Comment by aidos

Reminds me of Niven/Pournelle's "The Mote in God’s Eye" where the aliens have a very pragmatic/Jury-rigged approach to technology and everything is more or less improvised.

I have noticed this with co-workers also, when you have the ability to read/write/understand things very quickly, you tend to spend much less time on making things tidy, clear and maintainable.

You use an AI to make the spaghetti.

You use another AI to document the spaghetti.

You use the third AI to make a spicy meatball from the spec.

Interestingly, I have personally felt this way about projects in which I was involved in the past(written both by me and by others)…

sometimes starting from scratch just faster and/or easier.

>just throw the code away and rebuild it

What about all the undocumented "adjustments" ("bug fixes" in a professional context) that were made to make it actually useful?

Have better agents rewrite it in the future.

> This also assumes that the same application build by humans wouldn't become a "spaghetti mess".

nah, it reflects on how applications built by humans usually do become spaghetti messes with all the resulting brittleness and unintended negative side effects of changes that result

but it probably doesn't matter for a little toy piano app

And the models of the future will surely be better than they are today. This stuff is still a very long way from maturity.

Sometimes it seems like they're moving very slowly. That makes sense: It's easy to get used to how they work today and it is also easy to forget how much worse they were last year.

When we look back and realize that just 4 years ago these tools didn't really exist at all, it becomes clear that the rate of progress is rather amazing.

In 4 years, we've gone from "hah, good luck with that crap!" to "little kids writing music-learning games on their own in a few minutes"

That's pretty friggin' awesome, and it's not finished yet. :)

I think that sort of careless waste is a very human behavioral pattern, but then we are the ones training these bots.

ed sp

errors compound

Eh, not really. It's the same issue with porting. You always rely on features you didn't properly articulate.

Good luck to future models figuring out which weird section of code are bugs and which are features.

AI writes faster, so the rate it incurs tech debt is proportionally higher. However it's ability to have large context kept on memory compared to humans is also a key component fighting against it. These are occasionally forgotten when code quality of AI for large code bases are discussed. So Yes I think humans also build spaghetti, but as they write slower they get to the same place a lot later. However humans can't correct it, or can't correct it fast enough. AI can.

I agree with this. Clean code is important today because it helps humans to understand it. Cleanliness is not otherwise intrinsically valuable.

Today I don't always need to understand the code. When I do, I can ask the LLM to explain the code or to specify the algorithm in pseudocode or even re-write the code until I can understand it.

I think, as an industry, we haven't yet fully grasped the impact of agentic coding. We don't yet know what software engineering is going to be like in 5 to 10 years.

That's what happens with scale...

The purpose of a car itself didn't change. But the massive inflated demand, as our city planners decided every adult must be put in a rolling metal cage to participate in society, changed the environment it was originally designed for.

Now it's a matter of geopolitical stability, or even basic human habitability of these spaces, that a car converts as much of that chemical energy into movement, and releases as little toxic byproducts in the process. Whereas before, that cost, at scale, was small enough to neglect.

Just like a modern CPU evolved into an incomprehensible mess, even though the basic consumer needs hadn't changed much, because the politics of computing forced them to run expanding institutional cruft at reasonable speeds, on battery-powered always-on addiction machines.

> then ... in some places (maybe cars that people care about working on) it became cleaner again

Those cleaner looking engine bays are usually worse to work on. Not better.

When you open up the hood and immediately see lines everywhere, that also means they’re within reach. This is great.

The engine bays that look nice and clean for the showroom still have those same lines. They’re just buried in there. If you need to work on them you’re going to be reaching underneath things, climbing under the car, or even removing other parts to access something simple.

Also, it’s not all about emissions. A lot of those lines are for modern comforts like cruise control and improvements like features that make cold starts easier or make the engine behave better at extreme temperatures. Some of those have been superseded by electronically controlled versions which is why some of those lines are disappearing on modern cars, but the overall complexity has increased further.

It was simple because it was inefficient and archaic. Reducing pollution is not "nonsense"

I think the vacuum hoses are actually for the brake booster and why you don't have any regular brakes if your engine dies. But yes, smaller engine + turbo or twin turbo is definitely more complex than a simple big block. There's also an absolute shit ton more sensors on everything now.

And Claude is even younger.

Comparing LLM output to compiler output is such a stale meme by now that it's surprising to see people still saying it. Obviously a deterministic translation of a higher level programming language to machine code is different than the slop cannon.

Suppose she decides from the experience that she likes making games, and wants to expand on it. She wants to support more songs, different types of song sources, colorful animated backgrounds, flashy graphics, change how it scores, a hundred other things. But by the time she gets halfway through it claude just starts getting things wrong and making them worse, and it turns into a nightmare where she doesn't even know how to go back and going back doesn't fix the problem. Or going back undoes some things she did want along with all the stuff it broke, and now she has to do it all over again. She makes a change on one screen and it changes the behavior on a dozen others. Claude starts telling her that things are impossible, or that it did this because there was a comment that said she wanted it, or coming up with other weird complicated reasons, citing random lines of code, why this or that can't work. And then she decides that yeah, making things is an awful experience and she never wants to do it again.

You mean the 8 year old shouldn't be thinking about how she will maintain this code when she's 15? This generation is lost.

I think the fear is that a lot of this stuff will end up being load bearing. A lot more folks now know enough to be dangerous but not enough to know what to throw away.

I wasn’t trying to make a “got em” comment.

The fact that this is possible and works at all is mind blowing - even more mind blowing is that my 8 yo is growing up in a world where they can talk to a machine to produce a custom application in seconds and they don’t realise how mind blowing it is!

In terms of the code, it would take even less time than that to tidy it up. For this application you wouldn’t bother. That’s almost a form of “premature optimisation” unless you’re actually planning on doing more work on it.

My hunch is that what the world is about to see a lot of is much bigger bits of work, or changes to other bigger existing systems done by people without the skills to know how to contain the complexity. That’s going to come with a burden.

The only reason it's a spaghetti mess is because it's not being prompted correctly by an expert.

It's not about prettiness. It's about being harder to extend thus making future adaptations harder.