90% of Claude-linked output going to GitHub repos w <2 stars • Hacker News Board

Re: 90% of Claude-linked output going to GitHub repos w <2 stars

#21

Post by phantomCupcake » Wed, Mar 25, 2026, 9:05 PM UTC

embedding-shape wrote: post #5

I'd betcha a lot more than 90% goes to repositories without any stars at all, or even public code!

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.

Re: 90% of Claude-linked output going to GitHub repos w <2 stars

#22

Post by throwaway27448 » Wed, Mar 25, 2026, 9:05 PM UTC

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.

Re: 90% of Claude-linked output going to GitHub repos w <2 stars

#23

Post by phantomCupcake » Wed, Mar 25, 2026, 9:06 PM UTC

louiereederson wrote: post #2

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

Thanks for starting the conversation and sharing my dashboard. :)

Re: 90% of Claude-linked output going to GitHub repos w <2 stars

#24

Post by anon7000 » Wed, Mar 25, 2026, 9:08 PM UTC

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.

Re: 90% of Claude-linked output going to GitHub repos w <2 stars

#25

Post by phantomCupcake » Wed, Mar 25, 2026, 9:09 PM UTC

maxbeech wrote: post #20

[flagged]

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.

Re: 90% of Claude-linked output going to GitHub repos w <2 stars

#26

Post by wetoastfood » Wed, Mar 25, 2026, 9:16 PM UTC

tlogan wrote: post #18

Aurornis wrote: post #11

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.

The actual number is that 98% have less than 2 stars (0 or 1). About 90.25% has zero stars.

How do you know that?

Re: 90% of Claude-linked output going to GitHub repos w <2 stars

#27

Post by thorum » Wed, Mar 25, 2026, 9:18 PM UTC

throwaway27448 wrote: post #22

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.

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.

Re: 90% of Claude-linked output going to GitHub repos w <2 stars

#28

Post by ramoz » Wed, Mar 25, 2026, 9:18 PM UTC

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/

Re: 90% of Claude-linked output going to GitHub repos w <2 stars

#29

Post by zadikian » Wed, Mar 25, 2026, 9:19 PM UTC

throwaway27448 wrote: post #22

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.

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.

Re: 90% of Claude-linked output going to GitHub repos w <2 stars

#30

Post by ttul » Wed, Mar 25, 2026, 9:22 PM UTC

Aurornis wrote: post #11

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.

Yeah. Most of my public repos have 0 stars. Most of what I write sucks.