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

Reflections on software engineering in the age of AI

adiamond.me

Post reply on HN
Print view View original

41–50 of 110 posts

Re: Reflections on software engineering in the age of AI

#41

Post by brazukadev »

ManuelKiessling wrote: post #38
whoke wrote: post #20

"you haven’t done any of the hard thinking you would normally do in writing the code yourself" It's true, I spend less time solving problems that arise naturally from the process of implementation. But implementation errors have a poor signal-to-noise ratio. For every error that exposes a real design problem there are 10 others that involve routine fixes: type errors, scope issues, import resolution, dependencies. Th…

This is half question, half thought experiment: What exactly is it that makes us think „great, I can delegate coding to the agent, and focus on architecture myself“, instead of „great, I can delegate coding to the agent, and I can delegate architecture to the agent, and I can focus on myself“? And how many levels up can you construct this sentence before things go south? What I‘m implying with this question is, of co…

You can delegate architecture to agents, as long as you know different architectures and decide which one is the most fit for a given scenario. AI can choose one but it will usually pick the one that is more present in the training corpus.

React + NextJS is a terrible architectural decision for most projects that LLMs recommend all the time.

Re: Reflections on software engineering in the age of AI

#42

Post by lilerjee »

raincole wrote: post #24
lilerjee wrote: post #13

This is not an Age of AI. Why do so many not-real-programmers think this is an age of AI? It's just a hype. I am developing my own app 2+ years manually, and not use "AI" at all. Using AI usually can cause many problems, which the author pointed at. Programming should be enjoyable, not an annoyed or unhappy thing.

> I am developing my own app 2+ years manually, and not use "AI" at all. How does this mean this isn't an age of AI? Because you're The Representative of Programmers? > so many not-real-programmers Oh sorry I missed this part. It seems that you really are!

The force of "AI" companies hype is very strong now, they are everywhere. If you research the articles very carefully, you will feel this force.

The force cannot beat the reality or truth.

Re: Reflections on software engineering in the age of AI

#43

Post by dominotw »

whoke wrote: post #20

"you haven’t done any of the hard thinking you would normally do in writing the code yourself" It's true, I spend less time solving problems that arise naturally from the process of implementation. But implementation errors have a poor signal-to-noise ratio. For every error that exposes a real design problem there are 10 others that involve routine fixes: type errors, scope issues, import resolution, dependencies. Th…

ironically llm prove the its not possible to just think "abstract thoughts" . we cannot remove concrete "implmenation" facts like paris is capital of france and retain just abstract "countries have capitals"

Re: Reflections on software engineering in the age of AI

#44

Post by michaelchisari »

dnadler wrote: post #37
michaelchisari wrote: post #35

Earlier quoted context omitted.

| type errors, scope issues, import resolution, dependencies. I write code myself and use the LLM to find mistakes then fix them manually. I recommend inverting the conventional wisdom on LLMs: 1. Don't use it to write code. It's a terrible programmer. But it's an intelligent rubber duck and a solid analysis tool. 2. Write the code yourself. It'll go faster than figuring it out as you go along. It's just typing if yo…

> Don't use it to write code. It's a terrible programmer. I see this sentiment often, and I’m honestly not sure where this comes from, as it’s really not been my experience. I feel like this must come from people feeling threatened and just moving the goals posts, or not knowing how to use the tools effectively.

It's a common enough experience that it shouldn't be dismissed.

Re: Reflections on software engineering in the age of AI

#45

Post by tgarrett »

danans wrote: post #27
tgarrett wrote: post #12

Earlier quoted context omitted.

> Outside of the very few computer scientists working on novel algorithms, It's a quite a bit broader than that: for instance most of science and engineering is heavily supported by simulations (very useful when the system you're considering doesn't have perfect spherical or cylindrical symmetry), and there is still tons of algorithm development going on. The world is vast, and thus so is the domain of programming. A…

> It's a quite a bit broader than that: for instance most of science and engineering is heavily supported by simulations (very useful when the system you're considering doesn't have perfect spherical or cylindrical symmetry), That isn't the vast majority of traditional software engineering work, and arguably is better called applied physics or applied science. Super interesting though - and definitely uses programmin…

> That isn't the vast majority of traditional software engineering work, and arguably is better called applied physics or applied science.

Fair enough, and yeah definitions are always going to be somewhat fuzzy. Still it seems safe to assume there are also a lot of novel things going on in games, embedded, finance, AI itself of course... Generally I can't help but feel that we have only dipped our toes into the vast ocean of program space, and I'm curious what else is out there.

Re: Reflections on software engineering in the age of AI

#46

Post by throwrioawfo »

prymitive wrote: post #22

For me the biggest issue with AI coding model is not that it writes code, or how it writes code, or whether it will replace me or not. I mean, these are real problems, but just not the ones that makes the difference to me daily. Instead what sets my feeling about the AI is simple: the experience of working with AI models, because it's the worse experience of my life so far. Every single LLM will make up stuff, go dow…

> doing ALMOST what I asked it to do, but just not quite

This is my exact experience. LLMs get 95% of the way to my personal quality bar, and for simple tasks 100% of the way.

More complex things, no. This means that, in practice, I end up having to understand the code pretty much as much deeply as I would anyway, without agents.

So, essentially, my experience is that it's automated away the easy bits, but left the hard bits, so all of my time is spent doing the hard bits, which is mentally exhausting.

Maybe Fable would be good enough to get to 100% of my quality bar on more complex tasks, but I never got chance to try it.

Re: Reflections on software engineering in the age of AI

#47

Post by ezoe »

danans wrote: post #7

> Someone asks you to add a feature to an existing program While I empathize with the tone, even before AI the creativity was largely at the feature definition step, not in the implementation. Outside of the very few computer scientists working on novel algorithms, the vast majority of software development is a mapping problem between the feature request and the mundane technical details, something repeatedly (and co…

Such a creative era was until early 1990s. Back then, we have to implement almost everything that is provided by standard library and popular frameworks we take it for granted for now.

Re: Reflections on software engineering in the age of AI

#48

Post by marcosdumay »

dnadler wrote: post #37
michaelchisari wrote: post #35

Earlier quoted context omitted.

| type errors, scope issues, import resolution, dependencies. I write code myself and use the LLM to find mistakes then fix them manually. I recommend inverting the conventional wisdom on LLMs: 1. Don't use it to write code. It's a terrible programmer. But it's an intelligent rubber duck and a solid analysis tool. 2. Write the code yourself. It'll go faster than figuring it out as you go along. It's just typing if yo…

> Don't use it to write code. It's a terrible programmer. I see this sentiment often, and I’m honestly not sure where this comes from, as it’s really not been my experience. I feel like this must come from people feeling threatened and just moving the goals posts, or not knowing how to use the tools effectively.

I see your sentiment quite often here on HN¹, I'm honestly not sure what kind of experience you may have had with automatic program writers. LLM code absolutely sucks.

1 - I wonder why my other social circles are so different.

Re: Reflections on software engineering in the age of AI

#49

Post by manuisin »

jdw64 wrote: post #9

Reading posts on HN, I notice that even across different programming domains, surprisingly similar problems emerge. Seeing this, I can't help but think that programming might ultimately be a matter of organizational theory. Conway's Law speaks to this as well. Code structure and approach shift significantly depending on how an organization is structured. From that perspective, it makes sense why Gen AI coding yields…

That was very nice to read. Refreshing to see a deep take that’s optimistic.

Re: Reflections on software engineering in the age of AI

#50

Post by prymitive »

throwrioawfo wrote: post #46
prymitive wrote: post #22

For me the biggest issue with AI coding model is not that it writes code, or how it writes code, or whether it will replace me or not. I mean, these are real problems, but just not the ones that makes the difference to me daily. Instead what sets my feeling about the AI is simple: the experience of working with AI models, because it's the worse experience of my life so far. Every single LLM will make up stuff, go dow…

> doing ALMOST what I asked it to do, but just not quite This is my exact experience. LLMs get 95% of the way to my personal quality bar, and for simple tasks 100% of the way. More complex things, no. This means that, in practice, I end up having to understand the code pretty much as much deeply as I would anyway, without agents. So, essentially, my experience is that it's automated away the easy bits, but left the h…

> So, essentially, my experience is that it's automated away the easy bits

Yes, which is great for “easy” but mundane and time consuming tasks like refactoring structs when you have a ton of tests that look at snapshots of nested structs etc. Squeezing that last few bits of “make comments consistent with the style and tone of existing comments”, or “stop adding docs that make it sound like an academic paper” or just keep the overall feel of the code same across all files take a lot of effort and energy.

Post reply on HN