our new project to learn how it works, and was thinking, "I wouldn't have done it like this” and “the styling is not for me". Then the realization slapped me in my face: this code came from me!

This article also slapped me, and has crystallized my jumbled thoughts on the topic. I'm deep into my career as a productive software engineer, yet I'm concerned there is a visible vanishing point of my value. My retirement is also visible, but I'm more concerned about our trade and those of you who have many years ahead.

While adaptation is hard when moving a lightspeed, workflows must adapt, more time on imprinting the generated code into our heads with iterating on trialing, testing, editing, before PRs is prudent.

A larger problem is architectural drift and leak. Those feel like they could become extremely problematic. We’ll need to put more effort into steering agents so their output aligns with architectural goals. The steering will also need to be iteratively refined.

Great article! I’m concerned, but also rallying for us.

Re: What AI coding costs you

#196
post #49

Earlier quoted context omitted.

I’d encourage you to read this post: https://factory.strongdm.ai It hit the front page here a few weeks ago, but I don’t think most people took it seriously and got hung up on the $1000/day in tokens part. I am convinced that approach is the future of nearly all software development. It’s basically about how if you’re willing to spend enough tokens, these current models can already complete any software task. With th…

My question is always: what are you building? You need to tell the AI what to build. What if it does it in a way that isn't what you want, or makes the buttom blue instead of red, or any number of other decisions? AI can write the code, but not tell you what code you want it to write. In other words, how long are your specs? Either the LLM decides "whatever" or you have massive amounts of documentation to coordinate.…

Yes, the LLM writes the specs. In fact that LLM writes everything, and then the humans only flag anything they want changed, other than that it’s completely automated.

Imagine you were working with a very talented software shop. You might tell them your preferences sometimes and some things you want changed, but otherwise they mostly just build the right things the right way. And unlike a real software shop, the LLM system can implement changes incredibly fast.

Re: What AI coding costs you

#197

I started my coding apprenticeship back in early 80s with a senior programmer who taught me to code in LSI-11 processor codes. I memorized the whole table of octal processor opcodes and learned how to compose them with data to write programs on PDP-11. I was able to understand what each exact 16-bit word in my program is doing. It was a great skill. But then the same guy taught me FORTRAN 83, and I suddenly understoo…

Ask me what 9 times F is

It's fleventy five

Re: What AI coding costs you

#198

Earlier quoted context omitted.

I doubt it's possible to draw a concrete line between in domain, and out of domain. Would you mind trying with a specific example? Because so much of engineering is understanding the interactions between systems. While I cant enumerate the exact asm codes, I do need to understand how the compiler is going to rewrite my function if I want to understand if a cast is safe, or if this function call order needs to be rewr…

One specific example that comes to mind is developer tooling in the form of bash scripts. Sure, I can write it myself, but I do this so infrequently that there is a cost for the context switch and ramp up. This, and similar dev ex things that have been languishing in the “one day” pile because there is always the next feature to build. I can now spend 10 minutes here and there to ship incremental QoL improvements alo…

You don't have a scripting language in your toolbox that you're comfortable with?

I would probably say a shell is "the correct tool for the job" but other than the appeal to authority, or appeal to tradition. There's not a great argument for a shell script over a language you're already comfortable with.

There are hundreds of examples that are easier or faster in python than shell.

Engineers are bad at making tooling, we're even worse making ephemeral tooling we're willing to throw away. Contrasted with other makers, you have machinests who gladly make a one off tool to make a single process easier.

The more 'correct way' than a shell script, is something simple and composable. A large unwieldy shell script that you can't make simple changes in, is terrible design, and it's a mistake to allow that inertia to gain speed.

It's not exactly a complete refutation but something I've been thinking about recently.

Re: What AI coding costs you

#199

Earlier quoted context omitted.

I doubt it's possible to draw a concrete line between in domain, and out of domain. Would you mind trying with a specific example? Because so much of engineering is understanding the interactions between systems. While I cant enumerate the exact asm codes, I do need to understand how the compiler is going to rewrite my function if I want to understand if a cast is safe, or if this function call order needs to be rewr…

I'm not disagreeing with your point. A good understanding of the domain and relevant systems is quite crucial. My point is that you don't always need to inspect the code at such low-level detail, provided there are tests or other ways to prove that the code behaves in the way that you describe.

> My point is that you don't always need to inspect the code at such low-level detail, provided there are tests or other ways to prove that the code behaves in the way that you describe.

This is true *only* in isolation. The pain of going through said depth of detail, is what builds the intuition for the whole system. Once and twice may not be noticeable, but a new habit, and that new habit's corresponding extreme downtime because no one understands the quirks anymore... Despite a few engineers who stake their life on the testing system, tests can't catch all issues. And it's extremely difficult to stop an oil tanker.

Re: What AI coding costs you

#200
We sysadmins have been seeing this for decades with docker, k8s and cloud adoption. None of the engineers I work with are able to debug a simple networking issue or compile a trivial piece of c code.

Otoh: didn't Socrates say the same about writing? It rots the brain?

Post reply on HN