Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cleaning up after AI rockstar developers

codingwithjesse.com

Post reply on HN
Print view View original

371–380 of 401 posts

Re: Cleaning up after AI rockstar developers

#371

Post by conductr »

mapleleaf1921 wrote: post #361
skydhash wrote: post #286

Earlier quoted context omitted.

> You will never get the chance of "customers requesting changes" if you never ship. Why does good code imply never shipping? Managers and Developers have different thresholds for “good enough to release”. The former are not the one on call for bugs or the one that get blamed for outage, but they are the ones that get praised when projects are completed quickly. Anything that’s past demo level is good for them.

I'm not saying they're mutually exclusive. I'm just saying that we can't expect them to come as a packaged deal. For example: Company A - janky code, ships quick Company B - great code, ships quick Company C - great code, ships slow Company D - janky code. Ships slow The average survival rate will be in the following order: B > A > C > D My point is company A will capture the market and iterate quicker than company C…

I like this. It has a lot to do with the company building journey too. Some companies that I feel are probably the B types had a super clear product vision that quickly resonated with users. So the original architecture that fit their vision was probably easy to scale for the features that came as a natural progression of the product. Meanwhile, a company that builds a product and tries to pivot or found the original vision only partially what customers wanted, well these situations put you in the position where it’s probably easier to just force what you have to work for the basis of your iteration. Starting from zero is usually not as easy as it sounds. It’s more like you make a Hail Mary football pass, usually ugly and risky but can get quick results.

Re: Cleaning up after AI rockstar developers

#372

Post by TonyStr »

saalweachter wrote: post #180
JoelMcCracken wrote: post #41

Earlier quoted context omitted.

This is one of the things I keep thinking about. At the very least, these tools make prototyping and idea vetting remarkably cheaper. Then we go back to the old “the prototype works; I’m the boss and I’m telling you to deploy it to production”

There's like three groups of developers you need: The prototypers, who move fast and break things, who throw together shiny first versions that look great and work some of the time; The architects, who take the prototypes and take the time to build it correctly; And the gardeners, who maintain the built system for the next 10-30 years, fixing bugs, making incremental improvements to speed or resource usage, and updat…

This is such a great mental model.

Re: Cleaning up after AI rockstar developers

#373

Post by TonyStr »

samrus wrote: post #204
DenisM wrote: 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…

You are right, but at the same time, if no UX designer is involved in the loop, what happens when they've prompted a prototype that looks good - and therefore eludes them to think it's designed good as well? How do we convince them that we need to involve a UX designer to fix the application flow?

Re: Cleaning up after AI rockstar developers

#374

Post by TonyStr »

Havoc wrote: post #62
maerF0x0 wrote: post #35

I've met a handful of people across my life that i'd call truly brilliant. Like, holy heck how in the world is this person this smart? Two things I've noted about really smart people are (usually mutually exclusively) 1) Sometimes they do not realize how smart they are, because it's simple to them, or because they know the subject they assume everyone else, say with a computer science degree, knows and recalls and un…

And then you’ve got a third problem - that well north of 50% believe themselves to be in that last sentence of yours

Some people are very good at working with complex abstract ideas, but are terrible at signaling that intelligence to others. And some are fantastic at signaling intelligence and steering conversation toward domains of knowledge that they've studied (many political commentators come to mind), but don't seem to have processed those ideas very deeply.

Re: Cleaning up after AI rockstar developers

#375

Post by TonyStr »

jaggederest wrote: post #185
conductr wrote: post #100

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…

>video on youtube, of someone absolutely struggling at a task that had a built-in checklist

This sounds like Bog who records himself setting up Linux distros or configuring software

Re: Cleaning up after AI rockstar developers

#376

Post by TonyStr »

conductr wrote: post #169
pjm331 wrote: post #106

Earlier quoted context omitted.

i feel fairly certain everyone has some set of activities or tasks they feel this way about my wife and i have two non-overlapping sets haha you can imagine how that plays out

Same wrt my wife and I. She’s quite clumsy and to my assertion doesn’t always think things through. So it’s a bad combination for “accidents” to always happen which I think are very preventable and quite obvious to occur using her approach. A lot of it is just mental errors that I don’t make, but it’s not that I’m perfect I probably just make different mistakes (I think less volume too ;) Yesterday she literally fail…

Well, how hard should you beat yourself up over a mistake like that? If I forgot my groceries in the car, I'd just laugh about it being a silly one-time mistake. But if it happened twice I'd take it more seriously, and maybe make a note or something to remind me. I'm sure everyone has made some silly mistake like forgetting a jacket at a party or leaving a phone at home sometime. I think we should be a little extra forgiving toward others, because we'd so easily forgive our own mistakes

Re: Cleaning up after AI rockstar developers

#377

Post by Peacefulz »

ramon156 wrote: post #7

I kind of envy people who need to clean up after others. At least you're puzzling. My current job is genuinely just boring. It's tasks that are so simple, a junior could do it. But no, instead they needed a medior. I'm not saying I'm better than this, nor that no medior will pick it up. I just cannot push myself to care about the code this company makes. It's old, dusty and it serves no one of importance. These custo…

I'm not the best friend. I often don't do my part to hold up my end of social contracts. That said, I'm a fairly decent low-commitment penpal. The internet is the place where I vent as well, and it often feels like a void. It doesn't scratch that therapuetic itch and therapy proper doesn't appeal to me.

What I'm getting at is if you'd like to find a stable place to vent about some shit without worrying about some assholes scraping it, I'd gladly share an email and a PGP key with you. If there's one thing I'm quite good at, it is minding my own business. That extends to the handling of other's business.

Have a good one.

Re: Cleaning up after AI rockstar developers

#378

Post by imtringued »

elictronic wrote: post #210
nrmitchi wrote: post #157

> 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…

"software is _unfortunately_ becoming more and more "disposable"[0], in the same way other products are" Software has been the most disposable object in our lives since you could push a new build over the web. Builds change overnight, new versions every month with small updates. You have it backwards. Software has very little to no regulation compared to physical products and requires little to no effort to change. I…

You're confusing binaries with source code.

The vast majority of software development is based around an incremental process over time.

Disposable source code would mean you prompt the AI for every new release and throw the old code away.

Re: Cleaning up after AI rockstar developers

#379

Post by imtringued »

anonymars wrote: post #291
akramachamarei wrote: post #161

Earlier quoted context omitted.

I'm sometimes puzzled by the way people use "circular" to describe an economic system pejoratively. (Not to suggest you are.) Seems like any worthwhile economic system is ultimately cyclical. Pulling resources into the loop is just a bonus....

Related "income tax when I earn the money, sales tax when I spend the money, taxes on my investment returns, it never ends!" Yes indeed, because macroeconomics is ultimately a giant circle!

The problem with real economics is that it isn't, but since economists told themselves that it is, they have no interest in making it so.

Re: Cleaning up after AI rockstar developers

#380

Post by evilturnip »

jmaw wrote: post #130
danjc wrote: post #14

As much as it's true that a novice will generally use AI to build a sloppy mess, I've also had success unsloppifying through some careful prompting.

Any tips on how you unsloppify things? Are you using things like claude.md/copilot.md (or similar) to guide better, do you have specific types of prompts that you run, or do you adjust your code review practices in some way to more efficiently review lots of slop code? One of my particular complaints is how code-gen LLMs tend to re-create the same code over and over again. Case in point, a use-case where a team name…

I also ask it to explain the system back to me. Obviously it should understand the system just by reading the code. But somehow, explaining the system back to me seems to make it more effective. Then I'll ask it questions about how I should make changes to the system. Sometimes I'll agree, sometimes I'll disagree and offer an alternative and ask it to assess the alternative. Having this entire conversion in its context seems to make it way more effective at refactoring/unsloppifying code.
Post reply on HN