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

41–50 of 151 posts

Re: Coding assistants are solving the wrong problem

#41

Post by trcf23 »

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…

Also most of the studies shown start to be obsolete with AI rapid path of improvements. Opus 4.5 has been a huge game changer for me (combined with CC that I had not used before) since December. Claude code arrived this summer if I’m not mistaken.

So I’m not sure a study from 2024 or impact on code produced during 2024 2025 can be used to judge current ai coding possibilities.

Re: Coding assistants are solving the wrong problem

#42

Post by viraptor »

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…

> But you still need to know how to do things properly in general, otherwise the results are bad.

Even that could use some nuance. I'm generating presentations in interactive JS. If they work, they work - that's the result, and I extremely don't care about the details for this use case. Nobody needs to maintain them, nobody cares about the source. There's no need for "properly" in this case.

Re: Coding assistants are solving the wrong problem

#43

Post by trcf23 »

ozlikethewizard wrote: post #33
mirsadm wrote: post #26

Earlier quoted context omitted.

I use Claude Code a lot but one thing that really made me concerned was when I asked it about some ideas I have had which I am very familiar with. It's response was to constantly steer me away from what I wanted to do towards something else which was fine but a mediocre way to do things. It made me question how many times I've let it go off and do stuff without checking it thoroughly.

Call me a conspiracy theorist, and granted much of this could be attributed to the fact that the majority of code in existence is shit, but im convinced that these models are trained and encouraged to produce code that is difficult for humans to work on. Further driving and cementing the usage of then when you inevitably have to come back and fix it.

Or it takes a lot of time effort and intelligence to produce good code and IA is not there yet…

Re: Coding assistants are solving the wrong problem

#44

Post by heeton »

zkmon wrote: post #11

Wondering why is ths on front page? There is hardly any new insight other than a few minutes of exposure to greenish glow that makes everything looks brownish after you close that page.

I upvoted because I’m very keen for more teams to start trying to solve this problem and release tools and products to help.

Context gathering and refinement is the biggest issue I have with product development at the moment.

Re: Coding assistants are solving the wrong problem

#45

Post by exceptione »

ozlikethewizard wrote: post #33
mirsadm wrote: post #26

Earlier quoted context omitted.

I use Claude Code a lot but one thing that really made me concerned was when I asked it about some ideas I have had which I am very familiar with. It's response was to constantly steer me away from what I wanted to do towards something else which was fine but a mediocre way to do things. It made me question how many times I've let it go off and do stuff without checking it thoroughly.

Call me a conspiracy theorist, and granted much of this could be attributed to the fact that the majority of code in existence is shit, but im convinced that these models are trained and encouraged to produce code that is difficult for humans to work on. Further driving and cementing the usage of then when you inevitably have to come back and fix it.

I don't think they would be able to have an LLM withouth the flaws. The problem is that an LLM cannot make a distinction between sense and nonsense in the logical way. If you train an LLM on a lot of sensible material, it will try to reproduce it by matching training material context and prompt context. The system does not work on the basis of logical principles, but it can sound intelligent.

I think LLM producers can improve their models by quite a margin if customers train the LLM for free, meaning: if people correct the LLM, the companies can use the session context + feedback to as training. This enables more convincing responses for finer nuances of context, but it still does not work on logical principles.

LLM interaction with customers might become the real learning phase. This doesn't bode well for players late in the game.

Re: Coding assistants are solving the wrong problem

#46

Post by voiper1 »

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.

Re: Coding assistants are solving the wrong problem

#47

Post by CatMustard »

ozlikethewizard wrote: post #33
mirsadm wrote: post #26

Earlier quoted context omitted.

I use Claude Code a lot but one thing that really made me concerned was when I asked it about some ideas I have had which I am very familiar with. It's response was to constantly steer me away from what I wanted to do towards something else which was fine but a mediocre way to do things. It made me question how many times I've let it go off and do stuff without checking it thoroughly.

Call me a conspiracy theorist, and granted much of this could be attributed to the fact that the majority of code in existence is shit, but im convinced that these models are trained and encouraged to produce code that is difficult for humans to work on. Further driving and cementing the usage of then when you inevitably have to come back and fix it.

This could be the case even without an intentional conspiracy. It's harder to give negative feedback to poor quality code that's complicated vs. poor quality code that's simple.

Hence the feedback these models get could theoretically funnel them to unnecessarily complicated solutions.

No clue has any research been done into this, just a thought OTTOMH.

Re: Coding assistants are solving the wrong problem

#48

Post by dboreham »

WD-42 wrote: post #8
monero-xmr wrote: post #2

First you must accept that engineering elegance != market value. Only certain applications and business models need the crème de le crème of engineers. LLM has been hollowing out the mid and lower end of engineering. But has not eroded highest end. Otherwise all the LLM companies wouldn’t pay for talent, they’d just use their own LLM.

I keep hearing this but I don’t understand. If inelegant code means more bugs that are harder to fix later, that translates into negative business value. You won’t see it right away which is probably where this sentiment is coming from, but it will absolutely catch up to you. Elegant code isn’t just for looks. It’s code that can still adapt weeks, months, years after it has shipped and created “business value”.

Perhaps this was never actually true. Did anyone do an A/B test with messy code vs beautiful code?

Re: Coding assistants are solving the wrong problem

#49

Post by grey-area »

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…

It will not in fact always do what you ask it because it lacks any understanding, though the chat interface and prolix nature of LLMs does a good job at hiding that.

Re: Coding assistants are solving the wrong problem

#50

Post by bonesss »

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…

> AI can write the code, but it doesn't refuse to write the code without first being told why it wouldn't be a better idea to…

LLMs combine two dangerous traits simultaneously: they are non-critical about suboptimal approaches and they assist unquestioningly. In practice that means doing dumb things a lazy human would refuse because they know better, and then following those rabbit holes until they run out of imaginary dirt.

My estimation is that that combination undermines their productivity potential without very structured application. Considering the excess and escalating costs of dealing with issues as they arise further from the developers work station (by factors of approximately 20x, 50x, and 200x+ as you get out through QA and into customer environments (IIRC)), you don’t need many screw ups to make the effort net negative.

Post reply on HN