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

AI is forcing us to write good code

bits.logic.inc

Post reply on HN
Print view View original

91–100 of 229 posts

Re: AI is forcing us to write good code

#91

Post by johnnyfived »

mkozlows wrote: post #15

I like this. "Best practices" are always contingent on the particular constellation of technology out there; with tools that make it super-easy to write code, I can absolutely see 100% coverage paying off in a way that doesn't for human-written code -- it maximizes what LLMs are good at (cranking out code) while giving them easy targets to aim for with little judgement. (A thing I think is under-explored is how much…

I've said this before here, but "best practices" in code indeed is very typical even with different implementations and architectures. You can ask a LLM to write you the best possible code for a scenario and likely your implementation wouldn't differ much.

Writing, art, creative output, that's nothing at all like code, which puts the software industry in a more particular spot than anything else in automation.

Re: AI is forcing us to write good code

#92

Post by deepsquirrelnet »

Philip-J-Fry wrote: post #81
CharlieDigital wrote: post #70

Earlier quoted context omitted.

What I find works really well: scaffold the method signature and write your intent in the comment for the inputs, outputs, and any mutations/business logic + instructions on approach. LLM has very high chance of on shotting this and doing it well.

This is what I tend to do. I still feel like my expertise in architecting the software and abstractions is like 10x better than I've seen an LLM do. I'll ask it to do X, and then ask it to do Y, and then ask it to do Z, and it'll give you the most junior looking code ever. No real thought on abstractions, maybe you'll just get the logic split into different functions if you're lucky. But no big picture thinking, even…

I think this is my experience as well.

I tend to use a shotgun approach, and then follow with an aggressive refactor. It can actually take a lot of time to prune and restructure the code well. At least it feels slow compared to opening the Claude firehose and spraying out code. There needs to be better tools for pruning, because Claude is not thorough enough.

This seems to work well for me. I write a lot of model training code, and it works really well for the breadth of experiments I can run. But by the end it looks like a graveyard of failed ideas.

Re: AI is forcing us to write good code

#93

Post by zahlman »

CharlieDigital wrote: post #70
danieka wrote: post #60

I thought that the article would be about if we want AI to be effective, we should write good code. What I notice is that Claude stumbles more on code that is illogical, unclear or has bad variable names. For example if a variable is name "iteration_count" but actually contains a sum that will "fool" AI. So keeping the code tidy gives the AI clearer hints on what's going on which gives better results. But I guess tha…

What I find works really well: scaffold the method signature and write your intent in the comment for the inputs, outputs, and any mutations/business logic + instructions on approach. LLM has very high chance of on shotting this and doing it well.

What if I write the main function but stub out calls to functions that don't exist yet; how will it do with inferring what's missing?

Re: AI is forcing us to write good code

#94

Post by joshribakoff »

charcircuit wrote: post #76
sleepy_keita wrote: post #62

Earlier quoted context omitted.

Humans can work with these cases better though because they have access to better memory. Next time you see "iteration_count", you'll know that it actually has a sum, while a new AI session will have to re-discover it from scratch. I think this will only get better as time goes on, though.

You are underestimating how lazy humans can be. Humans are going to skim code, scroll down into the middle of some function and assume iteration count means iteration count. AI on the other hand will have the full definition of the function in its context every time.

You are underestimating the importance of attention. You can have everything in context and still attend to the wrong parts (eg bad names)

Re: AI is forcing us to write good code

#95

Post by firemelt »

yeah beekeeping, I think about it alot, I mean the agentic should be isolated on their own environment, its dangerous to give then ur whole pc who nows they silently putting some rootkit or backdoor to ur pc, like appending allowed ssh keys

Re: AI is forcing us to write good code

#96

Post by zahlman »

marcosdumay wrote: post #71
CuriouslyC wrote: post #49

Earlier quoted context omitted.

Pre-agents, 100% agree. Now, it's not a bad idea, the cost to do it isn't terrible, though there's diminishing returns as you get >90-95%.

LLMs don't make bad tests any less harmful. Nor they write good tests for the stuff people mostly can't write good tests for.

Okay, but is aiming for 100% coverage really why the bad tests are bad?

Re: AI is forcing us to write good code

#97

Post by zahlman »

spc476 wrote: post #75
bdangubic wrote: post #31

Earlier quoted context omitted.

laziness? unprofessionalism? both? or something else?

You forgot difficult. How do you test a system call failure? How do you test a system call failure when the first N calls need to pass? Be careful how you answer, some answers technically fall into the "undefined behavior" category (if you are using C or C++).

... Is that not what mocking is for?

Re: AI is forcing us to write good code

#99

Post by camel_gopher »

frio wrote: post #66
brynary wrote: post #29

Strong agreement with everything in this post. At Qlty, we are going so far as to rewrite hundreds of thousands of lines of code to ensure full test coverage, end-to-end type checking (including database-generated types). I’ll add a few more: 1. Zero thrown errors. These effectively disable the type checker and act as goto statements. We use neverthrow for Rust-like Result types in TypeScript. 2. Fast auto-formatting…

A TypeScript test suite that offers 100% coverage of "hundreds of thousands" of lines of code in under 1 second doesn't pass the sniff test.

Hey now he said 1,000ms, not 1 second

Re: AI is forcing us to write good code

#100

Post by mrtksn »

pgroves wrote: post #44

This is sort of why I think software development might be the only real application of LLMs outside of entertainment. We can build ourselves tight little feedback loops that other domains can't. I somewhat frequently agree on a plan with an LLM and a few minutes or hours later find out it doesn't work and then the LLM is like "that's why we shouldn't have done it like that!". Imagine building a house from scratch and…

> Imagine building a house from scratch

Thats why those Engineering fields have strict rules, often require formal education and someone can even end up in prison if screws up badly enough.

Software is so much easier and safer, till very recently anonymous engineering was the norm and people are very annoyed with Apple pushing for signing off the resulting product.

Highly paid software engineers across the board must have been an anomaly that is ending now. Maybe in the future only those who code actually novel solutions or high risk software will be paid very well - just like engineers in the other fields.

Post reply on HN