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

How I'm Productive with Claude Code

neilkakkar.com

Post reply on HN
Print view View original

181–190 of 192 posts

Re: How I'm Productive with Claude Code

#181

Post by coldtea »

williamcotton wrote: post #50
aguimaraes1986 wrote: post #11

This is the "lines of code per week" metric from the 90s, repackaged. "I'm doing more PRs" is not evidence that AI is working, it's evidence that you are merging more. Whether thats good depends entirely on what you are merging. I use AI every day too. But treating throughput of code going to production as a success metric, without any mention of quality, bugs, or maintenance burden is exactly the kind of thinking de…

Lines of code are meaningful when taken in aggregate and useless as a metric for an individual’s contributions. COCOMO, which considers lines of code, is generally accepted as being accurate (enough) at estimating the value of a software system, at least as far as how courts (in the US) are concerned. https://en.wikipedia.org/wiki/COCOMO

>at least as far as how courts are concerned.

Courts would be the last place to understand something like code quality or software project value....

Re: How I'm Productive with Claude Code

#182

Post by jwpapi »

neilkakkar wrote: post #158
jwpapi wrote: post #57

I have a little ai-commit.sh as "send" in package.json which describes my changes and commits. Formatting has been solved by linters already. Neither my approach nor OP approach are ground-breaking, but i think mine is faster, you also !p send (p alias pnpm) inside from claude no need for it to make a skill and create overhead.. Like thinking about it a pr skill is pretty much an antipattern even telling ai to just c…

OP here, I disagree, it's great to have a skill for cases where you have extra steps and want the agent to run some verification steps before making a PR. It's called making a PR, but it's not _just_ running the gh cli to make a PR. It's checking if I'm in a worktree, renames branches accordingly, adds a linear ticket if provided, generates a proper PR summary. I'm not optimising for how fast the PR is created, I wan…

I have cli script for that as well.

I have a cli script(wtq) that takes whatever is in my clipboard, creates a new worktree, cds into that worktree, installs dependencies, and then starts a claude session with the query in my clipboard. Once im done i can rune `wtf` and it it does the finish up work you described.

It’s not about the workflow. A skill doesn’t make sense when you have a deterministic describable workflow, it’s just slower, because you have an interpretation and consuming step in there.

You can just tell claude to turn the skill into a bash script and then alias it to whatever you like.

A skill is useful if you have a variety of use cases that need to be interepretated and need a lot of the same utility.

Re: How I'm Productive with Claude Code

#183

Post by sarchertech »

brabel wrote: post #179
sarchertech wrote: post #177

Earlier quoted context omitted.

COCOMO has been shown to be inaccurate numerous times. Google it. Here’s one result. “A very high MMRE (1.00) indicates that, on average, the COCOMO model misses about 100% of the actual project effort. This means that the estimate generated by the model can be double or even greater than the actual effort. This shows that the COCOMO model is not able to provide estimates that are close to the actual value.” No one i…

> No one in the industry has taken COCOMO seriously for nearly 2 decades. The funny thing is that we've just discussed how people do take it seriously. It's just that you don't like that. And what do you offer as an alternative? Like I said, vibes. You think that the value of some software is something you can only "feel". That's not how an engineer thinks. If you're engineer you should know that if you can't measure…

I don’t know what to tell you. All the evidence says COCOMO is too inaccurate to use. Show me evidence that says it’s accurate.

Just because someone wrote a book and a few bankruptcy trustees used it doesn’t magically make it accurate. Just because something is systematic doesn’t mean it’s worth using.

If you do a bit of googling you’ll find that the majority of studies show that systemic models don’t outperform expert guesses. So yep vibes are general just as good.

Show me a large tech company that currently uses COCOMO to plan software projects.

Also if you are a dev outside of NASA or another safety critical industry and you think you’re an engineer, you’re kidding yourself.

Oh and try not to sound like an asshole next time.

Re: How I'm Productive with Claude Code

#184

Post by Mrngl1991 »

aguimaraes1986 wrote: post #11

This is the "lines of code per week" metric from the 90s, repackaged. "I'm doing more PRs" is not evidence that AI is working, it's evidence that you are merging more. Whether thats good depends entirely on what you are merging. I use AI every day too. But treating throughput of code going to production as a success metric, without any mention of quality, bugs, or maintenance burden is exactly the kind of thinking de…

[dead]

Re: How I'm Productive with Claude Code

#185

Post by neilkakkar »

jwpapi wrote: post #182
neilkakkar wrote: post #158

Earlier quoted context omitted.

OP here, I disagree, it's great to have a skill for cases where you have extra steps and want the agent to run some verification steps before making a PR. It's called making a PR, but it's not _just_ running the gh cli to make a PR. It's checking if I'm in a worktree, renames branches accordingly, adds a linear ticket if provided, generates a proper PR summary. I'm not optimising for how fast the PR is created, I wan…

I have cli script for that as well. I have a cli script(wtq) that takes whatever is in my clipboard, creates a new worktree, cds into that worktree, installs dependencies, and then starts a claude session with the query in my clipboard. Once im done i can rune `wtf` and it it does the finish up work you described. It’s not about the workflow. A skill doesn’t make sense when you have a deterministic describable workfl…

I see what you mean - I have a setup-worktree script that does this, but I use the skill for knowing when to do bits and pieces. I would agree, if it were 100% deterministic script is much better.

Re: How I'm Productive with Claude Code

#187

Post by theAurenVale »

tbh the real productivity gain for me is iteration count. before id try maybe 2-3 approaches before shipping something. now i can test 10 diffrent implementations in the same window. code quality doesnt always go up but i understand the problem space alot better by the time im done

Re: How I'm Productive with Claude Code

#188

Post by theAurenVale »

the real bottleneck isnt writing code its knowing what to write. every productivity article about AI tools measures output volume but nobody seems to be asking whether the things being built faster are actualy the right things. ive been building a side project and honestly the hardest part is still deciding what matters, the AI just helps me iterate on that decision faster

Re: How I'm Productive with Claude Code

#190

Post by marvec »

How about "time to the first paying user" metric? Parallelism could slow that down. Or even "lines of code per paying user"? Or just a user... It is not an art to agent-code a ton of code. It is an art to land just the few ones that are a must for a good MVP.
Post reply on HN