Live data from Hacker News

Cleaning up after AI rockstar developers

codingwithjesse.com

321–330 of 401 posts

Re: Cleaning up after AI rockstar developers

#321

Earlier quoted context omitted.

I would say there are two explanations for group 2. The first is that you aren't as smart as you think you are, because if you actually understood the people around you in any real way, you would instantly find them less frustrating. But instead you are using flawed heuristics, built out of your own insecurities, to interact with the world. Possibility two is that you are smart, but you have developed a malformed cop…

Or perhaps there is a 3rd explanation, spending all of your time with people much less intelligent is frustrating and unsatisfying, and being such an outlier, it's how most of your time is spent. Someone with a 142 IQ is to the 100 average in the same way that 100 average is to someone with a 70 IQ. We don't expect people with average IQ to spend all of their days with 70 IQ people (in a peer situation). (BLAH BLAH B…

If you're so secure in your intelligence relative to your peers, why are you responding to me?

Personally, if I had to choose between a world of people with "low IQ" who are self-aware and one of people with "high IQ" or are extremely un-selfaware, I would choose the former every time.

Re: Cleaning up after AI rockstar developers

#322

Earlier quoted context omitted.

Not sure I understand. Is your contention that the distinction between senior and non-senior engineers is fake and everyone's doing basically the same thing? Or are you just objecting to the (arbitrary) names Microsoft uses for them?

False dichotomy. Of course not everyone has the same experience/skills, but any corporate system of putting individuals to tiers has little to do with experience/skills.

That's just not accurate. I've seen these systems run at multiple companies, and in every case they had a lot to do with skills and experience. It's true that they're not a perfect classification, and I think it's defensible that some people prefer a system where this kind of leveling doesn't happen.

But the tradeoff is that career advancement becomes less legible in a way that other people often find frustrating. Why does Alice get paid 3 times as much as me to work on cooler and more important stuff? "Alice is L7 and I'm L4" is often an easier answer to accept than "Alice is a better engineer than I am" or "People with Alice's experience have more options than I do".

Re: Cleaning up after AI rockstar developers

#323
post #264

Earlier quoted context omitted.

Slightly agree. :) I don't think handmade shoes are the right comparison, unless you're talking about software that's meant to be used by just one person. The more apt comparison might be to the engineers building and maintaining the manufacturing equipment in the shoe factory. It's a degree removed from the consumer, but there's definitely still craftsmanship involved there.

Going to be awfully hard to market rote machine maintenance as craftsmanship, but there are some suckers out there

If you've ever watched an episode of "How It's Made" and seen how incredibly customized these machines are, it won't be surprising that the people who build them are proud of their work.

Re: Cleaning up after AI rockstar developers

#324
post #272

Earlier quoted context omitted.

Oh really? Link them.

Not sure what I'm going to link to in my professional life, it's all private repos. We have a large microservice architecture in AWS. We've made major changes and the LLMs have helped every step of the way. Migrated our whole auth system from being regional, resulting in customers being limited to specific regions or managing their multiple accounts across regions, to a global authentication with data residency built…

I enjoyed hearing about the stuff you've done.

Would you mind talking about your experience making the 2 godot games? Which agent and model did you use? I've been wanting to dabble here and interested to hear stories.

Re: Cleaning up after AI rockstar developers

#325
post #319

Earlier quoted context omitted.

> considered a 10x developer The 10x developer never existed. You're telling me these people are doing a year's worth of work in 1.2 months? Seriously?! 10x?! In a year you can probably learn to program from scratch and participle if you're working 8hrs per day 5 days a week We need to stop exaggerating so much. A 2x dev would be insane! A 1.5x dev does a year's work in 8. A 1.1x dev does it in 11. Saving a whole mon…

Of course they do. Have you literally never run into a problem that the average developer can not solve, but a expert can solve? That is infinity times more productive. Even assuming that maybe the average developer could come to learn how to solve the problem you can easily see the gap between taking months to learn how to solve a problem versus already knowing how to solve it on short notice being over 10x. Large p…

  > Have you literally never run into a problem that the average developer can not solve, but a expert can solve?
In what time frame?

  > Even assuming that maybe the average developer could come to learn ... already knowing how to solve it on short notice being over 10x.
10x? I'm not convinced. 10x is a pretty big increase, as illustrated above.

Clearly I understand the gap, I explicitly mentioned it. I mentioned a month's work is quite valuable. I'm not the one diminishing that value, you are.

I can totally buy instances of 10x improvement, but that's not what we're talking about and not how anyone is using the term. Everyone is talking about sustained output. No one gives a shit if you're 100x for five minutes but 0.5x the rest of the time.

Your critique isn't wrong, per say, but it is a non sequitur to the conversation.

I doubt even a staff level engineer is even a 10x above the junior. Will the staff level engineer write better code and faster? Hell yeah they will! But will it take a junior 10 years to write the same software a staff level does in a year? Maybe. But if it does I'm not convinced they're even trying, so not a fair comparison. 10 years is a lot of time. A lot of time to learn, refactor, or even build the damn thing from scratch a few dozen times.

Seriously, 10x improvements are actually wild.

But why dismiss a 10% gain as if it's nothing? Why is the smaller number bad?

Is the need for the number to go up so strong that we don't care how divorced from reality it is?

Re: Cleaning up after AI rockstar developers

#326
post #96

Earlier quoted context omitted.

That's one dimension of it, but in the context of this thread we are talking about how maintainable a codebase is for other humans. If your codebase is messy you depend on a few key employees and it might be hard to onboard new ones, so there has always been financial incentives to reduce tech debt.

> so there has always been financial incentives to reduce tech debt. Yes. In practice, this does not weigh against organisational resistance. AI really makes it worse by adding an explicit numerical cost to doing anything.

Um, no, actually AI makes it better because the cost is lower now. I'm not sure what point you're trying to make here, obviously organizations already fight against tech debt all the time through a variety of means?

Re: Cleaning up after AI rockstar developers

#327

> Craftsmanship will always be in our hands, it's one thing we can never outsource to a machine. I'm right there with you, but this last sentence concerned me a bit. In my most other "industries", craftsmanship is not _dead_, but it's been pushed to the wayside for (significantly) cheaper and more available alternatives. You can still get hand-made leather shoes, but very few want to pay $1000+ for them. You can stil…

Craftsmanship is not dead in other industries in the same way it is being talked about for software. Sure, that cheap desk that arrived in a flat box and got assembled by me and a screwdriver was mass produced in a factory. But it's design had way more expert craftsmanship put into it than would ever be feasible for a bespoke product. High upfront design cost, then mass produced at a low marginal cost. That had been…

Do you honestly think an ikea desk has "more expert craftsmanship" than a hand crafted by a woodworker desk?

Re: Cleaning up after AI rockstar developers

#328

Earlier quoted context omitted.

> Imagine walking through life and everything is clear, obvious, easy to process and having to watch humanity make stupid choices over and over and over again when the answers have been long known... I don’t claim to be book smart or have a high IQ or whatever but I feel this way about small things that I feel are common sense. It’s maddening to me to watch people fumble around. Or do X when obviously it will result…

The older I get, the more I realize that individual variation in humans is truly enormous. Any trait you could pick is much more widely distributed than any individual human can see from their perspective. Just the other day I was watching a video on youtube, of someone absolutely struggling at a task that had a built-in checklist, verification steps, pictures, and basically (in my opinion) perfect guidance. This is…

It certainly doesnt help that 50% of the population is below 100 IQ, and something like 15% of the population are below 85.

Re: Cleaning up after AI rockstar developers

#329

Earlier quoted context omitted.

Craftsmanship is not dead in other industries in the same way it is being talked about for software. Sure, that cheap desk that arrived in a flat box and got assembled by me and a screwdriver was mass produced in a factory. But it's design had way more expert craftsmanship put into it than would ever be feasible for a bespoke product. High upfront design cost, then mass produced at a low marginal cost. That had been…

Do you honestly think an ikea desk has "more expert craftsmanship" than a hand crafted by a woodworker desk?

In some ways, sure.

The LACK (https://www.ikea.com/us/en/p/lack-side-table-white-30449908/) is probably one of the most optimized pieces of furniture you can buy. There's no hand crafted desk that can be this cheap. A wood worker won't even get out of bed for $17.

Now is it an amazingly beautiful, rock solid, heirloom quality piece of furniture? No, but it's not trying to be that.

Re: Cleaning up after AI rockstar developers

#330
post #204
post #26

Earlier quoted context omitted.

In some ways they are giving you a spec and UI mocks to implement.

This is a very interesting thought. We complain about having to fix some MBAs vibecpded slop, but it actually might be faster, easier, and alot less painful than getting them to try to explain their vision to us and implement what they have in mind. Like they actually iterate on the UX alot when they are vibecoding things up, answer alot of questions that can onky be answered when you see an initial version of experi…

Have my angry upvote. :-)

One of my faults is "When somebody tries to explain something I hear 'A' and everyone else in the room hears 'B'". And vice-versa. But if someone can iterate a very VERY rough cut of what they want and hand it off to a design / development team ... well ... damn. That might make everyone's life a lot easier.

Post reply on HN