Senior Developer Skills in the AI Age • Hacker News Board

Re: Senior Developer Skills in the AI Age

#241

Post by ManuelKiessling » Fri, Apr 04, 2025, 2:13 PM UTC

hansmayer wrote: post #232

Skimming through the article, it lacks clear structure and I am not sure what is the author attempting to show? Some new skills he had to use? Formulating requirements? That he can write extremely long prompts? The Conclusion section looks just like something a GenAI tool would produce. Or a first-year student in an essay.

I've taken this feedback to heart and tried to improve the structure a bit.

The main message I want to bring across is two-fold:

1. Senior developers are in a great position to make productive use of AI coding tools

2. I have (so far) identified three measures that make AI coding sessions much more successful

I hope the reworked version makes these more central and clear. I'm not a native English speaker, thus it's probably not possible for me to end up with an optimal version.

Still, I hope the new approach works a bit better for you — would love to receive another round of feedback.

Re: Senior Developer Skills in the AI Age

#242

Post by fragmede » Fri, Apr 04, 2025, 2:15 PM UTC

caseyohara wrote: post #109

fragmede wrote: post #72

Earlier quoted context omitted.

The rest of the business is the issue. I can whitelabel a Spotify clone but licensing rights and all that business stuff is outside my wheelhouse. An app that serves mp3s and has a bunch of other buttons? yeah, done. "shifting goalposts?" no, we're having a conversation, I'm not being deposed under a subpoena. My claim is that in a week you could build a thing that people want to use, as long as you can sell it, that…

Sure, yeah, go ahead, do it. Seriously! Build a SaaS business in a week and displace an existing business. Please report back with your findings.

As much as I'd like to pretend otherwise, I'm just a programmer. Say I build, I dunno, an Eventbrite clone. Okay, cool I've got some code running on Vercel. What do I do next? I'm not about to quit my day job to try and pay my mortgage on hopes and dreams, and while I'm working my day job and having a life outside of that. There's just not enough hours left in the day to also work on this hypothetical EventBrite clone. And there are already so many competitors of them out there, what's one more? What's my "in" to the events industry that would have me succeed over any of their numerous existing competitors? Sure, Thants to LLMs I can vibe code some CRUD app, but my point is there's so much I don't know that I don't even know what I don't know about business in order to be successful. So realistically it's just a fun hobby, like how some people sew sweaters.

Re: Senior Developer Skills in the AI Age

#243

Post by necovek » Fri, Apr 04, 2025, 2:44 PM UTC

ManuelKiessling wrote: post #175

necovek wrote: post #130

Earlier quoted context omitted.

> expert software engineers are legitimately seeing their productivity increase 10x It's funny you would say this, because we are really commenting on an article where a self-proclaimed "expert" has done that and the "10x" output is terrible.

I have just checked my article — the word "expert" isn't in it, so not quite sure where you got this from. I'm working in the field professionally since June 1998, and among other things, I was the tech lead on MyHammer.de, Germany's largest craftsman platform, and have built several other mid-scale online platforms over the decades. How well I have done this, now that's for others to decide. Quite objectively though…

Apologies for implying you are claiming to be an expert software engineer: I took the "senior" in the title and "25 years of experience" in the post to mean similar things as "expert".

I don't doubt this is doing something useful for you. It might even be mostly correct.

But it is not a positive advertisement for what AI can do: just like the code is objectively crap, you can't easily trust the output without a comprehensive review. And without doubting your expertise, I don't think you reviewed it, or you would have caught the same smells I did.

What this article tells me is that when the task is sufficiently non-critical that you can ignore being perfectly correct, you can steer AI coding assistants into producing some garbage code that very well might work or appear to work (when you are making stats, those are tricky even with utmost manual care).

Which is amazing, in my opinion!

But not what the premise seems to be (how a senior will make it do something very nice with decent quality code).

Out of curiosity why did you not build this tool in a language you generally use?

Re: Senior Developer Skills in the AI Age

#244

Post by hombre_fatal » Fri, Apr 04, 2025, 2:45 PM UTC

conductr wrote: post #164

hombre_fatal wrote: post #123

Earlier quoted context omitted.

I know what you mean. It takes the satisfaction out of a certain class of problems knowing that you can just generate the solution. On the other hand, most tasks aren't fun nor satisfying and frankly they are a waste of time, like realizing you're about to spend the afternoon recredentializing in some aspect of Webpack/Gradle/BouncyCastle/Next.js/Combine/x/y/z just to solve one minor issue. And it's pure bliss when t…

I like the antidote and does remind me that I tried to create a game, which gamedev has always been a challenge for me. I’ve attempted a few times and didn’t get very far with this one either. I think I could do the coding even though scale is large, but I’m not artistic and asset generation/iteration is my block. I tried a handful of ai tools specifically for this and found they were all really far behind. I don’t p…

I had this in my comment but deleted it, maybe you were responding to it, but in case you didn't see it: I found multiplayer browser games to be a good example of a hard project that LLMs help a lot with so that you can focus on the rewarding part.

LLMs can one-shot pretty good server-authority + client-prediction + rollback netcode, something I've probably spent weeks of my life trying to build and mostly failing. And they can get a basic frontend 'proof' working. And once you verify that the networked MVP works, you can focus on the game.

But the cool thing about multiplayer games is that they can be really small in scope because all of the fun comes from mechanics + playing with other people. They can be spaceships shooting at each other in a single room or some multiplayer twist on a dumbed down classic game. And that's just so much more feasible than building a whole game that's expected to entertain you as a single player.

Re: Senior Developer Skills in the AI Age

#245

Post by necovek » Fri, Apr 04, 2025, 2:47 PM UTC

nsonha wrote: post #222

Macha wrote: post #215

Earlier quoted context omitted.

Like AI could write code perfectly as soon as I thought of it, and that would not improve my productivity 10x. Coding was never the slow part. Everything that goes around coding (like determining that the extra load here is not going to overload things, getting PMs to actually make their mind up what the feature is going to do, etc.), means that there's simply not that much time to be saved on coding activities.

Same argument can be said for not using any tooling really. "Tech is the easy part". No difference typing code on notepad and having zero process/engineering infrastructure I guess. Because stakeholder management is the main engineering skill apparently. Btw, AI doesn't just code, there are AIs for debugging, monitoring etc too.

If you were to really measure speed improvement of notepad vs a tricked out IDE, it's probably not much. The problem would be the annoyance caused to an engineer who has to manually type out everything.

No, coding speed is really not the bottleneck to software engineer productivity.

Re: Senior Developer Skills in the AI Age

#246

Post by Henchman21 » Fri, Apr 04, 2025, 2:54 PM UTC

lloeki wrote: post #150

Henchman21 wrote: post #96

Earlier quoted context omitted.

What makes you think this was created by an LLM? I suspect they might actually have a pool named faster -- I know I've named pools similarly in the past. This is why I now name my pools after characters from the Matrix, as is tradition.

The pool is named backups according to zpool status and the paragraph right after. But then again the old id doesn't match between the two commands.

Yep that’s the stuff I noticed that was off too

Re: Senior Developer Skills in the AI Age

#247

Post by skydhash » Fri, Apr 04, 2025, 2:59 PM UTC

atemerev wrote: post #198

skydhash wrote: post #54

Earlier quoted context omitted.

Is it really 5x? I'm more surprised about 25+ years of experience, and being hard pressed to learn enough python to code the project. It's not like he's learning programming again, or being recently exposed to OOP. Especially when you can find working code samples about the subproblems in the project.

It is 5x if you are already a senior SE knowing your programming language really well, constantly suggesting good architecture yourself ("seed files" is a brilliant idea), and not accepting any slop / asking to rewrite things if something is not up to your standards (of course, every piece of code should be reviewed). Otherwise, it can be 0.2x in some cases. And you should not use LLMs for anything security-related u…

> It is 5x if you are already a senior SE knowing your programming language really well, constantly suggesting good architecture yourself ("seed files" is a brilliant idea), and not accepting any slop / asking to rewrite things if something is not up to your standards (of course, every piece of code should be reviewed).

If you know the programming language really well, that usually means you know what libraries are useful, memorized common patterns, and have some project samples laying out. The actual speed improvement would be on typing the code, but it's usually the activity that requires the least time on any successful project. And unless you're a slow typist, I can't see 5x there.

If you're lacking in fundamental, then it's just a skill issue, and I'd be suspicious of the result.

Re: Senior Developer Skills in the AI Age

#248

Post by FeepingCreature » Fri, Apr 04, 2025, 3:00 PM UTC

nottorp wrote: post #226

FeepingCreature wrote: post #221

Earlier quoted context omitted.

Well, that wasn't in your comment. :P If you hadn't told me that I would also not have bothered optimizing syscalls. Did you tell the AI the profiler results and ask for ways to make it faster?

> Well, that wasn't in your comment. :P Acting like a LLM now :P > Did you tell the AI the profiler results and ask for ways to make it faster? Looking for ways to turn a 10 minute job into a couple days?

AI actually doesn't really work for the "a couple days" scale yet. As a heavy AI user, this sort of iterative correction would usually be priced in in a 10-minute AI session. That said-

> Acting like a LLM now :P

Hey, if we're going to be like that, it sure sounds like you gave the employee an incomplete spec so you could then blame it for failing. So... at least I'm not acting like a PM :P

Re: Senior Developer Skills in the AI Age

#249

Post by nsonha » Fri, Apr 04, 2025, 3:00 PM UTC

necovek wrote: post #245

nsonha wrote: post #222

Earlier quoted context omitted.

Same argument can be said for not using any tooling really. "Tech is the easy part". No difference typing code on notepad and having zero process/engineering infrastructure I guess. Because stakeholder management is the main engineering skill apparently. Btw, AI doesn't just code, there are AIs for debugging, monitoring etc too.

If you were to really measure speed improvement of notepad vs a tricked out IDE, it's probably not much. The problem would be the annoyance caused to an engineer who has to manually type out everything. No, coding speed is really not the bottleneck to software engineer productivity.

> coding speed > the annoyance caused to an engineer

No one said productivity is this one thing and not that one thing, only you say that because it's convenient for your argument. Productivity is a combination of many things, and again it's not just typing out code that's the only area AI can help.

Re: Senior Developer Skills in the AI Age

#250

Post by nottorp » Fri, Apr 04, 2025, 3:03 PM UTC

noisy_boy wrote: post #240

nottorp wrote: post #181

Earlier quoted context omitted.

I'll write that down for reference in case I do ever join an organization like that in the future, thanks. 600% improvement is worth what, 3 days of billable work if it lasts 5 minutes?

Series of such "improvements" could be fame and fortune in your team/group/vertical. In such places, the guy who toots the loudest wins the most.

So THAT's why large organizations want "AI".

In such a place I should be a very loud advocate of LLMs, use them to generate 100% of my output for new tasks...

... and then "improve performance" by simply fixing all the obvious inefficiencies and brag about the 400% speedups.

Hmm. Next step: instruct the "AI" to use bubblesort.