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

51–60 of 151 posts

Re: Coding assistants are solving the wrong problem

#51

Post by xgb84j »

mirsadm wrote: post #26
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…

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.

Mediocre is fine for many tasks. What makes a good software engineer is that he spots the few places in every software where mediocre is not good enough.

Re: Coding assistants are solving the wrong problem

#52

Post by viraptor »

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.

Re: Coding assistants are solving the wrong problem

#53

Post by fpoling »

I have found that using Cursor to write in Rust what I previously would write as a shell or Python or jq script was rather helpful.

The datasets are big and having the scripts written in the performant language to process them saves non-trivial amounts of time, like waiting just 10 minutes versus an hour.

Initial code style in the scripts was rather ugly with a lot of repeated code. But with enough prompting that I reuse the generated code became sufficiently readable and reasonable to quickly check that it is indeed doing what was required and can be manually altered.

But prompting it to do non-trivial changes to existing code base was a time sink. It took too much time to explain/correct the output. And critically the prompts cannot be reused.

Re: Coding assistants are solving the wrong problem

#54

Post by geraneum »

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”.

People sometimes conflate inelegance with buggy code, where the market fit and value matter more than code elegance. Bugs still are not acceptable even in your MVP. Actually I think buggy software especially if those bugs destroy user experience, will kill products. It’s not 2010 anymore. There are a lot of less buggy software out there and attention spans are narrower than before.

edit: typo

Re: Coding assistants are solving the wrong problem

#56

Post by Perz1val »

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.

It is a mathematical, averaging model after all

Re: Coding assistants are solving the wrong problem

#57

Post by rcarmo »

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”.

Re: Coding assistants are solving the wrong problem

#58

Post by fragmede »

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.

To be fair, they're primed to write code, even when you don't ask for it. I explicitly tell Claude "do not write code" when I don't want any, otherwise it'll spit some out just to say hello (world).

Re: Coding assistants are solving the wrong problem

#60

Post by freehorse »

fragmede wrote: post #58
viraptor wrote: post #52

Earlier quoted context omitted.

> 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.

To be fair, they're primed to write code, even when you don't ask for it. I explicitly tell Claude "do not write code" when I don't want any, otherwise it'll spit some out just to say hello (world).

"Here is some python code that printf's the travel recommendations you asked for, btw"
Post reply on HN