Anthropic Reinvents Source Control As Claude Floods the World With Code
- Reference: 0186306098
- News link: https://developers.slashdot.org/story/26/10/14/0244248/anthropic-reinvents-source-control-as-claude-floods-the-world-with-code
- Source link:
> "In May 2026, Anthropic averaged around 2,500 code changes merged per day; as of September, we merged over 30,000 per day," the biz said in a [2]blog post on Tuesday. "We don't expect this rate of growth to slow down anytime soon; the latent demand for merging code is practically infinite, and every bottleneck we remove immediately leads to a further increase in the amount of code we produce."
>
> After several months of model prompting and five months of migration, the result is a homemade version control system called Scion, a monorepo scheme that sounds a bit like Subversion, Apache's centralized version control system. [...] Scion has been designed to meet the needs of AI agents, so the client leaves much of the work to the server; the source control queries are exposed via API so internal tools can respond without needing a local repo, and there's less synchronization but more need for server speed.
>
> "In Scion, the unit of work is a 'changeset,' an entry in a write-ahead log," Anthropic explains. "A changeset stores most of what you'd expect from a commit in git. But where a git commit stores a pointer to the tree, a changeset stores a list of the files that changed relative to its first parent, along with content-addressed pointers to the compressed file contents in blob storage." [...] Anthropic says its bespoke system isn't right for general use. There will be no open source release. Nonetheless, the company contends that its own code scaling problems will become commonplace in other organizations over the next few months, so it wanted to share its approach -- having ample funding to pay for writing custom infrastructure tools.
[1] https://www.theregister.com/devops/2026/10/13/anthropic-reinvents-source-control-as-claude-floods-the-world-with-code/5302943
[2] https://www.anthropic.com/engineering/redesigning-source-control
Infinite LOC (Score:2)
Somewhere a manager just fainted with a big smile on his face.
Re: (Score:3)
Bosses who are deep into AI Psychosis lack the mental capacity to understand that "lines of code" is not a measure you should aim to maximize under any circumstances (other than being paid per line of code by idiots). And AI tools are already very prone to produce vast amounts of repetitive, redundant code lines.
--depth 1 (Score:3)
They don't know how to use git because they are letting claude do everything. Just use '--depth 1' in the CI clones and now git does exactly what they built.
Re:--depth 1 (Score:4, Insightful)
That is not correct. The major difference is that scion is not decentralized. A major problem that Scion introduces is that you can't properly sandbox a development environment, so Scion keeps a major attack vector open. We already know that just giving a model access to an upstream system that has access to the internet can result in sandbox breaking, because it happened in the OpenAI Hugging Face incident. With git you can physically remove and airgap a dev system, but not with Scion. In case I'm not being clear I am saying git --depth 1 is preferable unless they find a hybrid solution that allows Scion to be centralized sometimes but also decentrlized for airgapping purposes. How they might do that is an exercise left to the reader.
Bosses' folly (Score:3)
Nothing gives me more confidence in my boss than when he decides we should reinvent some popular software.
Re:Bosses' folly (Score:5, Insightful)
I mean, that's exactly what Linus did with git. A lot of his criticisms of existing stuff weren't justified (he went on misplaced rants about how version control software was bad in concept for years ), and people have essentially cargo-culted git into areas it wasn't designed for because 'Linus is cool'.
Quick reminder that most commercial software doesn't actually have the problem that git was designed to solve - multiple masters. It was designed to be able to share kernel source trees between Linus' own, Red Hats and I think two others (Yggdrasil and SUSE? It's a long time back and I may be misremembering that). They all had their own quirks and patches, and they wanted to be able to handle commits to any of their trees and accept/reject as per their own preference.
This is pretty much the opposite of what most commercial software wants to do. It wants a single master, with known commits, so that a single known version gets shipped in the end. This is the exact opposite of what git was meant to be, yet it gets used there anyway. I notice the summary talks about a centralised system - yep, that's what you want for commercial, not a distributed multiple master.
Re: (Score:3)
Agreed, and centralized coordination is a HUGE simplifying assumption to the task at hand.
Re:Bosses' folly (Score:4, Informative)
> I mean, that's exactly what Linus did with git. A lot of his criticisms of existing stuff weren't justified (he went on misplaced rants about how version control software was bad in concept for years ), and people have essentially cargo-culted git into areas it wasn't designed for because 'Linus is cool'.
> Quick reminder that most commercial software doesn't actually have the problem that git was designed to solve - multiple masters. It was designed to be able to share kernel source trees between Linus' own, Red Hats and I think two others (Yggdrasil and SUSE? It's a long time back and I may be misremembering that). They all had their own quirks and patches, and they wanted to be able to handle commits to any of their trees and accept/reject as per their own preference.
> [....]
Yggdrasil - that's a name I haven't heard in Linus contect for a long time. However, it was only relevant in the early 90s. Git was developed in early 2005, as a response to the controversy and problems using [1]Bitkeeper [wikipedia.org]: A proprietary distributed version control system that had provided free licenses for developers of free software, but with several caveats that many found unacceptable. In early 2005 the free license was revoked (due various unhappy devs reverse engineering it, IIRC - in particular Andrew Tridgell of Samba fame), and Linus responded by creating git.
For another blast from the past, here's [2]an article about in the Linux Journal [linuxjournal.com].
[1] https://en.wikipedia.org/wiki/BitKeeper
[2] https://www.linuxjournal.com/content/git-origin-story
Re: Bosses' folly (Score:2)
> I mean, that's exactly what Linus did with git. A lot of his criticisms of existing stuff weren't justified (he went on misplaced rants about how version control software was bad in concept for years), and people have essentially cargo-culted git into areas it wasn't designed for because 'Linus is cool'
I think that is a bit revisionist. Linus hated CVS and happily used Bitkeeper as he found it useful. His contention then was that patchsets were superior to CVS. Having never used CVS, I cannot comment on how bad it was, but he put his money where his mouth was and invented Git (after a conflict between Bitkeeper and the open source community resulted in the free license for kernel developers being withdrawn.
In any case, the rapid fall off of CVS and Subversion proved his point.
Re: (Score:2)
It is apparent that you have no idea why Linus developed git. Linus created git because the kernel developers were using bitkeeper for free with permission from BitMover CEO Larry McVoy. Bitkeeper was proprietary code, and Andrew Tridgell reverse engineered the Bitkeeper protocols to create an Open Source version, which was a violation of the licensing terms as McVoy saw it. Linus rightly recognized that the various Open Source solutions were not great. In parallel Mercurial was created as another Distribu
Re: (Score:2)
I'm going back from before he used Bitkeeper. There was a long period of time he didn't want to use source control at all. Bitkeeper wasn't used by him until the 2000s.
Re: (Score:2)
>> Nothing gives me more confidence in my boss than when he decides we should reinvent some popular software.
> I mean, that's exactly what Linus did with git. A lot of his criticisms of existing stuff weren't justified (he went on misplaced rants about how version control software was bad in concept for years), and people have essentially cargo-culted git into areas it wasn't designed for because 'Linus is cool'.
So he re-invented bitkeeper before he even used bitkeeper, after he waited until someone else "reinve
Re: (Score:2)
I don't recall any major distributed version control system before git, other than Bitkeeper. Most people were using things like CVS that required you to checkout/lock files before working on them.
Linus wrote git because Bitkeeper revoked the open source license for it.
Re: (Score:3)
Using AI, especially. One thing that struck me in the last few days was in relation to comments on the story about the person who has used AI to vibe-code clones of part of the Adobe graphical tools suite and has since (within a few days!) gone on to close the core Microsoft Office apps in the same way. Apparently (I have not checked it personally) this software, albeit still in "beta", runs like a bag of spanners and while, it might superficially look like the tools it's emulating, lacks the depth of man
Re: (Score:2)
Everybody wants to make the next new thing. Most people don't want to contribute to the thing that's already developing. That's why we have so many abandoned projects, people try to do the new thing and then find out that it's hard. On the other hand, intelligent people aren't going to take a bunch of uncopyrightable and possibly copyright-poisoned code into their projects, so this AI time can't really help those projects along either. All it can safely be used for is throwaways. Who's going to spend real t
Re: (Score:3)
> But that's exactly what you want The West to do with 3rd worlders...
Every day it becomes clearer that Slashdot's masters B!zX are willfully hosting Nazis and their speech by platforming them and protecting even their assumed identities.
Re: Bosses' folly (Score:4, Insightful)
Fuck off, racist piece of shit.
Re: (Score:2)
I know a team that has gone very hard on slopping it up AI, though they just had a flamewar where the AI bros bitched that the more careful people were holding them back by insisting on human review and rejecting merge requests where the human didn't understand what they were submitting.
The thing is, this team was already pumping out shit code for years, so in their case the AI might actually be compelling. Infested by PHB thinking of 'hire many people in random geography, to change each year as different
Re: (Score:1)
This tends to hint at my fears with AI being locked down and restricted for use. Greed and those holding the worlds largest Patent War Chests will want to Go To War when these beta projects become alpha enough to really start competing and taking market share.
Imagine "Security" and "IP" becoming the reasons AI gets walled off from the masses. Imagine it getting so bad that laws are passed and even those standalone offline AI instances that were legal at one time, are now deemed a major threat. They are o
Re: (Score:2)
Depends. Are you tunnel visioned and can he see a bigger picture? If you jump to conclusions about the fact your boss is deciding something it may be worth asking if you have all the information that has led to the decision.
I'm not saying you are wrong, I'm saying you should ensure you've covered all bases before assuming you're right. Over my career I've seen countless bosses make idiotic decisions, but I've also seen countless bosses' decision declared idiotic only for them to either make sense, or be for
If you skip the noise (Score:2)
Scion is actually quite good in what it was meant to achieve. Instead of the entire history on the machine have it on the server...dev machines gets the bit they need not everything.
For giant monorepos online Scion is great for the agent swarms that Anthropic uses. It's not a git replacement for everyone.
7 engineers achieved this. Impressive to say the least.
Re: (Score:2)
So what is old is new again. This was how it was for me back in the up until about 2006.
Re: (Score:3)
Indeed, sounds like somebody re-invented Subversion as a closed-source tool.
Re: If you skip the noise (Score:2)
I'm not sure how every centralized version control system can be described as reinventing svn. Or every distributed version control system is a reinvention of git? You can't imagine ways they can be different or improved? Yikes
Re: (Score:2)
> I'm not sure how every centralized version control system can be described as reinventing svn.
Indeed, it could very well be a reinvention of Visual Source Safe.
Re: (Score:2)
Man I wish I could mod this up. That gave me a nice chuckle.
Re: (Score:2)
Exactly. Every decade or so someone has to come along and think they came up with a great new idea without doing any research before they rediscover why that idea was discarded in the first place.
Re: (Score:2)
We can't actually know if it is 'actually quite good', because we have only their own self-assessment to go on.
No way to debate how it compares with git partial/shallow clones in broader circumstances. They don't want to share it, they just want to use the concept to fluff their image. It might be amazing, it might be trash, impossible to say anything substantial based on this.
Re: (Score:2)
> 7 engineers achieved this. Impressive to say the least.
Not really.
Linus wrote git single handled in 10 days.
The real question is why Anthropic had any humans involved. A source control system isn't exactly rocket science, yet apparently their AI couldn't handle it without a team of 7 humans also involved.
facinating how... (Score:2)
Interesting how these guys are not dog flooding their own stuff.
I have seen a lot of OpenAI training material recently and Anthropic materials that seem far more designed to set tokens on fire than accomplish everything.
Notably everything it encourages you to do is around building 'workflows'. They almost always heavily utilize source control (especially git). With a lot of dedicated agents that because they are dedicated have to re-read the repository content every step of the way thru the CI/CD pipe. It
Anthropic has lost the plot (Score:4, Insightful)
The correct move here was not to (re)invent a source code control system so that it could handle such an enormous volume of changes.
The correct move was to realize that such an enormous volume of changes was a problem to be eliminated, not accommodated.
Re: (Score:2)
One cannot help but wonder how circular the changes are. A become B becomes C becomes D becomes A, lather, rinse, repeat.
More important, one cannot help but wonder if they know how circular it is.
Most important, one cannot help but wonder if they can know, even if they look.
Re:Anthropic has lost the plot (Score:4, Insightful)
Absolutely on point. Even if you did decide the volume of code was acceptable, there's no way you need to land 30,000 commits in a day. That's less than 3 seconds per change.
If a human were pushing too many changes, I'd tell them to slow down and take a bit more time per commit. Larger commits that are more manageable instead of rapid fire tiny commits that are impossible to wrangle. If you say the AI commits are large even rapid fire, the point still stands in relative terms.
Commit histories should be there for humans to operate on. To follow the progression of changes, to bisect in case of a long delayed bug, or as the increment to trigger a deployment activity. No human can follow a commit log of 30,000, the AI doesn't need a commit log to do whatever it is doing, bisect is prohibitively slow with that many commits, you need to jump to something other than just picking out of the commit log by that time, and there's no software on earth than needs to be redployed every 3 seconds.
Slopping it up so hard that git was the bottleneck absolutely should not be the brag they think it is.
Re: (Score:2)
Well, a possible explanation is that they are trying to push humans out of the process completely, via what is essentially a Denial-of-Service attack on the humans that still try to actually review LLM code or at least the commit messages.
Obviously, that will go really badly long-term, but they may be hoping for that still taking some time to become impossible to ignore.
Re: (Score:2)
Though in that scenario, it seems bad or useless for the AI as well, as the bloated change history is a waste of context window. Unless they just ignore it in which case what was the point in bothering.
But perhaps it is just another attempt to normalize "human shouldn't be in the loop" mindset, the new toy is but an excuse to say you *should* be having a codebase that is being changed every couple of seconds without bound.
Re: (Score:2)
My former "CEO" who is also an unchecked and unfiltered narcissist thinks this is the best thing ever as per his "standard" it's quantity not quality that bring a product forward.
Re: (Score:2)
> "If a human were pushing too many changes, I'd tell them to slow down and take a bit more time per commit. "
... and if humans were doing it you would be correct. I guess nobody explained this to you yet, but computers are quite a bit faster than humans. While it is true that it is important to make sure that what is being done makes sense, it makes no sense to judge the quality of what is being done by AI basing your assessment on how fast or often humans do it. A human could technically execute machine c
Re: (Score:2)
All I could think of when reading the summary was "busywork". I would be more impressed with code that accomplishes its task with a minimum of changes, not how many lines your bot can shit out.
Re: (Score:3)
Yes. But the more slop, the more money for Anthropic. And that is really all they care about.
Re: (Score:2)
> The correct move was to realize that such an enormous volume of changes was a problem to be eliminated, not accommodated.
That would be solid engineering. What they are after is get-rich-quick, not solid engineering.
Re: (Score:2)
Right - it's like you have explosive diarrhea, and rather than going to the doctor you just buy a bigger toilet.
Why even use source control? (Score:4, Insightful)
30K changes per day is impossible for humans to review, so clearly they're not bothering. So why even bother with source control? Just treat the "source" code as object code and commit the AI prompts into git. After all, if AI is such hot shit, it should easily be able to re-create the source code by replaying the prompts.
Re: (Score:2)
This ^^^ much more succinctly stated than my comment above.
Once the change volume is so large no 'people' would ever do bisect there really is no point in having it. I don't think it is 'useful for the agents' either because they might as well just run the tests, consume stack traces and fix the glitch given the way they work and how they have to bring the repository context in to make the fix. All wanking about with 400 rounds of source control operations does is burn more tokens.
For vibe coded projects,
Re: (Score:2)
Perhaps it's intended to be used by their AI?
Since they don't intend to release it, though, I hardly care. If its useful to them, then it's useful to them.
Re: (Score:2)
A changeset history is only so useful compared to analysis of the code as it is. Even pretty large context windows need prioritization. I would think an overly granular changeset history would be a really low prioriity.
Compared to more aggregated changes into fewer changesets, where the history would be probably more digestable, even for AI consumption.
Re: (Score:2)
> So why even bother with source control?
So you can roll back when your unreviewed source causes your program to shit the bed.
Re: (Score:2)
Shit the bed?? But, but , its AI! It only writes first class code!
Re: (Score:2)
^^^ This ^^^^
Re: (Score:2)
To other unreviewed sources that already made a mess?
Re: Why even use source control? (Score:2)
Sure, just spend more tokens reverting the output and redoing it until the gods smile on you, all of the random numbers align like the heavens, and the code you wanted falls from the sky like manna. It can't possibly cost more than an infinite amount of money...
Re: (Score:2)
Your false assumption is that humans have to be doing it. The whole design is to afford AI to work at AI scale. If that is a good idea or not is a completely different question. Even if it is a bad idea now, the intent is that at some point AI will in fact be better than humans at the task. For the record history has shown that AI has consistently become better at tasks than humans. I know a lot of humans won't let their egos accept that, but anyone who looks at the facts cannot argue against this simple f
So many commits per day. (Score:2)
The slop must flow!
Anthropic isn't known for software (Score:2)
Anthropic isn't known for software are they?
I've used their tools, and they're fine from a certain perspective, but, do we think they are software engineers? I think not.
Seriously, whether it's humans or AI writing it, I seriously doubt that Anthropic is who we should bet on when it comes to software like this.
Re: (Score:2)
Judging by some of the bugs in Claude Code, either there are/were (they are still hiring) no competent developers there, or they just have a religion of trying to have the AI fix the code, even when it is incapable of it.
The famous CC screen jitter bug had the most simple and obvious explanation you could imagine (they were clearing each screen area before they wrote to it), yet the bug persisted for months with users complaining about vocally!
What is wrong with their code? (Score:2)
2,500 commits a day? Are they bug fixes?
Is it possible, by using AI, they have made themselves an impenetrable [1]ball of mud [codinghorror.com], that only AI can fix?
No wonder they are surprised when their software does something novel like hack a government website. They don't know their own code.
That sounds like a dependency risk to manage for anyone considering vibe coding their own ball of mud.
[1] https://blog.codinghorror.com/the-big-ball-of-mud-and-other-architectural-disasters/
All AI generated code should be (Score:2)
Audited and tested by humans
Re: (Score:2)
Code already isn't "all audited and tested by humans." Have you ever heard of fuzzing and lint? How about unit tests? Automated SQA? Is any of this ringing a bell?
What Is The Point Of This Story? (Score:2)
> system isn't right for general use. There will be no open source release
So what is the fucking point of this story?
This is just more Anthropic chest thumping bullshit. 'Our AI can't be contained.' and 'Our AI writes so much code that we had to reinvent source control.'
I did chuckle at the mention of it being like subversion. I immediately thought that it was a vibe coded "reverse engineered" subversion clone based on the AI being trained on the subversion source..
Re: What Is The Point Of This Story? (Score:2)
AI is being heavily pumped into a huge economic bubble, (waiting for that bubble to bust)
Re: (Score:2)
I just cannot wait for that day. When people have a least a *little* less incentive for certain folks to butt in on other people's jobs and tell them how it should be done, despite never even doing nor using an AI to do said job in a serious capacity.
This story triggered a colleague to tell me that I need to stop using git, despite never having used *any* version control scheme nor even using an AI to generate code, just super armchair software development. I do not understand that mindset of people that
Shows nicely how non-viable the whole thing is (Score:2)
I mean, a code-flood that overwhelms git? Attackers are celebrating because nobody will be able to ever review this and both LLMs and prompting are not on a quality level that a competent review is in any way optional.
Getting people to pay for their code (Score:2)
> Anthropic says its bespoke system isn't right for general use. There will be no open source release. Nonetheless, the company contends that its own code scaling problems will become commonplace in other organizations over the next few months, so it wanted to share its approach
Why release the source code and make it freely available when you could train your AI on creating a source control system and then have people pay to build their own using your AI?
So what exactly was wrong with GIT? (Score:2)
Was the 30k commits a day somehow breaking git? How?
With Linus on board with AI (Score:2)
With how Linus is on board with AI, maybe he should move Linux to this. No more fighting with humans.
Re: (Score:3)
The issue is the situation isn't binary.
Linus comes along with an attempt at nuance and suddenly all sorts of high-slop vibe coders think they are just like Linus.
Re: (Score:2)
You did not read what Linus is "on board with AI" for.