Hacker News new | past | comments | ask | show | jobs | submit
AI is not even close to replacing SWEs.

AI can write syntactically perfect code but barely has a sense of architecture.

It needs tons of 'guide wires' to keep it from going off track.

Unless you're building basic SaaS, it's still a 'research and coding assistant'.

AI has never produced non-messy architecture that I did not have to go in, re-think and guide a re-write.

This is spot on, AI can code, but it doesnt have the experience in the real world, so many things are designed differently from spec.

SWE's have to guide the AI, look at all those AI PR's, many of them make very bad assumptions.

loading story #50568944
> AI can write syntactically perfect code but barely has a sense of architecture.

Second point should be obvious to anyone actually building something even slightly new/complex.

loading story #50567220
The hype is so far outside of what it can actually do in many businesses. People running around saying AI has "solved" coding but code has never been the difficult part of the job, and AI hasn't solved the bringing together of context, intention, history, and various people's understanding. You can go far in tightly controlled situations, but it can also accelerate your technical debt until you become utterly dependent on tradeoffs that AI made for you. Eventually you can't do anything safely.

So many executives have turned all the safeties off and given over control of their business to a probabilistic system and ignored every engineer who said its dangerous and risky. The engineers will be the ones held accountable though, because since AI is "so effective" it must be operator error

Exactly but the problem is people doing one shot demos being impressed but not working on it further. People who were bad developers or not developers are the most impressed. Skilled developers see right through the slop.
Counter point: you don’t need architecture big things everyday, at least I don’t and everyone in my role (data engineering) knows that we don’t do that often.

Ofc unless you call some data modelling “architect” but I’m sure AI is fine for that. Guess how I know.

You're technically correct which is the best kind of correct -- but is your experience with these matters still as valuable as it used to be? How are you going to prove to management that it is? And who's to say that eventually AI won't be able to brute force its way into maintaining its slop? (Of course we can't be sure it will either, but you get my point.)
loading story #50566028
>> AI can write syntactically perfect code but barely has a sense of architecture.

This does not match my experience. At work I have AI write architecture docs for complex features based on requirements that the product team collects. When staff engineers review those docs, in the overwhelming majority of cases the only issues they can find can be characterized as nits or bike-shedding. In contrast, AI can find problems and even serious gaps in architectures designed by the most seasoned engineers on the team (because those engineers have been doing their best to resist using AI).

So I think the whole "AI can write good code but it cannot design architecture" is just cope. It's where the goal posts have been moved to after it became impossible to deny that AI can actually write good code. Next up it will be "AI can write good code and design good architecture, but it has no taste". Indeed we're seeing various of that already.

loading story #50572424