Hacker News Reader

Comment by selridge | Hacker News Reader

The right move is this, turned to 11.

Velocity or one-shot capability isn't the move. It's making stuff that used to be traumatic just...normal now.

Google fucking vibe-coded their x86 -> ARM ISA changeover. It never would have been done without agents. Not like "google did it X% faster." Google would have let that sit forever because the labor economics of the problem were backwards.

That doesn't MATTER anymore. If you have some scratch, some halfway decent engineers, and a clear idea, you can build stuff that was just infeasible or impossible. all it takes is time and care.

Some people have figured this out and are moving now.

View on HN

I think something like an x86 -> ARM change is perfect example of something where LLM assisted coding shines. lots of busywork (i.e. smaller tasks that don't require lots of context of the other existing tasks), nothing totally novel to do (they don't have to write another borg or spanner), easy to verify, and 'translation'. LLMs are quite good at human language translation, why should they be bad at translating from one inline assembly language to another?

Yeah. Lots of busywork where if you had to assign it to a human you would need to find someone with deep technical expertise plus inordinate, unflagging attention to detail. You couldn’t pass it off to a batch of summer interns. It would have needed to be done by an engineer with some real experience. And there is no way in the world you could hire enough to do it, for almost any money.

You've missed the subtlety here.

LLMs don't have attention to detail.

This project had extremely comprehensive, easily verifiable, tests.

So the LLM could be as sloppy as they usually arez they just had to keep redoing their work until the code actually worked.

I missed the subtlety?

I linked the paper! I read the paper. Yeah. they wrote the tests, which is how this worked! how the heck do you think it was supposed to work?

the fact that they needed to write the tests was just the means to implementation. It didn't change the non-LLM labor economics of the problem.

No, I meant subtlety of definition, you've attributed the diligence to the LLM when in fact it's the tests that provide that.

You've unfortunately committed the big sin of anthropomorphizing the LLM and calling it diligent.

An LLM cannot be diligant, it's stochastic so it's literally impossible for it to be diligant.

Writing all those tests was diligant.

I didn’t attribute diligence to anything.

I’m not worried about the personal character of diligence. I’m interested in what the technology unlocked and how things made with it are materially different in terms of labor configurations.

Lmfao I’ve committed the sin of anthropomorphism.

Fadda forgive me!

C’mon pal.

Who wrote the tests?

The meat wrote the tests. As I've been telling you, they're made out of meat.

And how does the answer to your question bear on the claim I’m making?

If you're trying to automate all coding activity, writing tests is coding activity. Arguably the greater fraction of effort between implementation, and verifying said implementation. If the only thing making your problem space tractable for the automation to be able to replace the lesser half of coding activity is an authored test suite you couldn't generate via your automation, then you really need to admit that.

"Did you check?" is the most expensive question, and one of the most feared in my experience in tech circles. Spent quite a few years as a dedicated tester once I developed the knack for it. Everybody gangsta til it's time to prove the damn thing works.

> "Did you check?" is the most expensive question, and one of the most feared in my experience in tech circles.

Here it’s a climb-down. Writing tests to validate translation is orders of magnitude less work (and less likely to fail or be too dull to do properly) than the alternative available prior to 2025.

The fact that they wrote tests and clearly established operational control is not some kinda gotcha! It’s how they managed to get this piece of technology to allow them to do the IMPOSSIBLE.

I am just really struggling to understand someone who reads that paper and thinks “yup, everything is still the same and we don’t need to re-evaluate any ideas” Like, if you want to say that they still need engineering discipline in order to do ISA transitions at scale then…ok? That’s true? But Gemini meant that this formerly impossible thing was now not only within reach but done.

Exactly, if the engineers know where to look for the solution in open-source code and point the AI there, it will get them there. Even if the language or the tech stack are different, AI is excellent at finding the seams, those spots where a feature connects to the underlying tech stack, and figuring out how the feature is really implemented, and bringing that over.

> Google would have let that sit forever because the labor economics of the problem were backwards.

This has been how all previous innovations that made software easier to make turned out.

People found more and more uses for software and that does seem to be playing out again.

I really don't think we're living in a "linearly interpolate from past behavior" kinda situation.

https://arxiv.org/abs/2510.14928

Just read some of that. It's not long. This IS NOT the past telescoping into the future. Some new shit is afoot.

Google3 was already PPC clean when they did that. Not as impressive as made out to be.

Reply on news.ycombinator.com