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

The End of Programming

pauldix.com

Post reply on HN
Print view View original

61–70 of 124 posts

Re: The End of Programming

#61

Post by fer »

> And you can say, “well it’s not that impressive because they had an oracle to compare against, so it was simple to go from one language to another”, but I think that’s selling this entire thing short.

It's not. If you give it a reference implementation, and unless the LLM/agent cheats, you'd get the migration minus undocumented/untested behavior. I've done that with different domain, migrating existing numerical code from Fortran to Rust. When working on the same codebase, agents routinely shit the bed unless given increasingly specific and concrete specs.

It's simply a spectrum between "make an airbnb for ants, make no mistakes" and providing an actual specification (and I consider an implementation to be such). What you don't provide and account for from the beginning will be paid in tokens later. That puts a price label on technical debt, which is interesting in itself, and a perverse incentive for AI companies.

Re: The End of Programming

#62

Post by ironmagma »

Gareth321 wrote: post #26

I agree with the thesis. Development is moving towards intent and alignment and clear understanding of needs. These have always been important but in a future where code is almost free, customers will be more demanding about having their needs met, fast. Our SaaS company is making plans to move towards bespoke development, which until now has been far too costly for most customers to accept. It also violates the mult…

The time has long passed since the “inevitable” things should have come into existence, for example universal basic housing. What happened instead of the advent of it is something to behold: somehow instead of supply being provisioned in response to demand, we simply changed the excess demand into an externality. Now there’s been a lot of “rage” about this, but it hasn’t been effectual. We still have plenty of homelessness right now and no particular mechanism to control it. We may not be ready for this change, but that doesn’t mean we will accept the change instead of simply pretending the problem never existed and should never exist, if everyone just behaved right.

Re: The End of Programming

#64

Post by simonw »

AJRF wrote: post #59
simonw wrote: post #46

Earlier quoted context omitted.

Yes, why do you ask?

I see a lot of enthusiasm from people who work alone or who have total control over a project and nothing but abject misery from people who work in a professional setting with a group of people using coding models. I'm just building some data points.

I don't work with a large team, so I don't personally experience the hell of coworkers dumping thousands of lines of unreviewed slop on me.

(I get a bit of exposure to that from my open source projects but it's much easier to close or ignore those.)

Re: The End of Programming

#65

Post by swingboy »

I’m still looking out for the end of programming for the human eye: these models are still pretty bad at any kind of UI that isn’t some React dashboard or single page report. For example, iOS / SwiftUI design. Sure, they can write the code just fine, but I’ve had a hard time just letting them vibe out a basic View with Sections that doesn’t look slopped out.

Re: The End of Programming

#66

Post by kodoman »

znnajdla wrote: post #22

The article gives the example of Bun's successful Zig to Rust of why this is the end of programming. I think that rewrite is a perfect example of why it's NOT the end of software engineering. A non-programmer could not have prompted AI to do that rewrite, and in fact a non-programmer would not have even conceived of the idea of doing that rewrite in the first place. Somebody is still needed to 1. come up with the ide…

Yeah when ever I have been worried about AI completely removing the need for any kind of programming skill I think about how much I had to guide it and stop it doing dumb things (even when using Sol or Fable).

I also tried to vibe code a machine learning thing and it got to a level where I was lost and I tried to move ahead without understanding the problem and let the agent figure it out. And despite using Fable it was a mess and I realized that I had to teach my self more before I can continue. Even worse it felt like it was working for a bit until It become clear it was trash. I would Imagine that kind of experience would annoy a lot of non-developers and they would not want to try again.

It feels like this narrative of programming and computer sciences skills being irrelevant is pushed by many groups (not just AI companies) who want to reduce the value of human skill and talent both financially and socially. It's quite insidious when you think about it, A gleeful sort of tone is detectable where the person is happy that nothing require mental effort or skill. Not that this is that article and that it seems to be saying that AI has changed everything (which I agree some what though I think people will still write some code by hand, Their are still things I code entirely by hand usually certain scripts or things I really need to understand and my intuition of them is important)

Re: The End of Programming

#67

Post by mastermage »

simonw wrote: post #46
AJRF wrote: post #40

Earlier quoted context omitted.

Simon - I hope this is not a rude question, but do you work with other engineers?

Yes, why do you ask?

I think he is saying this in reference to this: "If you can reduce a problem to a clearly verifiable end state, provide the necessary context [...]"

Which for reference i am not an engineer but a Physicist is literally one of the things we make jokes about for engineers. Not that we are much better in that regard as a verfiable end state in Physics is like realy realy dificult to get so is the necessary context.

Re: The End of Programming

#68

Post by the-smug-one »

wez_official wrote: post #38
the-smug-one wrote: post #14

The main reason that I'm in the process of switching jobs is to get more money, in case we are fucked as a profession later on. So yeah, even if I don't necessarily believe this is the future, I am certainly making sure that if it is the future I will be more comfortable.

What are you switching to?

Switching jobs, not profession. I am currently very underpaid.

Re: The End of Programming

#69

Post by satvikpendem »

znnajdla wrote: post #53
dogcomplex wrote: post #48

Earlier quoted context omitted.

Yes but those are all semantic tasks which can be done and understood in time by the next iteration of models training at that meta-level of architectural analysis. AI deeply understands what Bun, Zig and Rust are, how they work, can conceive of the before and after architecture (probably the hard step here), can conceive of the goal of the rewrite, and can verify (using Lean and machine-checked proofs of the before…

Sure, maybe step 2 can eventually be replaced by AI. But step 1? Why would the AI even conceive of the idea of doing a rewrite in the first place? And rewriting is just an example. There are tons of architectural decisions that need to be made every day in the building of advanced software. This is no "correct" way to do it that the AI can know in advance, it's a technical decision to be made by an engineer.

Maybe it sees a bunch of segfaults in the Zig codebase and decides a memory safe language is better, just as the human did in Bun's rewrite. I'm not sure why you think it wouldn't have been able to conceive a rewrite.

Re: The End of Programming

#70

Post by mechazawa »

AJRF wrote: post #24

Such a big disconnect in the coverage of coding models and the output they produce. If you discard coding purity questions like style, architecture, cleanliness - the stuff they come out with is buggy & error prone. The problems seems architectural - in that context windows are limited and you need more compute to increase them, married with the fact the models are really over confident. But if you do increase them i…

> Claude told them

People acting like meat proxies add no value. Claude is also very eager to make conclusions without digging deeper. It has no inherent curiosity or prior knowledge about the codebase asside from what it can see.

Post reply on HN