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

121–130 of 151 posts

Re: Coding assistants are solving the wrong problem

#121

Post by throwdbaaway »

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…

I call this the Groundhog Day loop

Re: Coding assistants are solving the wrong problem

#122

Post by embedding-shape »

throwdbaaway wrote: post #121
embedding-shape wrote: post #87

Earlier quoted context omitted.

> 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…

I call this the Groundhog Day loop

That's a strange name, why? It's more like a "iterate and improve" loop, "Groundhog Day" to me would imply "the same thing over and over", but then you're really doing something wrong if that's your experience. You need to iterate on the initial prompt if you want something better/different.

Re: Coding assistants are solving the wrong problem

#123

Post by embedding-shape »

physicsguy wrote: post #119
embedding-shape wrote: post #87

Earlier quoted context omitted.

> 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.

So far, I haven't yet seen any demonstration of those kind of multi-agent workflows ending up with code that won't fall down over itself in some days/weeks. Most efforts so far seems to have to been focusing on producing as much code as possible, as fast as possible, while what I'd like to see, if anything, is the opposite of that.

Anytime I ask for demonstration of what the actual code looks like, when people start talking about their own "multi-agent orchestration platforms" (or whatever), they either haven't shared anything (yet), don't care at all about how the code actually is and/or the code is a horrible vibeslopped mess that contains mostly nonsense.

Re: Coding assistants are solving the wrong problem

#124

Post by netdevphoenix »

micw wrote: post #120
netdevphoenix wrote: post #80

Earlier quoted context omitted.

> 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…

> I always try to learn and understand the generated code and changes

Not to be pedantic but, do you _try_ to understand? Or do you _actually_ understand the changes? This suggests to me that there are instances where you don't understand the generated code on projects others than your own, which is literally my point and that of many others. And even if you did understand it, as I pointed out earlier, that's not enough. It is a low bar imo. I will continue to keep my mind open but yours isn't a case study supporting the use of these assistants but the opposite.

In science, when a new idea is brought forward, it gets grilled to no end. The greater the potential the harder the grilling. Software should be no different if the builders want to lay a claim on the name "engineer". It is sad to see a field who claims to apply scientific principles to the development of software not walking the walk.

Re: Coding assistants are solving the wrong problem

#125

Post by coffeefirst »

locknitpicker wrote: post #86
coffeefirst wrote: post #38

Earlier quoted context omitted.

That’s not how this goes. Because the entire codebase is crap, each user encounters a different bug. So now all your customers are mad, but they’re all mad for different reasons, and support is powerless to do anything about it. The problems pile up but they’re can’t be solved without a competent rewrite. This is a bad place to be. And at some level of sloppiness you can get load bearing bugs, where there’s an unknow…

> That’s not how this goes. Once you gain some professional experience working with software development, you'll understand that that's exactly how it goes. I think you are failing to understand the "soft" in "software". Changing software is trivial. All software has bugs, but the only ones being worked on are those which are a) deemed worthy of being worked on, b) have customer impact. > So now all your customers ar…

Nothing I just described was hypothetical. I’ve been the developer on the rewrite crew, the EM determining if there’s anything to salvage, and the client with a list of critical bugs that aren’t getting fixed and ultimately killed the contract.

If you haven’t seen anything reach that level of tech debt with active clients, well, lucky you.

Re: Coding assistants are solving the wrong problem

#126

Post by rcarmo »

iLoveOncall wrote: post #72
rcarmo wrote: post #57

I think that the premise is wrong (and the title is very clickbaity, but we will ignore that it doesn’t really match the article and the “conclusion”): coding agents are “solving” at least one problem, which is to massively expand the impact of senior developers _that can use them effectively_. Everything else is just hype and people “holding it wrong”.

I really wonder how you people manage to ignore the many research studies that have come out and prove this wrong.

“You people” is a loaded term in US culture. And for what you know, I might just be an AI :)

Re: Coding assistants are solving the wrong problem

#128

Post by throwdbaaway »

embedding-shape wrote: post #122
throwdbaaway wrote: post #121

Earlier quoted context omitted.

I call this the Groundhog Day loop

That's a strange name, why? It's more like a "iterate and improve" loop, "Groundhog Day" to me would imply "the same thing over and over", but then you're really doing something wrong if that's your experience. You need to iterate on the initial prompt if you want something better/different.

I thought "iterate and improve" was exactly what Phil did.

Re: Coding assistants are solving the wrong problem

#129

Post by perrygeo »

bandrami wrote: post #85
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…

Huh. I'm extremely skeptical of AI in areas where I don't have expertise, because in areas where I do have expertise I see how much it gets wrong. So it's fine for me to use it in those areas because I can catch the errors, but I can't catch errors in fields I don't have any domain expertise in.

I feel the same way. LLMs errors sound most plausible to those who know least.

On complex topics where I know what I'm talking about, model output contains so much garbage with incorrect assumptions.

But complex topics where I'm out of my element, the output always sounds strangely plausible.

This phenomenon writ large is terrifying.

Re: Coding assistants are solving the wrong problem

#130

Post by aaaasmile »

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…

>Arguably, AI hypers should lead with data not with anecdotal evidence

This reminds me of people who get sad when they realize they haven’t discovered anything amazing.

I am pedantic and “people that” → “people who” (for people, who is preferred).

Post reply on HN