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

Coding assistants are solving the wrong problem

bicameral-ai.com

Post reply on HN
Print view View original

111–120 of 151 posts

Re: Coding assistants are solving the wrong problem

#111

Post by falloutx »

voiper1 wrote: post #46
bambax wrote: post #37

> Unlike their human counterparts who would and escalate a requirements gap to product when necessary, coding assistants are notorious for burying those requirement gaps within hundreds of lines of code This is the kind of argument that seems true on the surface, but isn't really. An LLM will do what you ask it to do! If you tell it to ask questions and poke holes into your requirements and not jump to code, it will…

I hear your pushback, but that I think that's his point: Even seasoned coders using plan mode are funneled towards "get the code out" when experience shows that the final code is a tiny part of the overall picture. The entire experience should be reorganized that the code is almost the afterthought, and the requirements, specs, edge cases, tests, etc are the primary part.

This is always been the businessman's dream to write requirements and then coding becomes a mindless work but requirements and specs can never cover every small detail. Code itself is the spec but Business people just dont wanna write it. if you handle all edge cases and limitation in the spec, and then do the same in the code, you are just writing code twice.

This also completely ignores the fact that PMs and Business teams are generating specs by AI too, so its slop covered by more slop and has no actual specific details until you reach the code level.

Re: Coding assistants are solving the wrong problem

#112

Post by falloutx »

jpalomaki wrote: post #94
Arch-TK wrote: post #59

"Experienced developers were 19% slower when using AI coding assistants—yet believed they were faster (METR, 2025)" Anecdotally I see this _all the time_...

The article they are referring to is 404, but based on the URL was published bit more than year ago. That's quite long time in a field that is evolving so rapidly and which even the pioneers are still figuring out.

Its not from a year ago, just 6 months ago: https://metr.org/blog/2025-07-10-early-2025-ai-experienced-o...

Re: Coding assistants are solving the wrong problem

#113

Post by helloplanets »

theshrike79 wrote: post #99
helloplanets wrote: post #40

Earlier quoted context omitted.

So, your point is that programmers identify the unexpected edge cases through the act of taking their time writing the code by hand. From my experience, it takes a proficient developer to actually plan their code around future issues from separate processes. I think that it's mistaken to think that reasoning while writing the code is at all a good way to truly understand what your code is doing. (Without implying tha…

> From my experience, it takes a proficient developer to actually plan their code around future issues from separate processes. And it takes even more experience to know when not to spend time on that. Way too many codebases are optimised to 1M DAU and see like 100 users for the first year. All that time optimising and handling edge cases could've been spent on delivering features that bring in more users and thus mo…

Agreed. Overengineering and premature optimization are the root of all crud.

Re: Coding assistants are solving the wrong problem

#114

Post by mpalmer »

robertlagrant wrote: post #97

> There’s a name for misalignment between business intent and codebase implementation: technical debt. I wish we'd stop redefining this term. Technical debt is a shortcut agreed upon with the business to get something out now and fix later, and the fix will cost more than the original. It is entirely in line with business intent.

Exactly. The quote is a great definition of a bug, not debt

Re: Coding assistants are solving the wrong problem

#115

Post by embedding-shape »

bonoboTP wrote: post #63
micw wrote: post #14

For me, AI is an enabler for things you can't do otherwise (or that would take many weeks of learning). But you still need to know how to do things properly in general, otherwise the results are bad. E.g. I'm a software architect and developer for many years. So I know already how to build software but I'm not familiar with every language or framework. AI enabled me to write other kind of software I never learned or…

Yes but in my experience this sometimes works great, other times you paint yourself in a corner and the sun total is that you still have to learn the thing, just the initial ram is less steep. For example I build my self a nice pipeline for converting jpegs on disk to h264 on disk via zero-copy nvjpeg to nvenc, with python bindings but have been pulling out my hair over bframe ordering and weird delays in playback et…

Yeah, knowing what words to use is half the battle. Quickly throw away a prompt like "Hey, `make build` takes five minutes, could you make it fast enough to run under 1 minute" and the agent will do some work and say "Done, now the build takes 25 seconds as we're skipping the step of building the images, use `make build INCLUDE_IMAGES=true` when you want to build with images". It's not wrong, given the prompt, but takes a bit to get used to how they approach things.

Re: Coding assistants are solving the wrong problem

#116

Post by zhshsha »

aurareturn wrote: post #62
TrickyRick wrote: post #21

Earlier quoted context omitted.

Source: Trust me, bro. A company selling an AI model telling others their AI model is so good that it's building itself. What could possibly motivate them to say that? Remember a few years ago when Sam Altman said we had to pause AI development for 6 months because otherwise we would have the singularity and it would end the world? Yeah, about that...

Claude Code creator is saying it too. He doesn't code anymore. I personally don't code manually anymore either so I'm inclined to believe them.

[dead]

Re: Coding assistants are solving the wrong problem

#117

Post by WD-42 »

locknitpicker wrote: post #73
friendzis wrote: post #22

Earlier quoted context omitted.

You not only stumble upon a weird bug in your hacky solution that takes engineering weeks to debug, but your interfaces are fragile so feature velocity drops (bugs reproduce and unless you address reproduction rate you end up fixing bugs only) and things are so tightly coupled that every two line change is now multi-week rewrite. Look at e.g. facebook. That site has not shipped a feature in years and every time they…

> You not only stumble upon a weird bug in your hacky solution that takes engineering weeks to debug, but your interfaces are fragile so feature velocity drops (bugs reproduce and unless you address reproduction rate you end up fixing bugs only) and things are so tightly coupled that every two line change is now multi-week rewrite. I don't think you fully grasp the issue you're discussing. Things don't happen in a va…

This has always been true. I just don’t see how AI makes accumulating tech debt more attractive, as the original poster seems to be implying. If anything it seems to make things worse. At least when you write shit code by hand you know it so you can remember to go back to it, keep it in mind as a potential source of bugs. But YOLO from AI and you probably have no idea.

Re: Coding assistants are solving the wrong problem

#118

Post by sdwr »

viraptor wrote: post #52
Quothling wrote: post #13

I think AI will fail in any organisation where the business process problems are sometimes discuvered during engineering. I use AI quite a lot, I recently had Claude upgrade one of our old services from hubspot api v1 to v3 without basically any human interaction beyond the code review. I had to ask it for two changes I think, but over all I barely got out of my regular work to get it done. I did know exactly what to…

> but it doesn't refuse to write the code without first being told why it wouldn't be a better idea to do X first Then don't ask it to write code? If you ask any recent high quality model to discuss options, tradeoffs, design constraints, refine specs it will do it for you until you're sick and tired of it finding real edge cases and alternatives. Ask for just code and you'll get just code.

They are way better at code-related tasks than design or strategy ones. Anything involving users or business strategy or a "why" is vague and misguided, they have no insight.

Re: Coding assistants are solving the wrong problem

#119

Post by physicsguy »

embedding-shape wrote: post #87
physicsguy wrote: post #27

Earlier quoted context omitted.

I've had quite a bit of the "tell it to do something in a certain way", it does that at first, then a few messages of corrections and pointers, it forgets that constraint.

> it does that at first, then a few messages of corrections and pointers, it forgets that constraint. Yup, most models suffer from this. Everyone is raving about million tokens context, but none of the models can actually get past 20% of that and still give as high quality responses as the very first message. My whole workflow right now is basically composing prompts out of the agent, let them run with it and if some…

Yes, agreed. I find it interesting that people are saying they're building these huge multi-agent workflows since the projects I've tried it on are not necessarily huge in complexity. I've tried variety of different things re: isntructions files, etc. at this point.

Re: Coding assistants are solving the wrong problem

#120

Post by micw »

netdevphoenix wrote: post #80
micw wrote: post #14

For me, AI is an enabler for things you can't do otherwise (or that would take many weeks of learning). But you still need to know how to do things properly in general, otherwise the results are bad. E.g. I'm a software architect and developer for many years. So I know already how to build software but I'm not familiar with every language or framework. AI enabled me to write other kind of software I never learned or…

> Or I fixed a bug in a linux scanner driver. None of these I could have done properly (within an acceptable time frame) without AI. But also none of there I could have done properly without my knowledge and experience, even with AI There are some things here that folks making statements like yours often omit and it makes me very sus about your (over)confidence. Mostly these statements talk in a business short-term r…

Thanks for pointing these things out. I always try to learn and understand the generated code and changes. Maybe not so deep for the android app (since it's just my own pet project). But especially for every pull request to a project. Everyone should do this out of respect to the maintainers who review the change.

> Are you 100% sure your code changes didn't introduce unexpected bugs?

Who is this ever? But I do code reviews and I usually generate a bunch of tests along with my PRs (if the project has at lease _some_ test infrastructure).

Same applies for the rest of the points. But that's only _my_ way to do these things. I can imagine that others do it a different way and that the points above are more problematic then.

Post reply on HN