[HN Gopher] 90% of Claude-linked output going to GitHub repos w ...
___________________________________________________________________
90% of Claude-linked output going to GitHub repos w <2 stars
Author : louiereederson
Score : 107 points
Date : 2026-03-25 18:16 UTC (4 hours ago)
(HTM) web link (www.claudescode.dev)
(TXT) w3m dump (www.claudescode.dev)
| louiereederson wrote:
| Toggling the stars shows 50b lines of code created across all
| projects, only 5b on projects with 2+ stars since Claude Code
| launch. Kind of eye opening where these Claude Code tokens are
| going.
|
| Came across this from this ShowHN post yesterday
| https://news.ycombinator.com/item?id=47501348
| phantomCupcake wrote:
| Thanks for starting the conversation and sharing my dashboard.
| :)
| louiereederson wrote:
| I hope you don't mind, I thought this was a really valuable
| dashboard.
| phantomCupcake wrote:
| Not at all! The ShowHN didn't really get a lot of feedback
| but this thread has already given me a lot to think about
| adding/improving.
| tombert wrote:
| I mean, most of the code that I have written to Github with
| normal human intelligence also goes to Github repos will less
| than two stars. They're usually repos that I create and no one
| else touches.
| embedding-shape wrote:
| I'd betcha a lot more than 90% goes to repositories without any
| stars at all, or even public code!
| phantomCupcake wrote:
| Absolutely! I think the real stats will far exceed what we can
| see on public GitHub. That said, going through some of the top
| "performers" by commit and line count - I am surprised by how
| many people have all their code in public repos.
| xnyan wrote:
| I have many GH repos, most have no stars. Probably because most
| of what I write is not very useful to other people due to quality
| or use case. I would say this is true of most fully human-created
| repos on GitHub.
| furyofantares wrote:
| 100% of all code I have put on github, using claude or not, is on
| repos with zero stars.
| user3939382 wrote:
| At a glance this may read as "most of this code isn't valuable to
| others" but reality is probably complected with "this type of
| code is reducing the need for shared libraries".
| Vektorceraptor wrote:
| guilty :) 1 Star here - and even that is worthless
| Aurornis wrote:
| Perfect example of a base rate fallacy -
| https://en.wikipedia.org/wiki/Base_rate_fallacy
|
| What percentage of GitHub activity goes to GitHub repos with less
| than 2 stars? I would guess it's close to the same number.
| levocardia wrote:
| My reaction as well -- I have a few dozen public repos of 100%
| human-written code, most are 0 stars!
| nickcw wrote:
| The first thing I do when I make a new repo is star it myself
| ;-)
| Imustaskforhelp wrote:
| https://knowyourmeme.com/memes/obama-awards-obama-a-medal
| sleepybrett wrote:
| I have a few dozen org repos, of course none of them have
| stars, who stars their corporate repos?
| tlogan wrote:
| The actual number is that 98% have less than 2 stars (0 or 1).
| About 90.25% has zero stars.
| wetoastfood wrote:
| How do you know that?
| tlogan wrote:
| https://ghe.clickhouse.tech/
| Bratmon wrote:
| Wait, you just answered a completely different question and
| pretended it was relevant!
|
| I can play that game too: The average elephant eats 500
| pounds of vegetation a day, therefore most AI interaction on
| Github is fake.
| ZeWaka wrote:
| I think this is useful in answering the grandparent comment's
| question:
|
| stars : uniq(k)
|
| 1 : 14946505
|
| 10 : 1196622
|
| 100 : 213026
|
| 1000 : 28944
|
| 10000 : 1847
|
| 100000 : 20
| ttul wrote:
| Yeah. Most of my public repos have 0 stars. Most of what I
| write sucks.
| Joel_Mckay wrote:
| Yeah, but knowing something sucks means you are probably
| reasonably competent at coding. =3
|
| https://en.wikipedia.org/wiki/Dunning%E2%80%93Kruger_effect
| strongly-typed wrote:
| Doesn't matter if the recruiter doesn't call you back
| because you're not a 1000x engineer.
| racl101 wrote:
| +1 star for ttul
| runarberg wrote:
| There is still a sampling bias if you compare blanket human
| written repos. I would guess people are far more likely to
| share their homework assignments, experiments, hackathon
| results, weekend toys, etc. as a public repo if they put some
| amount of work into it. I would guess minority of those would
| get any stars at all. If the whole thing was generated by AI in
| less then 20 minutes, I would guess they are more likely to
| simply throw it away when they are done with it.
|
| Personally I think comparing github stars is always going to be
| a fraught metric.
| zahrevsky wrote:
| Off topic, but it reminds me of another principle: every
| geographic heatmap is just a population map.
| https://xkcd.com/1138/
| louiereederson wrote:
| True it is a bit of a sensationalist title, but the implication
| is probably directionally right, and at the very least raises
| further questions.
|
| Check out the largest projects by commits and LOC. These are
| huge projects, and for the most part they have 0 stars, 0
| people watching and 0 forks. You'd think for that level of
| output these signals (however weak) would show some traction.
| Someone pointed to the Broadway ratings aggregator with 24m
| lines of code earlier - there seem to be a bunch of examples
| like this. The 11m line me_theory_simulation repo by
| lizthedeveloper of the multiverse school is also interesting.
|
| All of this together potentially paints a picture that the
| spike in Claude usage is tied to low attention but high LOC
| repos. This is fine, but it also means Claude Code usage might
| overstate the sustainable technological/economic impact that is
| occurring as a result of the product today. Also leads to
| question on sustainability of Claude Code usage given this
| stuff costs real money.
| Computer0 wrote:
| I have a star on one of my repos. Almost all of my work is only
| relevant to me or is internal to my org.
| mikkupikku wrote:
| Maybe because people are using claude to to write code for
| themselves, to scratch their own itch, and upload it to the world
| just because. The value of code can't be measured in star counts.
| dev_l1x_be wrote:
| Did we democratise software engineering? Seriously, I created a
| bunch of tools that I find useful without the bloated framework
| issues that are present in software nowadays. Jokes on me if
| something does not work.
| heliumtera wrote:
| Software production yes engineering no lol
| chrisweekly wrote:
| Even if that stat were compared directly to the base rate (human
| output), it could easily be explained by correlating strongly
| with Claude usage skewing towards new repos.
| maxbeech wrote:
| the more interesting signal in that data is about intent, not
| quality. most of these low-star repos probably aren't failed open
| source attempts - they're personal tools that were never meant to
| be shared.before ai-assisted coding, the effort-to-build ratio
| was high enough that most personal scripts stayed on a laptop or
| in a private gist. pushing to a public repo implied an implicit
| claim that someone else might want this. now the build cost is
| low enough that people just push things to git for their own
| version history and move on.what's actually happening is that git
| is becoming a personal dev journal as much as a collaboration
| platform. stars were always a weak proxy for value, but they're
| especially wrong for this use case.the 90% number probably also
| undercounts the real extent of this - most serious claude code
| usage is on private repos and internal tooling that never touches
| public github at all. the 50b lines stat would look very
| different if you could see total token output vs just github-
| public-linked output.
| phantomCupcake wrote:
| It would be very interesting to see how much of this is the
| "audience of one" type of project - i.e. personal scripts - vs
| new developers/vibe coders trying to start an app. I have
| definitely been surprised by the scale of some of the repos
| that seem to be vibe-coded. People who seem to have no history
| in development are building game engines, and payroll systems,
| and Broadway review websites.
|
| Unfortunately that type of analysis would take a bit more work,
| but I think the repo info and commit messages could probably be
| used to do that.
| throwaway27448 wrote:
| Do people really put weight in stars? It seems completely
| unrelated to anything but, well, popularity. Even when I modify
| other peoples' code I fork to a private repo and maintain my
| changes separately, and I'm fairly certain I have _never_ starred
| a repo.
| thorum wrote:
| Stars have been useless as signals for project quality for a
| while. They're mostly bought, at this point. I regularly see
| obviously vibe-coded nonsense projects on GitHub's Trending
| page with 10,000 stars. I don't believe 10,000 people have even
| cloned the repo, much less gotten any personal value from it.
| It's meaningless.
| zadikian wrote:
| I've seen people "buy" stars enough not to look at them so
| closely. Maybe will consider whether it has 0-1 or 2-2M.
| robarr wrote:
| For example, it's used as a kind of internal bookmarking
| system. I don't necessarily star a repo because I think it has
| good code, but maybe a good idea or something related to
| something I'm interested in developing.
| ianbutler wrote:
| Maybe not to devs, but I've had VCs ask about them because of
| popularity so there you go it's a signal to someone.
|
| Whatever reaction you have to this know that my internal
| reaction and yours were probably close.
| ModernMech wrote:
| Probably not today, but there was a time when you could get
| funding based on just a github repo with a bunch of stars.
| anon7000 wrote:
| The HN headline is at least misleading, because I suspect a
| majority of Claude usage is at the enterprise level (deep
| pockets), which goes to private GitHub repos.
| ramoz wrote:
| Shout out to Broadwayscore by thomaspryor@github
|
| At 2mo old - nearly a 1GB repo, 24M loc, 52K commits
|
| https://github.com/thomaspryor/Broadwayscore
|
| Polished site:https://broadwayscorecard.com/
| mjr00 wrote:
| I was really confused how this could be possible for such a
| seemingly simple site but it looks like it's storing + writing
| many new commits every time there's a new review, or new
| financial data, or a new show, etc.
|
| Someone might want to tell the author to ask Claude what a
| database is typically used for...
| a-dub wrote:
| json in git for reference data actually isn't terrible.
| having it with the code isn't great, and the repo is
| massively bloated in other ways, but for change tracking a
| source of truth, not bad except for maybe it should be
| canonicalized.
| madrox wrote:
| Already enough comments about base rate fallacy, so instead I'll
| say I'm worried for the future of GitHub.
|
| Its business is underpinned by pre-AI assumptions about usage
| that, based on its recent instability, I suspect is being
| invalidated by surges in AI-produced code and commits.
|
| I'm worried, at some point, they'll be forced to take an
| unpopular stance and either restrict free usage tiers or restrict
| AI somehow. I'm unsure how they'll evolve.
| hungryhobbit wrote:
| Or they'll just keep forcing policies that let them steal the
| code you post on GitHub (for their AI training), and make
| everyone leave that way.
| phantomCupcake wrote:
| This.
|
| But also, GitHub profiles and repos were at one point a window
| into specific developers - like a social site for coders. Now
| it's suffering from the same problem that social media sites
| suffer from - AI-slop and unreliable signals about developers.
| Maybe that doesn't matter so much if writing code isn't as
| valuable anymore.
| louiereederson wrote:
| The instability is related to their Azure migration isn't it?
| Cynically you could say it hasn't been helped by the rolling
| RIFs at Microsoft
| madeofpalk wrote:
| Does anyone actually know? So far I've just seen people
| guessing, and seeing that repeated.
| pojzon wrote:
| I dont believe sudden influx of few million bots running
| 24/7 generating PRa and commits and invoking actions does
| not impact GitHub.
|
| It even sounds silly when you say it this way.
| progmetaldev wrote:
| I keep hearing this, and I know Azure has had some issues
| recently, but I rarely have an issue with Azure like I do
| with GitHub. I have close to 100 websites on Azure, running
| on .NET, mostly on Azure App Service (some on Windows 2016
| VMs). These sites don't see the type of traffic or amount of
| features that GitHub has, but if we're talking about Azure
| being the issue, I'm wondering if I just don't see this
| because there aren't enough people dependent on these sites
| compared to GitHub?
|
| Or instead, is it mistakes being made migrating to Azure,
| rather than Azure being the actual problem? Changing
| providers can be difficult, especially if you relied on any
| proprietary services from the old provider.
| petcat wrote:
| In a (possibly near) future where most new code is generated by
| AI bots, the code itself becomes incidental/commodotized and
| it's nothing more than an intermediate representation (IR) of
| whatever solution it was prompt-engineered to produce. The
| value will come from the proposals, reviews, and specifications
| that caused that code to be produced.
|
| Github is still code-centric with issues and discussions being
| auxilliary/supporting features around the code. At some point
| those will become the frontline features, and the code will
| become secondary.
| philipp-gayret wrote:
| Having managed GitHub enterprises for thousands of developers
| who will ping you at the first sign of instability.. I can tell
| you there has not been one year pre-AI where GitHub was fully
| "stable" for a month or maybe even a week, and except for that
| one time with Cocoapods that downtime has always been their own
| doing.
| ekjhgkejhgk wrote:
| Fuck GitHub. It's a corporate attempt at owning git by
| sprinkling socials on top. I hope it fails.
|
| If you need to host git + a nice gui (as opposed to needing to
| promote your shit) Forgejo is free software.
| theteapot wrote:
| Why is this interesting?
| Joel_Mckay wrote:
| The LLM content piracy to isomorphic plagiarism business loop
| is unsustainable. Yet for context search it is reasonably
| useful. =3
|
| https://www.youtube.com/watch?v=T4Upf_B9RLQ
| mrlonglong wrote:
| Codeberg if you hate AI.
| echelon wrote:
| I wonder if there's a critical failure mode / safety feature of
| our species for some percentage of the population to always
| dislike whatever some other large percentage of the population
| likes.
|
| As if it's to prevent the species from over-indexing on a
| particular set of behaviors.
|
| Like how divisive films such as "Signs", "Cloud Atlas", and
| even "The Last Jedi" are loved by some and utterly reviled by
| others.
|
| While that's kind of a silly case, maybe it's not just some
| random statistical fluke, but actually a function of the
| species at a population level to keep us from over-indexing and
| suboptimizing in some local minima or exploring some dangerous
| slope, etc.
| hk1337 wrote:
| How long does it normally take projects to get stars though?
| You're not going to have a project with 100+ stars overnight or
| even within a month, you have to promote the project?
| JanisErdmanis wrote:
| Depends widely on the target audience. In my case, targeting
| Julia developers who want to package their applications into
| installers to reach 100 stars took 2 years -
| https://peacefounder.org/AppBundler.jl. If I were to target
| Python developers, I would have many more stars.
| ModernMech wrote:
| It depends on how much you promote your repo and how big it is.
| I know when my repo gets posted somewhere because I'll get a
| little burst of stars for a few days and then it'll calm down
| until it's posted somewhere again. Much larger repos will get
| stars at a more constant rate as they reach a critical liftoff
| velocity.
| monster_truck wrote:
| I cannot understate how much of an improvement that is. If I had
| a dollar for all the shit I made myself, the old fashioned way,
| that got 0 attention at all? I'd have enough for a month or two
| of claude
| adhipg wrote:
| Isn't that expected as well?
|
| The idea with Claude writing code for most part is that everyone
| can write software that they need. Software for the audience of
| one. GitHub is just a place for them to live beyond my computer.
|
| Why will I want to promote it or get stars?
| bredren wrote:
| Some of the comments point toward genuine concern, some smell of
| gatekeeping.
|
| It is interesting to see a flip in attitude toward GitHub.
| largbae wrote:
| What percentage of non-Claude-linked output hours to repos with
| <2 stars?
| sy26 wrote:
| embarrassing
___________________________________________________________________
(page generated 2026-03-25 23:00 UTC)