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

The highest quality codebase

gricha.dev

Post reply on HN
Print view View original

131–140 of 409 posts

Re: The highest quality codebase

#131

Post by georgemcbay »

FeteCommuniste wrote: post #92
nyadesu wrote: post #67

Earlier quoted context omitted.

In my case, I enjoy writing code too, but it's helpful to have an assistant I can ask to handle small tasks so I can focus on a specific part that requires attention to detail

Yeah, I sometimes use AI for questions like "is it possible to do [x] using library [y] and if so, how?" and have received mostly solid answers.

> Yeah, I sometimes use AI for questions like "is it possible to do [x] using library [y] and if so, how?" and have received mostly solid answers.

In my experience most LLMs are going to answer this with some form of "Absolutely!" and then propose a square-peg-into-a-round-hole way to do it that is likely suboptimal vs using a different library that is far more suited to your problem if you didn't guess the right fit library to begin with.

The sycophancy problem is still very real even when the topic is entirely technical.

Gemini is (in my experience) the least likely to lead you astray in these situations but its still a significant problem even there.

Re: The highest quality codebase

#133

Post by minimaxir »

mvanbaak wrote: post #121
minimaxir wrote: post #110

Earlier quoted context omitted.

It's necessary to allow Claude Code to be fully autonomous, otherwise it will stop and ask you to run commands.

and just letting it to do whatever it thinks it should do, without a human intervening, is a good plan?

Discovering that is the entire intent of this experiment, yes.

Re: The highest quality codebase

#134

Post by g947o »

When I ask coding agents to add tests, they often come up with something like this:

    const x = new NewClass();
    assert.ok(x instanceof NewClass);
So I am not at all surprised about Claude adding 5x tests, most of which are useless.

It's going to be fun to look back at this and see how much slop these coding agents created.

Re: The highest quality codebase

#135

Post by pdntspa »

nottorp wrote: post #104
FeteCommuniste wrote: post #92

Earlier quoted context omitted.

Yeah, I sometimes use AI for questions like "is it possible to do [x] using library [y] and if so, how?" and have received mostly solid answers.

Just be careful if functionality varies between library y version 2 and library y version 3, or if there is a similarly named library y2 that isn't the same. You may get possibilities, but not for what you asked for.

If you run to the point where you can execute each idea and examine its outputs, problems like that surface pretty quickly

Re: The highest quality codebase

#137

Post by skydhash »

stouset wrote: post #115
FeteCommuniste wrote: post #92

Earlier quoted context omitted.

Yeah, I sometimes use AI for questions like "is it possible to do [x] using library [y] and if so, how?" and have received mostly solid answers.

Or “can you prototype doing A via approaches X, Y, and Z, and show me what each looks like?” I love to prototype various approaches. Sometimes I just want to see which one feels like the most natural fit. The LLM can do this in a tenth of the time I can, and I just need to get a general idea of how each approach would feel in practice.

> Sometimes I just want to see which one feels like the most natural fit.

This sentence alone is a huge red flag in my books. Either you know the problem domain and can argue about which solution is better and why. Or you don't and what you're doing are experiment to learn the domain.

There's a reason the field is called Software Engineering and not Software Art. Words like "feels" does not belongs. It would be like saying which bridge design feels like the most natural fit for the load. Or which material feels like the most natural fit for a break system.

Re: The highest quality codebase

#138

Post by tracker1 »

On the Result responses... I've seen this a few times. I think it works well in Rust or other languages that don't have the ability to "throw" baked in. However, when you bolt it on to a language that implicitly can throw, you're now doing twice the work as you have to handle the explicit error result and integrated errors.

I worked in a C# codebase with Result responses all over the place, and it just really complicated every use case all around. Combined with Promises (TS) it's worse still.

Re: The highest quality codebase

#139

Post by Gricha »

dcchuck wrote: post #24

I spent some time last night "over iterating" on a plan to do some refactoring in a large codebase. I created the original plan with a very specific ask - create an abstraction to remove some tight coupling. Small problem that had a big surface area. The planning/brainstorming was great and I like the plan we came up with. I then tried to use a prompt like OP's to improve it (as I said, large surface area so I wanted…

I think I end up doing that with plans inadvertently too. Oftentimes I'll iterate on a plan too many times, and only recognize that it's too far gone and needs a restart with more direction after sinking in 15 minutes into it.

Re: The highest quality codebase

#140

Post by mvanbaak »

minimaxir wrote: post #133
mvanbaak wrote: post #121

Earlier quoted context omitted.

and just letting it to do whatever it thinks it should do, without a human intervening, is a good plan?

Discovering that is the entire intent of this experiment, yes.

fair point. will re-read the whole thing. I'm sorry for my ignorance.
Post reply on HN