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

91–100 of 185 posts

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

#91

Post by FromTheFirstIn »

jcelerier wrote: post #86
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…

> The people saying LLMs can code are hard for me to understand. They are good for simple bash scripts and complex refactoring and drafting basic code idioms and that's about it that's like, 90% of the code people are writing

But not 90% of the work people do. It’s solved a task, not a problem.

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

#92

Post by simonw »

NicoJuicy wrote: post #79
CjHuber wrote: post #44

Earlier quoted context omitted.

Can you maybe give an example you’ve encountered of an algorithm or a data structure that LLMs cannot handle well? In my experience implementing algorithms from a good comprehensive description and keeping track of data models is where they shine the most.

There are severe edge cases. Here are some of the last days. Eg. Just updating bootstrap to angular bootstrap. It didn't transfer how I placed the dropdowns ( basically using dropdown-end). So everything was out of view in desktop and mobile. It forgot the transloco I used everywhere and just used default English ( happens a lot). Suggested code that fixed 1 bug ( expression property recursion), but now linq to SQL w…

Do you have any automated tests for that project?

I'm bringing to suspect a lot of my great experiences with coding agents come from the fact that they can run tests to confirm they haven't broken anything.

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

#93

Post by simonw »

IanCal wrote: post #77
simonw wrote: post #71

Earlier quoted context omitted.

I expect that customers who have those needs would much rather hire somebody to be the intermediary with the LLM writing the code than take on that role themselves. You'll get the occasional high agency non-technical customer who decides to learn how to get these things done with LLMs but they'll be a pretty rare breed.

This may be a timeframe issue but I sincerely doubt anyone wants to hire someone to be an intermediary. They just want the thing done. I know that right now few want to sit in front of claude code, but it's just not that big of a leap to move this up a layer. Workflows do this even without the models getting better.

YouTube can show anyone how to unblock a sink. Most people still choose to call a plumber.

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

#95

Post by mrheosuper »

apical_dendrite wrote: post #24

I've been working with a data processing pipeline that was vibe-coded by an AI engineer, and while the code works, as software that has to fit into a production environment, it's a mess. Take logging for example. The pipeline is made up of AWS lambdas written in python. The person who built it wanted to add context to each log for debugging and the LLM generated hundreds of lines of python in each lambda to do this (…

Does it work ?

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

#96

Post by latentsea »

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…

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 comes out in the shape you expect it to.

This works well for humans too, but custom analysers are abstract and not many devs know how to write them, so they are mostly provided by library authors. However, being able to generate them via LLMs makes them so much more accessible, and IMHO is a game changer for enforcing an architecture.

I've been exploring this direction a lot lately, and it feels very promising.

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

#97

Post by vrc »

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…

I’m a PM and I’ve been able to do a lot of very interesting near production ready bits of coding recently with an LLM. I say near production ready because I specifically only build functional data processing stuff that I intentionally build with clean I/O requirements to hand to the real engineers on the team to slot in. They still have to fix some things to meet our standards, but I’m basically a “researcher” level coder. Which makes sense — I do have an undergrad and MS in CS, and did a lot of mathy algo stuff. For the last 15+ years I could never use anything in my brain to help the team solve things I was best suited to solve. I am now, and that’s nice.

The one key point is that I am keenly aware of what I can and cannot do. With these new superpowers, I often catch myself doing too much, and I end up doing a lot more rewrites than a real engineer would. But I can see Dunning Kruger playing out everywhere when people say they can vibe code an entire product.

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

#98

Post by jumploops »

throwaway314155 wrote: post #31
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…

> Candidly, it's awful. Noting your caveat but I’m doing this with Python and your experience is very different from mine.

Oh, don't get me wrong, the models are marvelous!

The "it's awful" admission is due to the "don't look at code" aspect of this exercise.

For real work, my split is more like 80% LLM/20% non-LLM, and I read all the code. It's much faster!

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

#99

Post by bgrainger »

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…

Completely agree, and I've started writing more Roslyn analyzers to provide quick feedback to the LLM (assuming you're using it in something like VS Code that exposes the `problems` tool to the model).

I also want C# semantics even more closely integrated with the LLM. I'm imagining a stronger version of Structured Model Outputs that knows all the valid tokens that could be generated following a "." (including instance methods, extension properties, etc.) and prevents invalid code from even being generated in the first place, rather than needing a roundtrip through a Roslyn analyzer or the compiler to feed more text back to the model. (Perhaps there's some leeway to allow calls to not-yet-written methods to be generated.) Or maybe this idea is just a crutch I'm inventing for current frontier models and future models will be smart enough that they don't need it?

Post reply on HN