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

AI can code, but it can't build software

bytesauna.com

Post reply on HN
Print view View original

141–150 of 185 posts

Re: AI can code, but it can't build software

#141

Post by bloppe »

hamasho wrote: post #81
bloppe wrote: post #29

Earlier quoted context omitted.

> I'm paying much less attention for quality now. After all, why bother when AI produce working code? I hear this so much. It's almost like people think code quality is unrelated to how well the product works. As though you can have 1 without the other. If your code quality is bad, your product will be bad. It may be good enough for a demo right now, but that doesn't mean it really "works".

I know how important code quality is. But I can't (or don't have energy to) convince junior engineers and sometimes project managers to submit good quality code instead of vibe-coded garbage anymore.

I just hope I never have to work at a company like that again

Re: AI can code, but it can't build software

#142

Post by enraged_camel »

jumploops wrote: post #19

I've been forcing myself to "pure vibe-code" on a few projects, where I don't read a single line of code (even the diffs in codex/claude code). Candidly, it's awful. There are countless situations where it would be faster for me to edit the file directly (CSS, I'm looking at you!). With that said, I've been surprised at how far the coding agents are able to go[0], and a lot less surprised about where I need to step i…

>> Codex (gpt-5-codex) on the other hand, does exactly what you ask, almost to a fault.

I've seriously tried gpt-5-codex at least two dozen times since it came out, and every single time it was either insufficient or made huge mistakes. Even with the "have another agent write the specs and then give it to codex to implement" approach, it's just not very good. It also stops after trying one thing and then says "I've tried X, tests still failing, next I will try Y" and it's just super annoying. Claude is really good at iterating until it solves the issue.

Re: AI can code, but it can't build software

#143

Post by KurSix »

This whole situation painfully reminds me of the low-code/no-code boom from like 5–10 years ago.

Back then everyone was saying developers would become obsolete and business analysts would just “click together” enterprise solutions. In the end, we got a mess of clunky non-scalable systems that still had to be fixed and integrated by the same engineers.

LLMs are basically low-code on steroids - they make it easier to build a prototype, but exponentially harder to turn it into something actually reliable.

Re: AI can code, but it can't build software

#144

Post by saint-evan »

prmph wrote: post #27
simonw wrote: post #4

This is a good headline. LLMs are remarkably good at writing code. Writing code isn't the same thing as delivering working software. A human expert needs to identify the need for software, decide what the software should do, figure out what's feasible to deliver, build the first version (AI can help a bunch here), evaluate what they've built, show it to users, talk to them about whether it's fit for purpose, iterate…

> LLMs are remarkably good at writing code. Just this past weekend, I've designed and written code (in Typescript) that I don't think LLMs can even come close to writing in years. I have a subscription to a frontier LLM, but lately I find myself using like 25% of the time. At a certain level the software architecture problems I'm solving, drawing upon decades of understanding about maintainable, performant, and verif…

Maybe if you mentioned a more complex, lower level or niche language than typescript like maybe C, MIPS or some niche exotic systems language pushing around registers. I'd believe yu, with caveat, but with abstract high level abstract languages like Python, typescript and the likes? It's highly unlikely that you would've put together syntax in any uniquely surprising combination. Maybe yu mean yu designed a clever fix to a problem within a larger codebase so thar would mean a context/attention issue for the LLM but there's no way in hell yu wrote up a contained piece of code solving a specific problem, not tied to a larger software env, that couldn't also have been written by frontier LLMs provided yu could articulate the problem, a course-of-action and expected output/behavior. LLMs are very good at writing code in isolation, humans still have deeper intuition and we're still extremely good at doing the plug-in, wiring and big picture planning. Yu over-estimate what you've done with typescript or misunderstand what 'LLMs are good at writing code' [in isolation] means

Re: AI can code, but it can't build software

#145

Post by simonw »

skydhash wrote: post #136
simonw wrote: post #68

Earlier quoted context omitted.

> Only a tiny subset of software development projects are like that though. Right: the majority of software development is things like "build a REST API for these three database tables" or "build a contact form with these four fields" or "write unit tests for this new function" or "update my YAML CI configuration to run this extra command".

You do know that system programming is a thing? Or that desktop applications are software too?

I said "the majority of software development". Those are both relatively niche disciplines in 2025.

Re: AI can code, but it can't build software

#146

Post by KurSix »

latentsea wrote: post #96
prmph wrote: post #27

Earlier quoted context omitted.

> LLMs are remarkably good at writing code. Just this past weekend, I've designed and written code (in Typescript) that I don't think LLMs can even come close to writing in years. I have a subscription to a frontier LLM, but lately I find myself using like 25% of the time. At a certain level the software architecture problems I'm solving, drawing upon decades of understanding about maintainable, performant, and verif…

I think C# is really going to shine in the LLM coding era. You can write Roslyn Analyzers to fail the build on arbitrary conditions after inspecting the AST. LLMs are great at helping you write these too. If you get a solid architecture well defined you can then use these as guardrails to constrain development to only happen in the manner you intend. You can then get LLMs to implement features and guarantee the code…

Linters are great at catching specific pattern violations, but they’re useless against bad decomposition or a poorly chosen abstraction. An LLM can generate code that passes all 100 linters and still ends up being a logical mess - with business logic in the wrong layer and completely unmaintainable.

Re: AI can code, but it can't build software

#147

Post by KurSix »

eterm wrote: post #35

I've been experimenting with a little vibe coding. I've generally found the quality of .NET to be quite good. It trips up sometimes when linters ping it for rules not normally enforced, but it does the job reasonably well. The front-end javascript though? It's both an absolute genuis and a complete menace at the same time. It'll write reams of code to gets things just right but with no regards to human maintainabilit…

You can take the git idea even further.

Instead of just committing more often, make the agent write commits following the conventional commits spec (feat:, fix:, refactor:) and reference a specific item from your plan.md in the commit body. That way you’ll get a self-documenting history - not just of the code, but of the agent’s thought process, which is priceless for debugging and refactoring later on

Re: AI can code, but it can't build software

#148

Post by Kim_Bruning »

"On two occasions I have been asked, 'Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?' I am not able rightly to apprehend the kind of confusion of ideas that could provoke such a question."

   --Charles Babbage
We have now come to the point where you CAN put in the wrong figures and sometimes the right answer comes out (possibly over half the time!). This was and is incredible to me and I feel lucky to be alive to see it.

However, people have taken that to mean that you can ask any old question any old way and have the right answer come out now. I might at one point have almost thought so myself. But LLMs currently are definitely not there yet.

Consider (eg) Claude Code to be your English SHell (Compare: zsh, bash).

Learn what it can and can't do for you. It's messier to learn than straight and/or/not; and I'm not sure there's manuals for it; and any manual will be outdated next quarter anyway; but that's the state of play at this time.

Re: AI can code, but it can't build software

#149

Post by somebehemoth »

simonw wrote: post #145
skydhash wrote: post #136

Earlier quoted context omitted.

You do know that system programming is a thing? Or that desktop applications are software too?

I said "the majority of software development". Those are both relatively niche disciplines in 2025.

Can you please explain? Are you saying all software development outside of the web is "niche"?

Re: AI can code, but it can't build software

#150

Post by loco5niner »

Kim_Bruning wrote: post #148

"On two occasions I have been asked, 'Pray, Mr. Babbage, if you put into the machine wrong figures, will the right answers come out?' I am not able rightly to apprehend the kind of confusion of ideas that could provoke such a question." --Charles Babbage We have now come to the point where you CAN put in the wrong figures and sometimes the right answer comes out (possibly over half the time!). This was and is incredi…

Well, the right answers have been put in the knowledgebase. It's just that the prompt may be wrong.
Post reply on HN