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

11–20 of 185 posts

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

#11

Post by bcrosby95 »

subtlesoftware wrote: post #3

True for now because models are mainly used to implement features / build small MVPs, which they’re quite good at. The next step would be to have a model running continuously on a project with inputs from monitoring services, test coverage, product analytics, etc. Such an agent, powered by a sufficient model, could be considered an effective software engineer. We’re not there today, but it doesn’t seem that far off.

> The next step would be to have a model running continuously on a project with inputs from monitoring services, test coverage, product analytics, etc. Such an agent, powered by a sufficient model, could be considered an effective software engineer.

Building an automated system that determines if a system is correct (whatever that means) is harder to build than the coding agents themselves.

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

#12

Post by bloppe »

subtlesoftware wrote: post #3

True for now because models are mainly used to implement features / build small MVPs, which they’re quite good at. The next step would be to have a model running continuously on a project with inputs from monitoring services, test coverage, product analytics, etc. Such an agent, powered by a sufficient model, could be considered an effective software engineer. We’re not there today, but it doesn’t seem that far off.

> We’re not there today, but it doesn’t seem that far off.

What time frame counts as "not that far off" to you?

If you tried to bet me that the market for talented software engineers would collapse within the next 10 years, I'd take it no question. 25 years, I think my odds are still better than yours. 50 years, I might not take the bet.

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

#13

Post by roxolotl »

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…

One of the interesting corollaries of the title is that this can also be true of humans. Being able to code is not the same as being a software engineer. It never has been.

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

#14

Post by AnimalMuppet »

bradfa wrote: post #7

The context windows are still dramatically too small and the models aren’t yet seeming to train on how to build maintainable software. There is a lot less written down about how to do this on the public web. There’s a bunch of high level public writing but not may great examples of real world situations that happen on every proprietary software project, because that’s very messy data locked away internal to companies…

In fairness, there's a lot more "software" than there is "maintainable software" in their training data...

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

#15

Post by jfim »

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 guess the big question is if experienced product management types can pick up enough coding technical literacy to work like this without programmers

I'd argue that they can't, at least on a short timeframe. Not because LLMs can't generate a program or product that works, but that there needs to be enough understanding of how the implementation works to fix any complex issues that come up.

One experience I had is that I had tried to generate a MITM HTTPS proxy that uses Netty using Claude, and while it generated a pile of code that looked good on the surface, it didn't actually work. Not knowing enough about Netty, I wasn't able to debug why it didn't work and trying to fix it with the LLM didn't help either.

Maybe PMs can pick up enough knowledge over time to be able to implement products that can scale, but by that time they'd effectively be a software engineer, minus the writing code part.

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

#16

Post by subtlesoftware »

bloppe wrote: post #12
subtlesoftware wrote: post #3

True for now because models are mainly used to implement features / build small MVPs, which they’re quite good at. The next step would be to have a model running continuously on a project with inputs from monitoring services, test coverage, product analytics, etc. Such an agent, powered by a sufficient model, could be considered an effective software engineer. We’re not there today, but it doesn’t seem that far off.

> We’re not there today, but it doesn’t seem that far off. What time frame counts as "not that far off" to you? If you tried to bet me that the market for talented software engineers would collapse within the next 10 years, I'd take it no question. 25 years, I think my odds are still better than yours. 50 years, I might not take the bet.

Great question. It depends on the product. For niche SaaS products, I’d say in the next few years. For like Amazon.com, on the order of decades.

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

#17

Post by bloppe »

thomasfromcdnjs wrote: post #8
subtlesoftware wrote: post #3

True for now because models are mainly used to implement features / build small MVPs, which they’re quite good at. The next step would be to have a model running continuously on a project with inputs from monitoring services, test coverage, product analytics, etc. Such an agent, powered by a sufficient model, could be considered an effective software engineer. We’re not there today, but it doesn’t seem that far off.

Agreed. I've played around with agent only code bases (where I don't code at all), and had an agent hooked up to server logs, which would create an issue when it encounters errors, and then an agent would fix the tickets, push to prod and check deployment statuses etc. Worked good enough to see that this could easily become the future. (I also had it claude/codex code that whole setup) Just for semantic nitpicking, I…

The article "AI can code, but it can't build software"

An inevitable comment: "But I've seen AI code! So it must be able to build software"

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

#18

Post by bloppe »

jahbrewski wrote: post #5
subtlesoftware wrote: post #3

True for now because models are mainly used to implement features / build small MVPs, which they’re quite good at. The next step would be to have a model running continuously on a project with inputs from monitoring services, test coverage, product analytics, etc. Such an agent, powered by a sufficient model, could be considered an effective software engineer. We’re not there today, but it doesn’t seem that far off.

I’ve heard “we’re not there today, but it doesn’t seem that far off” since the beginning of the AI infatuation. What if, it is far off?

It's telling to me that nobody who actually works in AI research thinks that it's "not that far off".

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

#19

Post by jumploops »

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 in.

Things that seem to help: 1. Always create a plan/debug markdown file 2. Prompt the agent to ask questions/present multiple solutions 3. Use git more than normal (squash ugly commits on merge)

Planning is key to avoid half-brained solutions, but having "specs" for debug is almost more important. The LLM will happily dive down a path of editing as few files as possible to fix the bug/error/etc. This, unchecked, can often lead to very messy code.

Prompting the agent to ask questions/present multiple solutions allows me to stay "in control" over the how something is built.

I now basically commit every time a plan or debug step is complete. I've tried having the LLM control git, but I feel that it eats into the context a bit too much. Ideally a 3rd party "agent" would handle this.

The last thing I'll mention is that Claude Code (Sonnet 4.5) is still very token-happy, in that it eagerly goes above and beyond when not always necessary. Codex (gpt-5-codex) on the other hand, does exactly what you ask, almost to a fault. For both cases, this is where planning up-front is super useful.

[0]Caveat: the projects are either Typescript web apps or Rust utilities, can't speak to performance on other languages/domains.

Post reply on HN