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

121–130 of 229 posts

Re: AI is forcing us to write good code

#121

Post by zarzavat »

mrtksn wrote: post #116
zarzavat wrote: post #112

Earlier quoted context omitted.

> people are very annoyed with Apple pushing for signing off the resulting product. Apple is very much welcome to push for signing off of software that appears on their own store. That is nothing new. What people are annoyed about is Apple insisting that you can only use their store, a restriction that has nothing to do with safety or quality and everything to do with the stupendous amounts of money they make from it…

It's literally the case of Apple requiring signing the binary to run on the platforms they provide, Apple doesn't have say on other platforms. It is a very similar situation with local governments. Also, people complain all the time about rules and regulations for making stuff. Especially in EU, you can't just create products however you like and let people decide if it is safe to use, you are required to make your p…

...but the EU is one of the entities forcing Apple to allow other stores.

It turns out that Apple is not, in fact, the government.

Re: AI is forcing us to write good code

#122

Post by teaearlgraycold »

nathan_f77 wrote: post #119

This is exactly how I've been working with AI this year and I highly recommend it. This kind of workflow was not feasible when I was working alone and typing every line of code. Now it's suprisingly easy to achieve. In my latest project, I've enforced extremely strict linting rules and completely banned any ignore comments. No file over 500 lines, and I'm even using all the default settings to prevent complex functio…

I went from "ugh I don't want to write e2e tests" to "well I'll at least have the LLM write some". 50% coverage is way better than 0%! I'm very strict about the runtime code, but let the LLM take the reins on writing tests (of course still reviewing the code).

It's funny how on one side you have people using AI to write worse code than ever, and on the other side people use AI as an extension of their engineering discipline.

Re: AI is forcing us to write good code

#123

Post by charcircuit »

joshribakoff wrote: post #94
charcircuit wrote: post #76

Earlier quoted context omitted.

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)

Improving AI is easier than improving human nature.

Re: AI is forcing us to write good code

#124

Post by zmmmmm »

Very little there about the code itself being good. A lot about putting good guardrails around it and making it fast and safe to develop. Which is good for sure. But I feel it's misconstruing it to say the actual code is "good". The whole reason the guard rails provide value is the code is, by default, "not good" and how good the result is presumably sitting in a spectrum between "the worst possible that satisfies the guardrails" and "actually good".

Re: AI is forcing us to write good code

#125

Post by tempodox »

This is hallucination. Or maybe a sales pitch. If production bugs and the requirement to retain a workable code base don’t get us to write “good” code, then nothing will. And at the current state of the art, “AI” will tend to make it worse.

Re: AI is forcing us to write good code

#127

Post by stackghost »

ogogmad wrote: post #102
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…

> This is sort of why I think software development might be the only real application of LLMs outside of entertainment. Wow. What about also, I don't know, self-teaching*? In general, you have to be very arrogant to say that you've experienced all the "real" applications. * - For instance, today and yesterday, I've been using LLMs to teach myself about RLC circuits and "inerters".

Why would you think that a machine known to cheerfully and confidently assert complete bullshit is suitable to learn from?

Re: AI is forcing us to write good code

#128

Post by baq »

tombert wrote: post #103

Something I just started doing yesterday, and I'm hoping it catches on, is that I've been writing the spec for what I want in TLA+/PlusCal at a pretty high level, and then I tell Codex implement exactly to the spec. I tell it to not deviate from the spec at all, and be as uncreative as possible. Since it sticks pretty close to the spec and since TLA+ is about modifying state, the code it generates is pretty ugly, but…

You might find success with having the LLM contribute to the spec itself. It suddenly started to work with the most recent frontier models, to the point that economics of writing then shifted due to turn getting 10-100x cheaper to get right.

Re: AI is forcing us to write good code

#129

Post by lmeyerov »

Most of this rings true for us for the same reasons. We have been moving large old projects in this direction, and new ones start there. It's easier to do these via tool checks than trust skills files. I wouldn't say the resulting code is good, which folks are stumbling on, but it is rewarding better code - predictable, boring, tested, pure, and fast to iterate on, which are all indeed part of our SDLC principles.

Some of the advice is a bit more extreme, like I haven't found value in 100% code coverage, but 90% is fine. Others miss nuance like we have to work hard to prevent the AI from subverting the type checks, like by default it works around type errors by using getattr/cast/typeignore/Any everywhere.

One item I'm hoping is AI coders get better at is using static analysis tools and verification tools. My experiments here have been lukewarm/bad, like adding an Alloy model checker for some parts of GFQL (GPU graph query language) took a lot of prodding and found no bugs, but straight up asking codex to do test amplification on our unit test suite based on our code and past bugs works great. Likewise, it's easy to make it port conformance tests from standards and help with making our docs executable to help prevent drift.

A new area we are starting to look at is automatic bug patches based on production logs. This is practical for the areas we setup for vibe coding, which in turn are the areas we care about more and work most heavily on. We never trusted automated dependency update bots, but this kind of thing gets much more trustworthy & reviewable. Another thing we are eyeing is new 'teleport' modes so we can shift PRs to remote async development, which previously we didn't think worth supporting.

Re: AI is forcing us to write good code

#130

Post by zwnow »

tempodox wrote: post #125

This is hallucination. Or maybe a sales pitch. If production bugs and the requirement to retain a workable code base don’t get us to write “good” code, then nothing will. And at the current state of the art, “AI” will tend to make it worse.

Shhhh the original poster is the CEO of an AI based company. I am sure there is no bias here. /s
Post reply on HN