Live data from Hacker News

Cleaning up after AI rockstar developers

codingwithjesse.com

61–70 of 401 posts

Re: Cleaning up after AI rockstar developers

#61

This is why I always work at a new company at least 6-12 months before making any major changes. I use that time to get into the flow of how things are being done (even if I think they are not efficient). I may make some suggestions but that's it. Of course, I'll probably never get hired again anywhere so it doesn't matter anymore.

In 6-12 months you could ship a new product or a large feature. This strategy might actually put you on a performance improvement plan instead.

Re: Cleaning up after AI rockstar developers

#62

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

Re: Cleaning up after AI rockstar developers

#63

Like many other critiques along this line, I think the answer is: Yes, for now. For example, in my own code base, I have an agent dedicated to maintaining a sane data model. This agent reviews the plan in advance and again during code review. And then I review the code myself. This seems to be sufficient for my work, at least. YMMV. It was a good post though. I enjoyed the take and the writing.

If you're reviewing the code yourself, then I don't think this article is about you.

Re: Cleaning up after AI rockstar developers

#64
post #48

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”

Prototyping is widely underappreciated. People think it's waste to throw away stuff but it's more costly to build upon shoddy foundations

But... "time to market!", "we won't have cash by the time this gets implemented properly" etc etc are the usual suspects here.

Re: Cleaning up after AI rockstar developers

#65
I was such a fool to lean hard into two production engineers to build the infrastructure around the two very profitable projects I built. I could have made so much more money spaghetti coding it all like a 10x boss and then jumped to Anthropic for one of those sweet 9-figure comp deals. Stupid, stupid, stupid me.

At least that's my takeaway here.

Re: Cleaning up after AI rockstar developers

#67
post #48

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”

Prototyping is widely underappreciated. People think it's waste to throw away stuff but it's more costly to build upon shoddy foundations

100% - one of the biggest advantages of software is its mutability, so why not use it to prototype properly?

Re: Cleaning up after AI rockstar developers

#68

> Half the code was written in a language you didn't understand. The other half was written using libraries you never heard of. > As you waded through the slop, you browsed job postings and fantasized about leaving Just because you didn't understand something or haven't heard about a library, doesn't mean its slop. How do you make sure your definition of "clean code" is not a slop to others?

I'll avoid trying to guess what the author meant, but I found it rather relatable. Some of these "rockstars" pick weird languages, niche database, esoteric frameworks and whatnot, not because they're needed, but because that's the rockstar thing to do at that moment. And then they leave and you're stuck managing a Cassandra database and a Rust application when everything else around you is MariaDB and Java, and you have to maintain an application in an abandoned JavaScript framework, even though dynamic frontend wasn't a requirement.

Re: Cleaning up after AI rockstar developers

#69

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…

It's lonely being an outlier, especially in a trait that's so fundamental to how you see the world. Despite best effort, it's hard to relate to most people, and they especially find it hard to relate to you. The delta of lived experience is quite wide, often insurmountable.

Re: Cleaning up after AI rockstar developers

#70
this resonates with me, but fortunately one difference between LLMs and rockstar developers, is that LLMs will at least _try_ to explain what they are doing, and why something has to be certain why. I've gotten quite a lot of mileage from being a five-year-old with Claude and just asking "why" until I'm satisfied
Post reply on HN