Live data from Hacker News

The highest quality codebase

gricha.dev

51–60 of 409 posts

Re: The highest quality codebase

#51
post #44
post #26

Earlier quoted context omitted.

Not at all my experience. I’ve often tried things like telling Claude this SIMD code I wrote performed poorly and I needed some ideas to make it go faster. Claude usually does a good job rewriting the SIMD to use different and faster operations.

That sounds like a pretty "structured" problem to me.

that's one of the problems with AI. as it can accomplish more tasks people will overestimate it's ability.

what the person you replied to had claude do is relatively simple and structured, but to that person what claude did is "automagic".

People already vastly overestimate AI's capabilities. This contributes to that.

Re: The highest quality codebase

#52
Just the headline sounds like a YouTube brain rot video title:

"I spent 200 days in the woods"

"I Google translated this 200 times"

"I hit myself with this golf club 200 times"

Is this really what hacker news is for now?

Re: The highest quality codebase

#53

lol 5000 tests. Agentic code tools have a significant bias to add versus remove/condense. This leads to a lot of bloat and orphaned code. Definitely something that still needs to be solved for by agentic tools.

Oh I’ve had agents remove tests plenty of times. Or cripple the tests so they pass but are useless - more common and harder to prompt against.

Re: The highest quality codebase

#54
post #43

Claude is really good at specific analysis, but really terrible at open-ended problems. "Hey claude, I get this error message: ", and it'll often find the root cause quicker than I could. "Hey claude, anything I could do to improve Y?", and it'll struggle beyond the basics that a linter might suggest. It suggested enthusiastically a library for and it was all " Recommended " about it, but when I pointed out that the…

That's why you treat it like a junior dev. You do the fun stuff of supervising the product, overseeing design and implementation, breaking up the work, and reviewing the outputs. It does the boring stuff of actually writing the code. I am phenomenally productive this way, I am happier at my job, and its quality of work is extremely high as long as I occasionally have it stop and self-review it's progress against the…

I think we have different opinions on what's fun and what's boring!

Re: The highest quality codebase

#55
post #43

Claude is really good at specific analysis, but really terrible at open-ended problems. "Hey claude, I get this error message: ", and it'll often find the root cause quicker than I could. "Hey claude, anything I could do to improve Y?", and it'll struggle beyond the basics that a linter might suggest. It suggested enthusiastically a library for and it was all " Recommended " about it, but when I pointed out that the…

That's why you treat it like a junior dev. You do the fun stuff of supervising the product, overseeing design and implementation, breaking up the work, and reviewing the outputs. It does the boring stuff of actually writing the code. I am phenomenally productive this way, I am happier at my job, and its quality of work is extremely high as long as I occasionally have it stop and self-review it's progress against the…

Maybe I'm weird but I enjoy "actually writing the code."

Re: The highest quality codebase

#56
post #11
post #4

This is a great example of there being no intelligence under the hood.

Would a human perform very differently? A human who must obey orders (like maybe they are paid to follow the prompt). With some "magnitude of work" enforced at each step. I'm not sure there's much to learn here, besides it's kinda fun, since no real human was forced to suffer through this exercise on the implementor side.

No (human) developer would _add_ tests. ^/s

Re: The highest quality codebase

#57

Well of course it produced bad results... it was given a bad prompt. Imagine how things would have turned out if you had given the same instructions to a skilled but naive contractor who contractually couldn't say no and couldn't question you. Probably pretty similar.

Yeah I don't see the utility in doing this hundreds of times back to back. A few iterations can tell us some things about how Claude optimizes code, but an open ended prompt to endlessly "improve" the code sounds like a bad boss making huge demands. I don't blame the AI for adding BS down the line.

Re: The highest quality codebase

#58
post #52

Just the headline sounds like a YouTube brain rot video title: "I spent 200 days in the woods" "I Google translated this 200 times" "I hit myself with this golf club 200 times" Is this really what hacker news is for now?

If you reverse the order this could be a very interesting Youtube series

Re: The highest quality codebase

#59
post #43

Earlier quoted context omitted.

That's why you treat it like a junior dev. You do the fun stuff of supervising the product, overseeing design and implementation, breaking up the work, and reviewing the outputs. It does the boring stuff of actually writing the code. I am phenomenally productive this way, I am happier at my job, and its quality of work is extremely high as long as I occasionally have it stop and self-review it's progress against the…

Maybe I'm weird but I enjoy "actually writing the code."

Me writing code is me spending 3/4 of my time wading through documentation and google searches. It's absolutely hell on my ADD. My ability to memorize is absolutely garbage. Throughout my career I've worked in like 10 different languages, and in any given project I'm usually working in at least 3 or 4. There's a lot of "now what is a map operation in this stupid fucking language called again?!"

Claude writing code gets the same output if not better in about 1/10 of the time.

That's where you realize that the writing code bits are just one small part of the overall picture. One that I realize I could do without.

Re: The highest quality codebase

#60
post #52

Just the headline sounds like a YouTube brain rot video title: "I spent 200 days in the woods" "I Google translated this 200 times" "I hit myself with this golf club 200 times" Is this really what hacker news is for now?

There are fundamental differences. Many people expect a positive gradient of quality from AI overhaul of projects. For translating back and forth, it is obvious from the outset that there is a negative gradient of quality (the Chinese whispers game).
Post reply on HN