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

41–50 of 409 posts

Re: The highest quality codebase

#41

Post by thewebguyd »

james_marks wrote: post #29
xnorswap wrote: post #18

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…

This is a key part of the AI love/hate flame war. Very easy to write it off when it spins out on the open-ended problems, without seeing just how effective it can be once you zoom in. Of course, zooming in that far gives back some of the promised gains. Edit: typo

> without seeing just how effective it can be once you zoom in.

The love/hate flame war continues because the LLM companies aren't selling you on this. The hype is all about "this tech will enable non-experts to do things they couldn't do before" not "this tech will help already existing experts with their specific niche," hence the disconnect between the sales hype and reality.

If OpenAI, Anthropic, Google, etc. were all honest and tempered their own hype and misleading marketing, I doubt there would even be a flame war. The marketing hype is "this will replace employees" without the required fine print of "this tool still needs to be operated by an expert in the field and not your average non technical manager."

Re: The highest quality codebase

#42

Post by fudged71 »

xnorswap wrote: post #18

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…

This tells me that we need to build 1000 more linters of all kinds

Re: The highest quality codebase

#43

Post by pdntspa »

xnorswap wrote: post #18

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 style principles articulated in its AGENTS.md file. (As it tends to forget a lot of rules like DRY)

Re: The highest quality codebase

#44

Post by zahlman »

kccqzy wrote: post #26
xnorswap wrote: post #18

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…

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.

Re: The highest quality codebase

#45

Post by hombre_fatal »

james_marks wrote: post #29
xnorswap wrote: post #18

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…

This is a key part of the AI love/hate flame war. Very easy to write it off when it spins out on the open-ended problems, without seeing just how effective it can be once you zoom in. Of course, zooming in that far gives back some of the promised gains. Edit: typo

Go one level up:

    claude2() {
      claude "$(claude "Generate a prompt and TODO list that works towards this goal: $*" -p)"
    }

    $ claude2 pls give ranked ideas for make code better

Re: The highest quality codebase

#46

Post by simonw »

The prompt was:

  Ultrathink. You're a principal engineer. Do not ask me any
  questions. We need to improve the quality of this codebase.
  Implement improvements to codebase quality.
I'm a little disappointed that Claude didn't eventually decide to start removing all of the cruft it had added to improve the quality that way instead.

Re: The highest quality codebase

#47

Post by cyral »

xnorswap wrote: post #18

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…

Using the plan mode in cursor (or asking claude to first come up with a plan) makes it pretty good at generic "how can I improve" prompts. It can spend more effort exploring the codebase and thinking before implementing.

Re: The highest quality codebase

#48

Post by hazmazlaz »

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.

Re: The highest quality codebase

#49

Post by mainmailman »

kccqzy wrote: post #26
xnorswap wrote: post #18

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…

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.

I'm not a C++ programmer, but wouldn't your example be a fairly structured problem? You wanted to improve performance of a specific part of your code base.

Re: The highest quality codebase

#50

Post by elzbardico »

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…

Small errors compound over time.
Post reply on HN