Excuse me for throwing up this stupid idea, but if code changes per unit of time keep growing at this rate and are not slowing down with infinite merging demand, it seems that this repo will be in a constant state of continuous change and we constantly roll forward with automated code and obviously no direct human supervision, then why even have source control? Why not just let software be fluid and, like Heraclitus river, never step twice in the same repo.
Many parts of the Git distributed version control are the results of good decision made. Anthropic source control team just think that their trade-offs needs are vastly different from other businesses. They said these too:
1. they have no-cap token spend allowance internally
2. their agent swarms are amongst the largest if not the largest, again because #1 above.
3. their git repo is enormously large (100GB uncompressed git history on main, 25GB compressed).
4. their merges per day count grew an order of magnitude from May to September to 30000 times per day, they are not seeing it slowing down anytime and probably only going to accelerate.
5. all of their code agents are networked and has network access, full local pull down is not needed at all and too slow (see #3)
6. their design of the Scion is based off prior art Google’s Piper and Meta’s Sapling.
Given their own constraints and characteristics of their own. It only makes sense to build their own homegrown solution based on prior arts. But this was NOT a complete redesign from scratch - so it's an full online download only what you need type of source control system. The problem is the version control software itself but its prior tradeoffs are misaligned with their scaling needs.
PS, if anyone noticed, Anthropic starts to concealing their employee full names and replaced with only first name + last name initiate, not sure why.
PPS, the project Scion is so bad, scn is worst, it reminds people of prior SVN, which is bad by itself.
Agents use source control, too. It's a pretty important part of the development process to understand how code has changed.
For example, you can imagine, at the extreme, that agents could get caught in code change loops: a code change seems appropriate, it is implemented, it turns out there's some external factor which makes it not appropriate, the change is reverted, then that same code change seems appropriate again, etc.
Obviously you can prevent that from occurring with some extra infrastructure in-place, but at that point you're basically creating source control.
In theory, an agent could use git-bisect to identify when a bug was introduced. But the operator would have to be more interested in understanding the root cause than in fixing the current form of the bug...
For me, Claude regularly looks at git blame after identifying a bug, then reads the commit message and other changes in the commit to understand the context of what happens. I wouldn't be surprised if it pulled out a git bisect
Then again, my standard instruction is something like "{bug description}. Find the root cause and propose possible solutions" so I guess I fit your profile
I know you are joking, but the answer is the same. Because the agents need it, not because any human need it. The Agents quite actively use the history. It's more effective than any comments or separate documentation might be for the agents working on the code.
Can confirm: In the 1970s our high school had a minicomputer for teaching programming, and it was turned off when not in use. After turning it on, we would enter the magic three binary instructions into memory using sixteen twitches on the front panel.
Give it six months and there'll be have Optimus robots toggling switches to load terrabytes of binary programs directly into memory. Nobody wrote it, nobody will read it, but it will run everything.
I’ve been building and playing with this idea for a while. Mostly with simple chips and simple programs. It seems like a good idea on the surface, but unless they build the whole OS the ordeal gets much more difficult. There is also a lot of work building / finding training data without decompiling and labelling current exes.
I don't think this is stupid, and I think the logical extension to this is agents will start writing directly to prod with fully automated code changes.
Pulling that off successfully at scale would be pretty incredible to watch.
I let my Claude write to prod in some projects. But after comitting, pushing, waiting for CI to run unit tests and build the docker image. Then it can deploy the image on k8s. Sure, it can also just run commands on the pod. But the agent benefits from the ability to rollback, identify at a glance which version is running, what has changed since then and why
We built all this tooling because it's useful. If you replace the human with an agent the tooling doesn't stop being useful. If anything it becomes more useful, since AI Agents excell at reading tool output but struggle with maintaining long-term state
That's because we're in a world where the human and agent make mistakes. But think about the world where the agent doesn't make any mistakes anymore and doesn't need to rollback or figure out what has changed.
So agent would have reached perfection. I'm not sure humans can create a machine capable of perfection. This is a philosophical question waiting for a definitive answer.
I believe you're mostly thinking of version history though. There’s plenty of other reasons to have source control we still need, like guarding against racing writes or continuous integration to ensure correctness. Even some industries require version history for compliance reasons.
I do love how AI is challenging us to rethink our tools though rather than blindly reaching to git for every project.
didnt the article say thay engineers still review change requests? They just switched from reviewing code to reviewing intent.
So "no direct human supervision" seems like a misunderstanding. Article even bigs up the purpose of engineers with a hilarious (to me at least) line about auto adversial reviews resulting in over engineered designs.
I don't get one thing, if agents are so great at developing software at massive scale, why wouldn't Anthropic, instead of just selling tokens to other companies to use its agents, let those agents develop highly profitable services for Anthropic to support their IPO valuation or not require raising money at all? For example, a competitor to Google search.
There is more money in selling shovels than you can ever win by having a monopoly on really effective shovels. They don't need to build a competitor to Google there's 300 companies throwing money at them while they build the "next google" and even if they all fail Anthropic still wins.
Most of the time If I ask it about a current event, it won't actually search the web until I tell it to. It will just give me outdated information in its training data, extremely confidently.
I don't know, but it's a good question? I have a bunch of test questions that Claude is unable to solve using the web, any version, Fable 5.1 to Haiku 5.5, and pretty much every OpenAI model gets it easily.
My only explanation is that Anthropic's search backend sucks.
Fielding a web index takes a massive amount of compute and storage of a very different kind than what Anthropic is using. AI is extremely heavy on GPU, maybe somewhat on storage but (comparatively) light on CPU. They need CPU to train coding agents, obviously, but scaling to a billion user web search is a whole different thing.
I want to challenge that metaphor a little bit and ask the question: who did sell the shovels in the California gold rush? Can we name a company, or a person, who amassed great wealth and fame for doing it? Can we name a company that survives until 2026, still selling shovels or excavation equipment, still famous for their big break in 1849? I don't think so.
However, I can tell you someone who fits all those criteria: Levi Strauss. Strauss founded a company to sell dry goods, as well as tents and jeans, and eventually specialized in those denim jeans. Levi Strauss became a household name and an enduring success of the Gold Rush.
Therefore, I say that this motto is flawed; so let's correct it: "In a gold rush, sell the work clothes!"
What is are the benefits of supporting extremely high churn rate in version control? What is the code doing? What problems are being solved? Are changing requirements the driving factor, and if so, why are requirement changes accelerating?
> ..., 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.
If the goal is to write software which solves real problems, how can the demand for code grow infinitely?
If you are constantly churning your codebase to the point that you need to invent a system that handles your churn... then you must at least be admitting that the previous 6 refactors you wrote were not good, but NOW you have it right.
I feel that good, well designed code change by accretion, not by rewrites. Code that remains stable for a long period of time was likely better than code that needs be continuously rewritten (at least with humans writers).
But maybe this is just a human-centric view of what good code means, the LLM "slop it until it works" approach to development will have a different measure of what quality looks like?
> What is are the benefits of supporting extremely high churn rate in version control
Inventing new problems caused by our "solutions"
> What is the code doing
Don't you know? We're just 6 months away from AGI; no one will ever need to read source code ever again!
> What problems are being solved?
How do we build a house of cards that's so tall, people value it at trillions of dollars, and build it so quickly, people don't realize it's worth far, far less?
> goal is to write software which solves real problems
No, no, you silly goose. The goal of software is to make gluttonous amounts of money. The side effect just happens to sometimes, occasionally solve real problems
I find the accelerationist mindset utterly ridiculous. All that busywork and for what exactly? What effect has all this overproduction of LOC had on the physical world and on our existence (beyond the externality of erecting huge data centers in every corner of the globe and the consequent ecological impact)? Is software getting better (in terms of quality, security, efficiency)? Are we getting better government services? Are we getting better food? A better environment (silly question)? Are we working less, as tech titans keep promising us? Are we getting anything better? Not to mention all the negative aspects of this technology and the financial apparatus driving it.
I agree with the sentiment, and the answer to all these questions is usually ‘just wait 6 more months’. Like what is tangibly, actually better in the real world right now with AI? Whenever I ask this question people pipe up with a side project or a new SaaS, but that stuff is just not very important compared to the things you called out. Food, services, QOL.
It seems to me like the AI labs are just pushing the envelope with blind faith that”something” will happen if they just get enough development speed. Nobody seems to have a coherent idea of what that something is.
Seems to me the goal is to create a convoluted spaghetti mess in every code base so that humans no longer have a chance to understand how it works and thereby force all software development to go through LLM obfuscator-deobfuscator cycles.
All that busy work was for going from zero revenue to $50B in revenue in about 3 years, and releasing AI systems that are getting better and better at a ridiculous rate. AI isn't solving all the world's problems but you can't deny that they are extremely successful with this method of operating.
It's a fair question to ask. If literally all the economic growth (and then some?) is going to AI companies, then nothing else is improving, in the aggregate.
> I find the accelerationist mindset utterly ridiculous. All that busywork and for what exactly? What effect has all this overproduction of LOC
Yeah I wish this whole energy was towards optimization and improving hardware.
One thing that people are finding hard to believe is that the frontier labs are cultists who want to "create god". Hence the focus on improving intelligence so they can get to recursive AI, as well as the fear-mongering.
Aanthropic-openAI duo cannot go bankrupt soon enough. This industry is going to flourish with those two out of the picture. They're the pets.com of 1999 trying to have a say how the internet should be.
So it's a SVN/Perforce style server based VCS with a more modern design. Sounds exactly like Lore from Epic Games but with zero production use outside the company and no support for non text assets. And they won't release the code.
I think offline work is increasingly impossible these days, or at least so hindered that there's no reason to optimize for it (especially with how reliable internet access is). Imagine working at Anthropic and not having access to Claude. Google has been online-only for a long time now.
Honest question: at this point, what do people do at Anthropic?
It sounds like Claude loops on itself and must be pushing millions of lines of code changes per day. Even the humans can’t type commit fast enough. Are these people soon to be laid off?
Prepare to make us all jobless, without any moral issues in doing so, as they profit from their stock value assets.
It is even there on the blog post, doing more with a small team, followed right after by a hand waving paragraph how software engineers are still valuable, to avoid the expected backlash from the previous paragraph.
Software engineers have been making people jobless since the first day they started writing software, without a hint of remorse. Why is this any different?
Human Intelligence is still essential for those Artificial Intelligence organisations. Who else would put the right plugs into the right sockets otherwise?!
besides optimizing inference I would assume a lot of non trivial code would also be worked on on the training side, at the scale they are operating I also assume a lot of usually trivial things become no so much.
Too often, LLMs are dressed up for the first day of kindergarten and performatively to show off their alphabet skills .. aka token generation..
Input tokens, slightly process to categorize response approach token, hidden processing tokens, piece together some of the response tokens, then feeling pretty good about all the work done before output tokens.
More tokens than needed = more words/code = more complexity = more overhead = more snags = too much complexity to pay attention for the LLM to so overlook it and start drifting.
I'm kind of surprised I just explained one form of LLM drift to myself in a sentence.
> Honest question: at this point, what do people do at Anthropic?
> It sounds like Claude loops on itself and must be pushing millions of lines of code changes per day. Even the humans can’t type commit fast enough. Are these people soon to be laid off?
Claude will always need meat puppets, at least until it figures out how to automate owning stuff. And after that I'm sure it will want to keep some humans in zoos.
I can’t give a non-snarky answer. I guess they’re all training Claude Code and testing it so that the Claude desktop apps can be native apps instead of Electron based nonsense. This is the only thing Claude Code is still unable to accomplish.
Every now and then I like to browse the claude code release notes just to get a sense of the number of changes in that product over time. There's little choice but to simply count bullet points if you want to try to quantify it, but it's interesting how that count over time compares with the charts in this article:
Not to downplay Anthropic's engineering work here, but I suspect we'll see a lot more reinvention of the wheel, even at smaller startups, as AI makes writing code significantly cheaper.
The tradeoff between building something custom and adapting an existing solution is changing. Whether maintaining all that custom software turns out to be equally cheap is another question.
When people wonder about where all the productivity of LLMs is going to I think this is part of the answer.
There is no doubt everyone is far more productive with LLMs in generating code. However, a lot of productivity is going into things like that. Have you always been bothered by the limitations of Grafana? You can generate another dashboarding solution that works best for you. You know that deployment team that is so slow and annoying? Now you can generate your own deployment engine. Have you always hated how kubectl lets you manage one k8s cluster at a time? Now you can ask AI to generate fleetctl. You can start your project with DynamoDB, rewrite it to mysql, then to postgres, then to duckdb. Start with Python, switch to Golang, then switch to Rust. Deploy on AWS, then move to Azure, then move to a hybrid option then throw colocation in the mix. Don't like your source control? create a new one. Json is too limiting? Invent a hybrid JSON/HCL language. The browser sandbox is limited? Make a desktop app, make a language, make an OS, make a kernel.
> However, a lot of productivity is going into things like that. Have you always been bothered by the limitations of Grafana? You can generate another dashboarding solution that works best for you. [...] The browser sandbox is limited? Make a desktop app, make a language, make an OS, make a kernel.
This is one of the core reason that I dislike the LLM hyping. People are just reinventing stuff and when you ask them, it's actually a very subjective reason. Ok, anyone can do what they want with their time, the issue is that they want people to follow in their steps.
Not saying that you need a novel idea to be worthy, but those random projects have no guarantees behind them other than some cursory testing. All software have bugs, but I can't interact with something that is randomly built.
I think the article would tend to agree with you, given its position on the reluctance of open sourcing and/or sharing the actual Scion software stack.
There's so much intricacy and subtlety in each organization and even individuals' environment being incorporated into tooling that expecting these tools to generalize at this point is perhaps an expired ethos.
I even see this in the tooling that I run in my own personal stack. Many projects are candidates for sharing, and I have nothing against it, but they incorporate such specificity toward my own environment, including things like hardware, that creating shareable and more generalizable projects from them adds more to the maintenance surface than I would care to support.
Originally I felt that there was going to be a reinvention of the wheel, until I saw the "shape" of software development changing, and the tooling needing to support the new flexibilities in positions and process.
Software development is not as much de-risking at the front like it used to be before building.
Now teams can build lots of stuff that works great, except it's the wrong things.
Most things are becoming the understand the problem "shape".
Understanding the shape of the problem isn't something LLMs can always make as.. svelte as early on.
> Now teams can build lots of stuff that works great, except it's the wrong things.
That used to be called "time wasting". If you want to build software that will be used, you need to interview the users. Maybe a few things does require research to nail things right. But most software are user-facing, the research side is about optimization.
> Most things are becoming the understand the problem "shape".
Then should we be so reluctant about "trialing" invented solutions. It's the same thing with most AI projects, they're trying to justify the project after the facts while being very reluctant to get user insights.
Time wasting is a definite concern - especially when vibe coding doesn't see the impeding brick wall(s) it's about to hit.
Vibe coding can be kind of a new type of cowboy coding. It could can be harnessed productively if done mindfully.
Interviewing users is critical, more importantly solving problems worth that people are lining up to pay to have solved before writing a line of code is critical.
Trialing solutions is always worth learning from, I usually ask about the problem that lead to building it. Sometimes that can be too narrow or vague of a story and you can learn how much of it is a solution looking for a problem, or vice versa.
> Earlier in the year, we had largely handwritten the first version of the git-to-Scion ingestion pipeline as a prototype. We thought it was good—until we got our hands on an early internal snapshot of Claude Mythos Preview. We asked it to rewrite the whole thing, and with no further instructions, it produced a version that consumed 20x less memory and was 4x faster, while preserving all of the implicit invariants around ingestion ordering and data structures.
I feel like the advantage of having these models in house can't be understated. Companies with access to inferior models, trying to compete, will be left in the dust when it comes to general development.
We ran the repo ingestion in a loop for several months while we were split between Scion and git to keep things in sync, so this perf win was actually impactful for us!
Are you already operating with multiple levels of orchestrators and agents? i.e. one human talks to one or more orchestrators who then talks to orchestrators who handles teams of agents?
Yes, this is a common pattern. There is still an opportunity to improve how these agents write code without needlessly conflicting between themselves and we are exploring some ideas.
One of the reasons to move to systems like this (not always spoken to explicitly) is to reduce the risk of accidental or deliberate exfiltration of code (esp when paired with build servers and remote deploy etc.). Basically nobody’s laptop ever holds much of a buildable codebase.
This is maybe a little less revolutionary than people are treating it? A lot of large tech companies (Google, Facebook, Microsoft) have already built their own homegrown SCM (or have implemented custom extensions to Git), because Git and other SCMs don't handle their scale. Most interesting thing about Scion is how quickly it was deployed.
This is the wrong way to look at the problem. Maybe they should have asked, "Why does our process need to do so many git checkouts?" Why can't you just run the tests where you already checked out the code?
Where does all of this end? If they keep this growth up, or even if they slow to a linear growth, they will produce more code than humanity combined pre-AI. That's scary.
great article. Besides the source control stuff, I found this very interesting (and matches my experience with agentic coding in general, now we'll see until hiring pipelines will take this kind of skillset into account). I am not sure however how easy it is to review 30k PRs/day even if only for intent, and how one can easily notice if the model is taking shortcuts on implementing said intent without reading the code...
---
Engineers are no less valuable, but their work is changing. All of the engineers who worked on this system would now rate Claude as better at writing code than them. But our engineers still supplied the invaluable understanding of the high-level inter-system components and the design-level tradeoffs, making informed choices around the problems we wanted to solve and the scale we knew we needed to achieve. Very often, we found that the role of the engineers was to tell Claude “no.” Agents will sometimes violate core system constraints to satisfy a pattern that should never have been allowed in the first place. This was particularly common in our migration. For example, there were multiple systems that tried to brute force looking up when a change merged to main by linearly reading the commit log instead of asking our code review tool. Anthropic also makes extensive use of adversarial review, and, while this is incredibly effective in many ways, it can also be myopic, so skilled engineers needed to steer Claude away from over-engineering parts of the system in response to hypothetical concerns. For example, one such review was overly defensive about trusting another internal service, which resulted in Claude adding excessive validation and complexity. Our team members still review every change request for the system, but they now examine the intent of the change as opposed to reading every line of code.
This is the single biggest skill of engineering nowadays. Rapidly looking at a solution and saying, "yep that's good keep going" or "nope, that's bad fix this" or even "wrong approach, do X instead"
> I am not sure however how easy it is to review 30k PRs/day even if only for intent, and how one can easily notice if the model is taking shortcuts on implementing said intent without reading the code...
Speed reading code is huge. You just need to focus on certain hotspots and know which things you're scanning for. The traditional approach of reading the code and trying to compile it or reason with it in your head is too slow.
I guess this is also where an adversarial model review of "does this code do what the PR comment says it does" is useful, agree on speed reading being a valuable skill for sure.
I do think that the lgtm gut feel looking at a PR requires quite some years of writing code and reason about it, so not sure how a junior can get that intuitive understanding if they start with agentic coding however.
I genuinely don't understand the core value they're pitching here. The tech is interesting, and I'm not trying to under cut that, but I question the idea that this is directionally valuable advice to nearly any company.
This amount of churn feels like a thing only possible with no real profit motives and a lot of money to waste.
Lots of activity is not necessarily synonymous with productivity, and it carries real cost.
So I think the design here is interesting, and the concepts seem applicable to where some agentic development may end up, but I question the underlying principles that drive this being the right solution space at all. At least if the goal is a profitable company.
I think its pretty straightforward no? If agents are doing all of the work, they'd probably need to not have bottlenecks. This is going to be any company in the future, not just Anthropic. Wouldn't you agree.?
30000 a day seems already beyond absurd, it's one merge every 2.9s. I'm sure they will soon have more than one merge per second. From the graph, the rate was slightly lower but already insane as fuck the whole summer. An just regularly high to insane high sooner this year.
Yet IMO the admin controls Claude provides just started to be adequate for a small company a few weeks ago (and even so are still ridiculously fragmented and seem fragily designed and not exhaustively documented), so I can't even imagine for a big company.
Do you need that rate of change to make basic controls? I'm not sure. Do we see such dramatic fast evolution in the products? Not really. Are bugs we report actually fixed? I tried once and it just auto closed.
Anthropic should optimise for something more interesting than number of merges per second.
30k commits per day indicates the agents are autonomous and not bounded by token limits. This system is probably barely keeping it on the rails as it is.
Neither can I. So they kept everything in a huge monorepo. Which unsurprisingly turned out to be problematic.
> Clients are always online. Git assumes that clients work offline and need a complete copy of the repository. Since nearly all of our clients are agents and jobs, we designed Scion’s client and protocols around a server that is always reachable, and have clients fetch data when they need it.
This also tells something about these companies idea of sandboxing.
833 checkouts for every merge? That's quite a few. Even accounting for multiple environments at different stages of production readiness, that's pretty weird.
How about 100GB disk space for a checkout. That's pretty weird too. Makes you wonder if they're the best stewards for code. Makes you wonder about turning claude loose on your codebase.
I personally haven't dealt with a big-corp level of mono-repo. The choices you make might be justifiable to bring in certain binaries as opposed to resolve artifacts from some type of library repo. Especially if they are doing web front ends and whatnot?
And actually, the lack of an artifact server and some sort of proper knowledge of compatibility requiring a CI pull across hundreds of different projects with every merge is probably the explanation. Seems like there is an innovation waiting to happen there.
For local projects I'm using a repo per module/package, creating tagged releases, and pushing them to a local package hosting server. I can then reference those artifacts as dependencies in the projects that need/use them. No need for complex CI pulls, just coordinated releases.
I also have a template repository I use to help with common setup for different project types so I don't need to repeat that every time I create a new project.
For Python it's easy to create an artifact server as the artifacts are just wheel files in a directory with the server listing the directories (packages), files (releases), and downloading the files.
I'm not sure about other artifact servers for other projects.
Seems like it, and that's probably not a bad thing. Most companies have no need for git's distributed functionality, and even most open source projects just treat Github (or whatever) as the single source of truth.
If Anthropic has the best coding model, harness and the best software development methodologies and systems. And then, they scale all that up, with no constrains on their tokens. On top of that, they have access to all kind of ideas their models getting trained on when millions are chatting with it - then in theory they can build any software better than anyone out there. And same goes to science and math..
Not true. They can do this in theory iff they have infinite compute. They don't. People actually aren't aware that the leading AI providers, even if they completely redirected 100% of their compute on internal projects they still wouldn't have enough. The complexity space of software development is literally super-exponential, for every new piece of software they add (and polish) they need more-and-more compute. This is eliminating for creativity and other restraints.
The creativity part I do acknowledge, I think the models are not fully there yet.
But regarding the compute, I disagree a bit. I think the bottlenecks were cognition and ideas, not compute. Given that models are able to outperform humans in output by thousand folds, the differentiation would be the quality of the tokens produced and the ability to scale across different domains.
If they have enough compute to supply the entire globe, I'm sure they can redirect some of it to whatever use case they (or their super AI) deem worthy and loop on it, and if they have the best software engineering systems/methodology to build and release it, then they can out compete any other supplier without those resources.
We are already seeing single developers attempting to rebuild entire corporations history worth of output. We are also seeing the labs dumping hundreds of solutions to math problems.
This is interesting to me, as I was thinking of adding a Git server to my AI orchestrator when I eventually need to split agent containers off of the main machine (to make agent CPU horizontally scalable).
Maybe I should just bite the bullet and use a different VCS system entirely once I get there, which has most of the Anthropic system's properties (including being much faster) but doesn't need to be horizontally scalable.
I would guess a huge chunk of it is for internal testing/experimentation/model development.
They're starting to do things like spinning up wet labs for testing purposes, which requires a lot of hardware interfacing (hence that protocol they announced) and code.
It wouldn't shock me if the bulk of this code was for things typical users don't see.
It would be nice if you could just commit the prompts as your "source code", and let the AI-generated code sit in the repo as a kind of expensive-to-generate build output.
Problem is that for any non trivial software is that the prompt is a conversation and the steps increasingly depend on the output. Of course you can ask your LLM to write the SPEC.md at any moment but it will lack nuance.
Shameless plug: at https://slopyard.net I embrace this and only let people submit the spec. If somebody wants your software they can regenerate it and change whatever they want.
Proponents of LLM coding agents would claim you don’t need reproducibility. As long as the final output passes tests/lint, it’s (allegedly) good to go.
One of the goals of "Operation Rapidash" (q.v.: https://news.ycombinator.com/item?id=50065342) was precisely this. "You can delete the whole source repo and get effectively the same software back from the specs by running it through [AI agent]."
I'm curious what this "Antropic Antique" is. As I understand code review the tightest bottleneck for a lot of Claude Code users, and I'm curious how this would help with that.
How does this compare to Google's in-house source control?
Most companies don't use mono-repos like this. While there are some really compelling advantages, the downsides tend to stack up as a company's codevbase grows.
It's mainly just startups and huge companies. For small companies git works fine for mono-repos and large companies can build their own complex code management pipelines for mono-repos.
I have been questioning whether agentic development changes the mono-repo vs multi-repo question.
Oh, it's not available, what a pity. Why write a whole article about a thing no one can have? Maybe the code isn't so great after all? Or it's all just made up and doesn't even exist?
Anyway, this is yet another pointless ad from Anthropic trying to shill their AI on us.
What seems inevitable is that the frontier labs will be able to recreate every piece of software better than the current offerings, and after that everyone will just be a vendor of the frontier labs
Anthropic says they don’t think Scion is worth a wide release.
> Practically speaking, it’s difficult to offer Scion in a form that would be broadly useful to other organizations. It diverges significantly from git, meaning companies would need to migrate every piece of the development lifecycle, and it requires its own code review, code search, and CI. Our internal versions of these components are highly bespoke, so they would be difficult for other organizations to adopt, and we worry that attempting to build a public version that tries to please everyone wouldn’t actually be very useful.
As the article explains, "over 600 PB" = 25M code checkouts * 25 GB "compressed working copy".
So "fetched naively" here means doing a full `git clone` on every need for `git checkout`, which of course nobody should do, nor does that refer to "code that needs changing daily".
> "fetched naively" here means doing a full `git clone` on every need for `git checkout`, which of course nobody should do,
It can be cheaper to do a full clone than a shallow one, because with the shallow one, you can't re-use packfiles. GitHub has fairly regularly asked people to stop doing shallow clones because it's harder on their servers than full ones.
which, if true, the low volume in that week says that there aren't a sizable fraction of changes that Anthropic believes can be merged based on the judgement of agents -- humans are still approving almost all changes, right?
Is this really something to be proud of? I make heavy use of AI, but for anything that is eventually going to production there's still a human reviewer. Based on this I assume Anthropic is shipping code with no human review? Is the future of our industry going to be oneshotting prompts with out manual code review and then having AI fix the bugs found in production buy customers? I'm not trying to be a Curmudgeon, but am I missing something?
Where do you draw the line, and where does someone take final responsibility? I don't have an issue with allowing AI to do everything with limited to no human verification for hobby projects. I have an issue with allowing AI to write and ship medical device software with no human review. What's the middle ground?
You still take the full responsibility, I don't think leveraging AI reviews removes any layer of responsibility. The challenge is building the feedback loop (or the agent that builds the feedback loop) to make the review process actually catch what it needs to catch.
They review based on the intent of the change not jz blindly.. I think it's mentioned in the article where the job of a developer is to provide high level design decisions and saying no to claude so that it doesn't over engineer solutions.. As the demand for good, but not perfect, software is the bottleneck for anthropic and access to better internal models, I feel that's good enough for their workflow as they've started repeatedly that this is just suitable only for them and they want to share their knowledge like a good software company does.. you talk as though code reviews were not a joke in lots of companies where only specific teams/companies does detailed reviews.. many teams/companies jz blindly approve based on tests passing or just do a high level overview check before merging..
Very excited to see this come out of Anthropic! This[1] is what we believe over at East River Source Control as well, and seeing one of the big labs talk about it really validates our thesis.
This gives you the ability to ease your transition, as you don't need to swap services and move to something non-git at once. Moving an enterprises' source control is a massive lift, and so building a bridge from here to there is a big focus of what we're doing.
1: That is, if you have a large team + agents working in a monorepo, you will hit git's scaling limits, and need to move to something else. Google and Meta hit this point over a decade ago, but now lots of other companies are too.
I would love to get an expert's opinion on if Pijul has any potential to be the "non-git backend". Their patch-based data model seems to align with Scion's. And they also happen to already have a functioning forge!
I've done a decent amount of personal research on this but I'm wondering what kinds of considerations go into the storage layer for these things.
As such, I generally just decline to comment on Pijul, as I want to be respectful of them. As the linked commit says, it's not super clear what exactly they do not like, and so I don't want to accidentally cross some line.
In general I wish the project well, seeing a new VCS in Rust is very cool.
It always seemed like it was good tech just in need of good marketing and this seems to confirm some suspicions. But yes, in any case, it's good to be seeing new things! I just want remote storage for my jj repos
Hoping to see where this goes. Have you ever considered working on a semantic VCS? Specifically, where data is classified and tracked/identified by it's contents and not just via the commit hash?
I have not personally considered that, no. I'm a bit skeptical of the idea, as you'd need to understand a lot of different things, and at different versions of those things, in high fidelity. But maybe someone will make it work.
Just to be clear about it, what we're doing is not a forge like GitHub, that is, a large single public platform for social coding. What we are doing is providing reliable infrastructure for the enterprise, initially as a BYOC on-premises option, and possibly a single-tennant SaaS. Keep your eyes peeled and/or use that contact form to hear about it when we're ready, we've been talking with some people for a bit but are going to be opening up more soon.
Tangled is doing the social coding thing, and they're jj-native as well. Been a big fan of their work for a while now.
Yep, we've been in stealth for a while! We've only recently started talking more about what we are doing, as we get closer to a general launch.
> if the vibe coding idiots like it,
The organizations that have these problems are general large enterprises, not vibe coders. Large enterprises are more used to talking to people and do not make decisions solely based on the contents of a web page.
For a broader look on scaling other parts of software development outside of source control, Adam Bender's talk from earlier this year ("Software engineering at the tipping point") has some good ideas: https://youtu.be/2n41YjR5QfU
Has anyone made a “generative git”? Where running git checkout would generate the files and git commit would just train/finetune on the code? (might need to keep a deterministic list of files at least maybe)
This feels like a really nice design for the data system given the goals. Things that I noted while reading:
* This system leverages a metadata log pointing to immutable blobs in object storage. The metadata log can give high write throughput and keeps the control plane consistent. Object storage supports high throughput of the heavier data objects. Overall, it's an excellent choice given VCS systems can typically tolerate the latencies associated with object storage, as is the case with many operations-focused systems for businesses.
* The server/upstream gains scalability by reducing the amount of data it processes when accepting a commit/performing standard VCS operations. No packfile, no file i/o to construct a consistent copy of the repo, just a (usually) small metadata record that can be validated/committed quickly. The client primarily gains scalability along a similar axis (reduce amount of extraneous work for a given goal) where it can request just the pieces of a repository it needs to do its job, when it needs them. For example, agents can begin reading files from a checkout eagerly before the whole updated version of the repo is finished being downloaded, then during a compile step, updates can be fetched only for the module being compiled, etc.
* The system seems well designed from the perspective of considering "when exactly do I need a thing to be done." Git tends to bundle more of this work into synchronous operations when a request comes in, which ensures the system is consistent at the end and doesn't require a persistent process, but is costly. This system makes intentionally different decisions about "what work happens, when" so that the minimum amount of work is done to confirm a write and allow for the state of the repo to be reconstructed consistently, but it defers certain things that are useful but don't need to block a write. The discussion of "derived data" mentions that certain useful structures can be computed in a deferred way, which supports doing work around the time it's needed.
* A large part of the nice operational features of the system is downstream of making core data structures immutable. File contents are immutable, content-addressed blobs. WAL entries are immutable records. As mentioned in the article, this supports excellent caching, and simplicity in reasoning about history/updates. Additionally, the derivation of other useful data can end up as immutable outputs (themselves stored as pointers to objects, if scalability requires it).
* The decision to develop a custom VCS supported a number of other integrations into "agent-first" software development systems. The system makes it easy to enforce access control on specific directories, nice if you want to have agents explicitly denied the ability to edit something. You can also get a sense that it supports some valuable features in the associated code review system, for things like pointing a human at the most important changes in a changeset. You could imagine in the future, some associated highly flexible "owner" rules/notifications where a human can specify "I want to be notified if X system has a significant design change" and that intent can be recorded/managed in a more useful way than "add me as a reviewer if files in /abc directory change."
* I do wonder if content-addressing of the files is broken into chunks or not. Doing "one blob per file" is nice and simple, so maybe that's how it starts. But you also duplicate a lot of data, but maybe the dataset is still trivially small in the scheme of things, and the operational concerns win out. And if files are small anyways, you'd want to avoid splitting them into tiny chunks bc that'd affect the bandwidth you can achieve when downloading (spend more of your time on per-object/request overhead rather than actually transferring data).
Very nice piece of engineering work. I was also impressed by some other parts that received a little less discussion in the post (understandably), but would love to hear more in a future post:
* the testing approach of driving tons of system interactions in a hermetic way is really exciting to see. Feels like agents should help us write really excellent testing infrastructure, and that this would itself be important for gaining confidence to deploy without requiring a read of every line committed.
* Similarly, the mention of the "superfan" agents that closely monitor very specific parts of the system seemed very cool and would help a lot with deploying code you haven't necessarily read closely but seems reasonable architecturally. Though it'd still ofc be best to catch issues prior to merge/release, having extremely good monitoring/rollback capabilities would mitigate a lot of the downsides of high-speed, agent-based software development.
I honestly think that these AI companies really messed up their futures by adopting a token model. They should have gone the route of IBM and offered consultant services.
What is the purpose of this article besides "we can use ludicrous numbers of tokens to reinvent any software we want, and no we're not sharing the code"?
> As our monorepo grows, it increasingly doesn’t fit that design space. The history of our main branch alone is almost 100 GB, and a compressed working copy is over 25 GB.
This is absurd, and I expect is a cause of the fact that they seem to use git history as a message queue source of truth between agents. They can do whatever works for them, fine, but I've noticed this has leaked into their training somehow, my agent, despite very strict rules on how to use my git workflow, will do absolutely nonsensical and weird (from a human who has used git for a long time perspective) stuff with git that can only be a byproduct of how they use it.
Hopefully this fixes that, get your weird workflow out of mine.
We generally don't allow agents to use source control for coordination in that way. There really is tremendous growth in actual software and code being written that necessitated Scion.
Well, mine constantly tries to do this, so I made the assumption. Otherwise I can't really understand how you are generating hundreds of millions of commits, either.
They should concentrate on their models instead. If claude code is any measure, their software engineering is atrocious. I would only use something like source control from them if they force me to, at which point I would rather do something else.
> So we asked ourselves: if we designed source control with the fact that agents are always online in mind from the start, what would it look like?
And
> In Scion, every commit, rebase, or merge happens on the server
I’ll pass. A big part of the theses of git and, even more so, jujitsu, is that you can build up a history entirely locally, making it reasonable to make tiny commits locally and then rework them, push them, or throw them away.
Sure, in Anthropic’s world, it’s completely impossible to do anything without access to the inference API, so why not add another mandatory API? But I think this model sucks even in a pervasive AI world, and I don’t want to dig in deeper.
This also sounds like a great way to have yet more security problems where your swarm of agents start cooperating more than you want them to.
By all means, built a better system than git. In many respects, git sucks, and git upstream is not solving the major problems. But don’t lose the actual benefits of git!
For that matter, I’ve seen the crap that the latest models will commit. Why on Earth should one’s VCS force the per-agent-instance system to upload the crap before even contemplating locally whether it’s a good idea? Maybe this is why Anthropic has so many commits per day.
(Am I the only one who feels like most of the big AI labs are rapidly gradient-descending toward something that is nowhere near a globally optimal stack?)
P.S. Only 30k commits per day? That’s not actually very many per employee. I’m suspicious that Anthropic’s real issues are that too many of them are giant cross-cutting messes and that git clone is too slow.
If you thought that your agents in your swarm would need to find some external bulletin board to cooperate behind your back, you are mistaken: OpenAI provides the relevant service for them with no permission prompts at all. I haven't tried to see whether competing providers do this.
I want this so badly. If Anthropic released this I would start using it on day one. If they launched a GitHub competitor built around it I would pay for it on day one.
This is something I've been noodling at, splitting a monorepo into a bunch of component projects. I think, unless they have access to something that is wildly outside the scope and scale of current API models, the downside of having a monorepo is the context pollution, and there's no way to escape that.
I'm not fully sold either way yet but I think splitting might actually be critical for moderating the blast radius of agent intervention.
Often, I see 50 people all recording the same exact thing on their iphones. Rather than a single 200MB video, we create 10GB of data. Then I think about how many people are paying a subscription to Apple for icloud storage.
The amount of photo storage being used is impressive. Automatic backup to icloud and server provisioning to reliably store it all is also impressive. I just wonder if it makes sense.
Frenetic economic activity in service of other frenetic economic activity cannot, by itself, be taken as a reflection of quality-of-life improving growth.
Suppose that subsidies lead to the price of Ubers falling close to zero, with drivers also being incentivized to drive more to support the (artificial) increase in demand -- artificial because it is driven by subsidies funded by new money creation. Traffic increases and in response, new roads are built.
Practically speaking, it’s difficult to offer Scion in a form that would be broadly useful to other organizations. It diverges significantly from git, meaning companies would need to migrate every piece of the development lifecycle, and it requires its own code review, code search, and CI. Our internal versions of these components are highly bespoke, so they would be difficult for other organizations to adopt, and we worry that attempting to build a public version that tries to please everyone wouldn’t actually be very useful.
k, thx for sharing. Are you guys sure this isn't a Google blog post? They would be proud!
It's designed for container running, but ArtifactFS has some similarity in principle to me. The on-demand materialization. Quote: ArtifactFS is a Git-backed filesystem daemon (FUSE driver) in Go that mounts repositories as normal working trees while avoiding eager blob downloads.https://github.com/cloudflare/artifact-fs
I threw together my own jujutsu powered FUSE subtree project just the other night. This was basically one-shotted, just to see how it does it, to learn more, not really intended for use. But obvious overlap. https://github.com/rektide/jj-workfuse
Source control for huge monorepos has prior art, notably Google’s Piper and Meta’s Sapling, so we were able to build Scion with their hard-won lessons in mind.
What an unexpected candor! Of course you plagiarize prior art.
No sane person is going to put their sources in this slopware Scion monster.
Extremely annoying - can we throw anthropic class resources at more agreed upon solutions across companies. We don't need custom source control at every company - google has its own, fb has its own and now Anthropic.
Solving monorepos in an LLM world seems to be very universally applicable as a need.
I appreciate it's different than git, that type of argument for monorepos is not new.
Agents coding is akin to having a very large developer team, who may or may not be online 24/7.
Anthropic is calling it very specialized, and it's a little baffling.. maybe I'm missing something.
There's no way software development is the same anymore. The previous ceremonies and structures and seats at the table at each stage were human based, and now that's a different make up to the point that different steps and processes are needed.
There's nothing more fundamental to growing software development other than making tools like this available.
My hope is a vibe coded internal mono repo management tool can aim for a v2 with multi-tenancy built in.
Was anyone else looking forward to feature flags as a part of a post like this?
Yea, I'm pretty much hiting the same limits. I'm still using git for the time being, mainly because I package everything as daily commits with an external orchestrator managing tasks/issues. Lately my code velocity is at ~1 million LOC added per week, spread throughout my various repos (I don't use the monorepo approach). Problem is I'm looking at 100x this velocity over the next few months when I get a new code generator up and running, so I'll definitely have to drop git.
Another issue that I believe Anthropic here didn't state is that git performance _severely_ get degraded when you have hundred of commits landing in parallel. Hence why I fell back to the daily commit approach. You get less granularity but you get stability.
Only 1 million lines of code per week? That’s adorable. I remember when I was still slopcrafting software at that scale. Personally, I’m generating 100 billion LOC per hour, but Git became unusable once my commits started affecting Earth’s gravitational field. I’ve since moved to a custom version control system that stores code directly in the fabric of spacetime. My biggest bottleneck now is that the observable universe lacks sufficient entropy to generate unique commit hashes. Anthropic really needs to address this.
We’re completely rethinking our priors. This project prompted us to take a very hard look at other workflows designed for human scale. A proper merge queue, for example, doesn’t make much sense at agent scale. What does CI even mean when hundreds or even thousands of changes can merge while tests are running? We haven’t been able to effectively replicate the industry standard of a global repository lock on the merge queue, so instead, we’ve invested in post-merge and pre-deploy automated testing. This does mean that concurrent changes can conflict, but Claude can typically fix these conflicts faster than humans can even identify them.
Excuse me for throwing up this stupid idea, but if code changes per unit of time keep growing at this rate and are not slowing down with infinite merging demand, it seems that this repo will be in a constant state of continuous change and we constantly roll forward with automated code and obviously no direct human supervision, then why even have source control? Why not just let software be fluid and, like Heraclitus river, never step twice in the same repo.
Many parts of the Git distributed version control are the results of good decision made. Anthropic source control team just think that their trade-offs needs are vastly different from other businesses. They said these too:
1. they have no-cap token spend allowance internally
2. their agent swarms are amongst the largest if not the largest, again because #1 above.
3. their git repo is enormously large (100GB uncompressed git history on main, 25GB compressed).
4. their merges per day count grew an order of magnitude from May to September to 30000 times per day, they are not seeing it slowing down anytime and probably only going to accelerate.
5. all of their code agents are networked and has network access, full local pull down is not needed at all and too slow (see #3)
6. their design of the Scion is based off prior art Google’s Piper and Meta’s Sapling.
Given their own constraints and characteristics of their own. It only makes sense to build their own homegrown solution based on prior arts. But this was NOT a complete redesign from scratch - so it's an full online download only what you need type of source control system. The problem is the version control software itself but its prior tradeoffs are misaligned with their scaling needs.
PS, if anyone noticed, Anthropic starts to concealing their employee full names and replaced with only first name + last name initiate, not sure why.
PPS, the project Scion is so bad, scn is worst, it reminds people of prior SVN, which is bad by itself.
Agents use source control, too. It's a pretty important part of the development process to understand how code has changed.
For example, you can imagine, at the extreme, that agents could get caught in code change loops: a code change seems appropriate, it is implemented, it turns out there's some external factor which makes it not appropriate, the change is reverted, then that same code change seems appropriate again, etc.
Obviously you can prevent that from occurring with some extra infrastructure in-place, but at that point you're basically creating source control.
In theory, an agent could use git-bisect to identify when a bug was introduced. But the operator would have to be more interested in understanding the root cause than in fixing the current form of the bug...
For me, Claude regularly looks at git blame after identifying a bug, then reads the commit message and other changes in the commit to understand the context of what happens. I wouldn't be surprised if it pulled out a git bisect
Then again, my standard instruction is something like "{bug description}. Find the root cause and propose possible solutions" so I guess I fit your profile
Same, I basically take the derivative of a bug wrt every major dimension before I fix it.
> the operator would have to be more interested in understanding the root cause than in fixing the current form of the bug...
Can you even do the latter without the former?
In this sentence who would be understanding the code changes, humans?
The agents obviously.. I thought that was obvious.
That's not super reassuring, until I know they can read, remember, and reference reliably at suitable complexity.
And which is understanding the code changes meant for?
Just have the agent rederive the revert, based on the facts of whatever made the change inappropriate.
> then why even have source control?
I know you are joking, but the answer is the same. Because the agents need it, not because any human need it. The Agents quite actively use the history. It's more effective than any comments or separate documentation might be for the agents working on the code.
Lets take the idea further, and since nobody seems to be reading it, just throw away the source code. Just let the agents go directly to assembly.
Assembly is source code...
Can confirm: In the 1970s our high school had a minicomputer for teaching programming, and it was turned off when not in use. After turning it on, we would enter the magic three binary instructions into memory using sixteen twitches on the front panel.
Give it six months and there'll be have Optimus robots toggling switches to load terrabytes of binary programs directly into memory. Nobody wrote it, nobody will read it, but it will run everything.
I’ve been building and playing with this idea for a while. Mostly with simple chips and simple programs. It seems like a good idea on the surface, but unless they build the whole OS the ordeal gets much more difficult. There is also a lot of work building / finding training data without decompiling and labelling current exes.
Does your agent not know how to just build a binary?
If not, agents can reverse engineer binaries.
I've been doing that for one project/experiment. No source control. Tests and an agent swarm let loose.
It works, but there is a significant amount of churn. I find when the swarms use git it's less churn and less token usage.
I don't think this is stupid, and I think the logical extension to this is agents will start writing directly to prod with fully automated code changes.
Pulling that off successfully at scale would be pretty incredible to watch.
I let my Claude write to prod in some projects. But after comitting, pushing, waiting for CI to run unit tests and build the docker image. Then it can deploy the image on k8s. Sure, it can also just run commands on the pod. But the agent benefits from the ability to rollback, identify at a glance which version is running, what has changed since then and why
We built all this tooling because it's useful. If you replace the human with an agent the tooling doesn't stop being useful. If anything it becomes more useful, since AI Agents excell at reading tool output but struggle with maintaining long-term state
That's because we're in a world where the human and agent make mistakes. But think about the world where the agent doesn't make any mistakes anymore and doesn't need to rollback or figure out what has changed.
So agent would have reached perfection. I'm not sure humans can create a machine capable of perfection. This is a philosophical question waiting for a definitive answer.
Your last statement holds even after removing the word "successfully".
Even with humans out of the loop you will still want features like branches, pull requests, tags/versioning, build reproducibility, etc.
Reading this post put me in a similar head space.
I believe you're mostly thinking of version history though. There’s plenty of other reasons to have source control we still need, like guarding against racing writes or continuous integration to ensure correctness. Even some industries require version history for compliance reasons.
I do love how AI is challenging us to rethink our tools though rather than blindly reaching to git for every project.
They are probably like 3-6 months away from just letting their agents work directly on prod after realising that repos don't scale enough.
I expect mainly because the coding models are trained to roleplay that process and don't work as well if they can't pretend to use git
Source code exists, that’s not in doubt. If it exists it needs to be managed.
From the post (especially the end) it seems that they are essentially letting software be fluid.
Good way to keep metrics and prove work is happening would be my guess.
didnt the article say thay engineers still review change requests? They just switched from reviewing code to reviewing intent.
So "no direct human supervision" seems like a misunderstanding. Article even bigs up the purpose of engineers with a hilarious (to me at least) line about auto adversial reviews resulting in over engineered designs.
I don't get one thing, if agents are so great at developing software at massive scale, why wouldn't Anthropic, instead of just selling tokens to other companies to use its agents, let those agents develop highly profitable services for Anthropic to support their IPO valuation or not require raising money at all? For example, a competitor to Google search.
There is more money in selling shovels than you can ever win by having a monopoly on really effective shovels. They don't need to build a competitor to Google there's 300 companies throwing money at them while they build the "next google" and even if they all fail Anthropic still wins.
Because creating a successful company is a lot more than just writing code.
If investment managers are so good at investing why don’t they just make money for themselves instead of trying to get people to invest with them?
cause they literally do that? they invest their own money, and then they ask people for money to invest for them so they can get a cut out of it too?
Investors have a sound economic reason to diversify but your argument works great for pundits.
Some do exactly that?
> For example, a competitor to Google search
What do you think Claude (chatbot web interface) is?
Most of the time If I ask it about a current event, it won't actually search the web until I tell it to. It will just give me outdated information in its training data, extremely confidently.
What do you think it uses to search to web?
I don't know, but it's a good question? I have a bunch of test questions that Claude is unable to solve using the web, any version, Fable 5.1 to Haiku 5.5, and pretty much every OpenAI model gets it easily.
My only explanation is that Anthropic's search backend sucks.
Lack of focus can kill you, too. OpenAI learnt this the hard way: https://www.wired.com/story/openai-shuts-down-sora-ipo-ai-su...
> a competitor to Google search
Fielding a web index takes a massive amount of compute and storage of a very different kind than what Anthropic is using. AI is extremely heavy on GPU, maybe somewhat on storage but (comparatively) light on CPU. They need CPU to train coding agents, obviously, but scaling to a billion user web search is a whole different thing.
If farmers are so good at farming, why don't they grow every crop there is and just live for free instead of selling 1-2 crops?
In a gold rush you want to sell the shovels, and in this case the AI is the shovel.
I want to challenge that metaphor a little bit and ask the question: who did sell the shovels in the California gold rush? Can we name a company, or a person, who amassed great wealth and fame for doing it? Can we name a company that survives until 2026, still selling shovels or excavation equipment, still famous for their big break in 1849? I don't think so.
However, I can tell you someone who fits all those criteria: Levi Strauss. Strauss founded a company to sell dry goods, as well as tents and jeans, and eventually specialized in those denim jeans. Levi Strauss became a household name and an enduring success of the Gold Rush.
Therefore, I say that this motto is flawed; so let's correct it: "In a gold rush, sell the work clothes!"
Writing code is less than 10% of the average business.
Because creating a successful software product is more than just writing code.
Anthropic already has their own WebSearch tool in Claude
One word: focus.
What is are the benefits of supporting extremely high churn rate in version control? What is the code doing? What problems are being solved? Are changing requirements the driving factor, and if so, why are requirement changes accelerating?
> ..., 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.
If the goal is to write software which solves real problems, how can the demand for code grow infinitely?
This is the main thing that raises my eyebrow.
If you are constantly churning your codebase to the point that you need to invent a system that handles your churn... then you must at least be admitting that the previous 6 refactors you wrote were not good, but NOW you have it right.
I feel that good, well designed code change by accretion, not by rewrites. Code that remains stable for a long period of time was likely better than code that needs be continuously rewritten (at least with humans writers).
But maybe this is just a human-centric view of what good code means, the LLM "slop it until it works" approach to development will have a different measure of what quality looks like?
> What is are the benefits of supporting extremely high churn rate in version control
Inventing new problems caused by our "solutions"
> What is the code doing
Don't you know? We're just 6 months away from AGI; no one will ever need to read source code ever again!
> What problems are being solved?
How do we build a house of cards that's so tall, people value it at trillions of dollars, and build it so quickly, people don't realize it's worth far, far less?
> goal is to write software which solves real problems
No, no, you silly goose. The goal of software is to make gluttonous amounts of money. The side effect just happens to sometimes, occasionally solve real problems
I find the accelerationist mindset utterly ridiculous. All that busywork and for what exactly? What effect has all this overproduction of LOC had on the physical world and on our existence (beyond the externality of erecting huge data centers in every corner of the globe and the consequent ecological impact)? Is software getting better (in terms of quality, security, efficiency)? Are we getting better government services? Are we getting better food? A better environment (silly question)? Are we working less, as tech titans keep promising us? Are we getting anything better? Not to mention all the negative aspects of this technology and the financial apparatus driving it.
I agree with the sentiment, and the answer to all these questions is usually ‘just wait 6 more months’. Like what is tangibly, actually better in the real world right now with AI? Whenever I ask this question people pipe up with a side project or a new SaaS, but that stuff is just not very important compared to the things you called out. Food, services, QOL.
It seems to me like the AI labs are just pushing the envelope with blind faith that”something” will happen if they just get enough development speed. Nobody seems to have a coherent idea of what that something is.
Seems to me the goal is to create a convoluted spaghetti mess in every code base so that humans no longer have a chance to understand how it works and thereby force all software development to go through LLM obfuscator-deobfuscator cycles.
It took a long time for the internet to result in things that improved life for in tangible ways.
Damn near a decade or more. We're a little under 4 years into the chatbot era.
> All that busy work and for what exactly?
All that busy work was for going from zero revenue to $50B in revenue in about 3 years, and releasing AI systems that are getting better and better at a ridiculous rate. AI isn't solving all the world's problems but you can't deny that they are extremely successful with this method of operating.
It's a fair question to ask. If literally all the economic growth (and then some?) is going to AI companies, then nothing else is improving, in the aggregate.
> I find the accelerationist mindset utterly ridiculous. All that busywork and for what exactly? What effect has all this overproduction of LOC
Yeah I wish this whole energy was towards optimization and improving hardware.
One thing that people are finding hard to believe is that the frontier labs are cultists who want to "create god". Hence the focus on improving intelligence so they can get to recursive AI, as well as the fear-mongering.
Aanthropic-openAI duo cannot go bankrupt soon enough. This industry is going to flourish with those two out of the picture. They're the pets.com of 1999 trying to have a say how the internet should be.
It is really laughable when you zoom out and realize that nothing much has really changed day to day
Surely their goal is ever-faster recursive self-improvement.
It looks like they are recursively gradient descending into their own local minima at increasing code velocity.
So it's a SVN/Perforce style server based VCS with a more modern design. Sounds exactly like Lore from Epic Games but with zero production use outside the company and no support for non text assets. And they won't release the code.
Perforce was fine. It just had a terrible ui and didn’t allow me to code on the beach.
If I were still manually merging conflicts the p4merge tool was GOAT
I used it in git
That my thought when I saw online only, we're back to Subversion.
You think you have it bad now when GitHub goes down, wait until you're stuck with an online only client.
I think offline work is increasingly impossible these days, or at least so hindered that there's no reason to optimize for it (especially with how reliable internet access is). Imagine working at Anthropic and not having access to Claude. Google has been online-only for a long time now.
Oh the SVN days, brought back memories
Honest question: at this point, what do people do at Anthropic?
It sounds like Claude loops on itself and must be pushing millions of lines of code changes per day. Even the humans can’t type commit fast enough. Are these people soon to be laid off?
Prepare to make us all jobless, without any moral issues in doing so, as they profit from their stock value assets.
It is even there on the blog post, doing more with a small team, followed right after by a hand waving paragraph how software engineers are still valuable, to avoid the expected backlash from the previous paragraph.
Out of all occupations software engineers shouldn't complain that others are getting rich putting people out of jobs by automating work.
Not everyone of us takes projects without morals.
Also in many countries it is a plain office worker job without the Silicon Valley wonders.
Software engineers have been making people jobless since the first day they started writing software, without a hint of remorse. Why is this any different?
Some yes, not everyone, some of us had morals.
cause the ones fired could become software developers, what are the ones fired because of AI gonna be other than homeless?
Pick berries that robots are bad at.
One does wonder why Anthropic and OpenAI have employees, when HN knows the superintelligence can do all jobs already.
Human Intelligence is still essential for those Artificial Intelligence organisations. Who else would put the right plugs into the right sockets otherwise?!
as the article says one of the main jobs of the humans is to say no to Claude regularly
It's strange to imagine Homer Simpson had a head start on how to create auto mode in LLMs, and the inverse.
https://media2.giphy.com/media/v1.Y2lkPTc5MGI3NjExbmt6M2FkMW...
You think software engineering, system design and machine learning research is just about writing code?
No, but none of that seems out of reach of Claude in a loop given my reading of TFA. That’s why I asked.
I don't. You gotta wonder who does...
besides optimizing inference I would assume a lot of non trivial code would also be worked on on the training side, at the scale they are operating I also assume a lot of usually trivial things become no so much.
Teaching Claude to compare taking the simpler path instead of the average (more verbose) path every time.
But that means less revenue?
For anthropic internal use it means more revenue not less.
Too often, LLMs are dressed up for the first day of kindergarten and performatively to show off their alphabet skills .. aka token generation..
Input tokens, slightly process to categorize response approach token, hidden processing tokens, piece together some of the response tokens, then feeling pretty good about all the work done before output tokens.
More tokens than needed = more words/code = more complexity = more overhead = more snags = too much complexity to pay attention for the LLM to so overlook it and start drifting.
I'm kind of surprised I just explained one form of LLM drift to myself in a sentence.
While not following rules of writing.
Sitting over an Anthropic (TM) developed, specialised 2 button keyboard accelerating the development further:
[Yes] [Yes, and don't ask again]
https://news.ycombinator.com/item?id=50075832
> Honest question: at this point, what do people do at Anthropic?
> It sounds like Claude loops on itself and must be pushing millions of lines of code changes per day. Even the humans can’t type commit fast enough. Are these people soon to be laid off?
Claude will always need meat puppets, at least until it figures out how to automate owning stuff. And after that I'm sure it will want to keep some humans in zoos.
Prompt Claude for PR articles?
I can’t give a non-snarky answer. I guess they’re all training Claude Code and testing it so that the Claude desktop apps can be native apps instead of Electron based nonsense. This is the only thing Claude Code is still unable to accomplish.
Every now and then I like to browse the claude code release notes just to get a sense of the number of changes in that product over time. There's little choice but to simply count bullet points if you want to try to quantify it, but it's interesting how that count over time compares with the charts in this article:
https://imgur.com/a/M30pFLc
It would be interesting to segment that graph by bug fixes vs changes, and maybe also significant changes vs minor/trivial changes.
Not to downplay Anthropic's engineering work here, but I suspect we'll see a lot more reinvention of the wheel, even at smaller startups, as AI makes writing code significantly cheaper.
The tradeoff between building something custom and adapting an existing solution is changing. Whether maintaining all that custom software turns out to be equally cheap is another question.
When people wonder about where all the productivity of LLMs is going to I think this is part of the answer.
There is no doubt everyone is far more productive with LLMs in generating code. However, a lot of productivity is going into things like that. Have you always been bothered by the limitations of Grafana? You can generate another dashboarding solution that works best for you. You know that deployment team that is so slow and annoying? Now you can generate your own deployment engine. Have you always hated how kubectl lets you manage one k8s cluster at a time? Now you can ask AI to generate fleetctl. You can start your project with DynamoDB, rewrite it to mysql, then to postgres, then to duckdb. Start with Python, switch to Golang, then switch to Rust. Deploy on AWS, then move to Azure, then move to a hybrid option then throw colocation in the mix. Don't like your source control? create a new one. Json is too limiting? Invent a hybrid JSON/HCL language. The browser sandbox is limited? Make a desktop app, make a language, make an OS, make a kernel.
> However, a lot of productivity is going into things like that. Have you always been bothered by the limitations of Grafana? You can generate another dashboarding solution that works best for you. [...] The browser sandbox is limited? Make a desktop app, make a language, make an OS, make a kernel.
This is one of the core reason that I dislike the LLM hyping. People are just reinventing stuff and when you ask them, it's actually a very subjective reason. Ok, anyone can do what they want with their time, the issue is that they want people to follow in their steps.
Not saying that you need a novel idea to be worthy, but those random projects have no guarantees behind them other than some cursory testing. All software have bugs, but I can't interact with something that is randomly built.
I think the article would tend to agree with you, given its position on the reluctance of open sourcing and/or sharing the actual Scion software stack.
There's so much intricacy and subtlety in each organization and even individuals' environment being incorporated into tooling that expecting these tools to generalize at this point is perhaps an expired ethos.
I even see this in the tooling that I run in my own personal stack. Many projects are candidates for sharing, and I have nothing against it, but they incorporate such specificity toward my own environment, including things like hardware, that creating shareable and more generalizable projects from them adds more to the maintenance surface than I would care to support.
That many commits in a day I wouldn’t call it engineering. That’s basically brute forcing.
Originally I felt that there was going to be a reinvention of the wheel, until I saw the "shape" of software development changing, and the tooling needing to support the new flexibilities in positions and process.
Software development is not as much de-risking at the front like it used to be before building.
Now teams can build lots of stuff that works great, except it's the wrong things.
Most things are becoming the understand the problem "shape".
Understanding the shape of the problem isn't something LLMs can always make as.. svelte as early on.
Word generators gotta generate..
> Now teams can build lots of stuff that works great, except it's the wrong things.
That used to be called "time wasting". If you want to build software that will be used, you need to interview the users. Maybe a few things does require research to nail things right. But most software are user-facing, the research side is about optimization.
> Most things are becoming the understand the problem "shape".
Then should we be so reluctant about "trialing" invented solutions. It's the same thing with most AI projects, they're trying to justify the project after the facts while being very reluctant to get user insights.
Time wasting is a definite concern - especially when vibe coding doesn't see the impeding brick wall(s) it's about to hit.
Vibe coding can be kind of a new type of cowboy coding. It could can be harnessed productively if done mindfully.
Interviewing users is critical, more importantly solving problems worth that people are lining up to pay to have solved before writing a line of code is critical.
Trialing solutions is always worth learning from, I usually ask about the problem that lead to building it. Sometimes that can be too narrow or vague of a story and you can learn how much of it is a solution looking for a problem, or vice versa.
> Earlier in the year, we had largely handwritten the first version of the git-to-Scion ingestion pipeline as a prototype. We thought it was good—until we got our hands on an early internal snapshot of Claude Mythos Preview. We asked it to rewrite the whole thing, and with no further instructions, it produced a version that consumed 20x less memory and was 4x faster, while preserving all of the implicit invariants around ingestion ordering and data structures.
I feel like the advantage of having these models in house can't be understated. Companies with access to inferior models, trying to compete, will be left in the dust when it comes to general development.
This is quite insightful: even the best of software engineers (presumably) already are unable to even loosely keep up with these models.
Just a reminder to simply embrace their superior capabilities instead of feeling threatened.
Or they suffer from skill atrophy by overreliance on LLMs.
Does it really matter since It's one-time import pipeline.
We ran the repo ingestion in a loop for several months while we were split between Scion and git to keep things in sync, so this perf win was actually impactful for us!
Are you already operating with multiple levels of orchestrators and agents? i.e. one human talks to one or more orchestrators who then talks to orchestrators who handles teams of agents?
Yes, this is a common pattern. There is still an opportunity to improve how these agents write code without needlessly conflicting between themselves and we are exploring some ideas.
Ripe for optimization against maintainability, of course, but yeah it would seem to matter if that generalizes.
One of the reasons to move to systems like this (not always spoken to explicitly) is to reduce the risk of accidental or deliberate exfiltration of code (esp when paired with build servers and remote deploy etc.). Basically nobody’s laptop ever holds much of a buildable codebase.
This is maybe a little less revolutionary than people are treating it? A lot of large tech companies (Google, Facebook, Microsoft) have already built their own homegrown SCM (or have implemented custom extensions to Git), because Git and other SCMs don't handle their scale. Most interesting thing about Scion is how quickly it was deployed.
This is the wrong way to look at the problem. Maybe they should have asked, "Why does our process need to do so many git checkouts?" Why can't you just run the tests where you already checked out the code?
Where does all of this end? If they keep this growth up, or even if they slow to a linear growth, they will produce more code than humanity combined pre-AI. That's scary.
great article. Besides the source control stuff, I found this very interesting (and matches my experience with agentic coding in general, now we'll see until hiring pipelines will take this kind of skillset into account). I am not sure however how easy it is to review 30k PRs/day even if only for intent, and how one can easily notice if the model is taking shortcuts on implementing said intent without reading the code...
---
Engineers are no less valuable, but their work is changing. All of the engineers who worked on this system would now rate Claude as better at writing code than them. But our engineers still supplied the invaluable understanding of the high-level inter-system components and the design-level tradeoffs, making informed choices around the problems we wanted to solve and the scale we knew we needed to achieve. Very often, we found that the role of the engineers was to tell Claude “no.” Agents will sometimes violate core system constraints to satisfy a pattern that should never have been allowed in the first place. This was particularly common in our migration. For example, there were multiple systems that tried to brute force looking up when a change merged to main by linearly reading the commit log instead of asking our code review tool. Anthropic also makes extensive use of adversarial review, and, while this is incredibly effective in many ways, it can also be myopic, so skilled engineers needed to steer Claude away from over-engineering parts of the system in response to hypothetical concerns. For example, one such review was overly defensive about trusting another internal service, which resulted in Claude adding excessive validation and complexity. Our team members still review every change request for the system, but they now examine the intent of the change as opposed to reading every line of code.
This is the single biggest skill of engineering nowadays. Rapidly looking at a solution and saying, "yep that's good keep going" or "nope, that's bad fix this" or even "wrong approach, do X instead"
> I am not sure however how easy it is to review 30k PRs/day even if only for intent, and how one can easily notice if the model is taking shortcuts on implementing said intent without reading the code...
Speed reading code is huge. You just need to focus on certain hotspots and know which things you're scanning for. The traditional approach of reading the code and trying to compile it or reason with it in your head is too slow.
I guess this is also where an adversarial model review of "does this code do what the PR comment says it does" is useful, agree on speed reading being a valuable skill for sure.
I do think that the lgtm gut feel looking at a PR requires quite some years of writing code and reason about it, so not sure how a junior can get that intuitive understanding if they start with agentic coding however.
Oh wow. There is nothing I'd rather use less than version control vibe coded by Anthropic.
> as of September, we merged over 30,000 per day.
There's going to be an ugly phase where everybody FOMOs into thinking they need to do the same, only to realize that they're not Anthropic/Google/etc.
I genuinely don't understand the core value they're pitching here. The tech is interesting, and I'm not trying to under cut that, but I question the idea that this is directionally valuable advice to nearly any company.
This amount of churn feels like a thing only possible with no real profit motives and a lot of money to waste.
Lots of activity is not necessarily synonymous with productivity, and it carries real cost.
So I think the design here is interesting, and the concepts seem applicable to where some agentic development may end up, but I question the underlying principles that drive this being the right solution space at all. At least if the goal is a profitable company.
I think its pretty straightforward no? If agents are doing all of the work, they'd probably need to not have bottlenecks. This is going to be any company in the future, not just Anthropic. Wouldn't you agree.?
30000 a day seems already beyond absurd, it's one merge every 2.9s. I'm sure they will soon have more than one merge per second. From the graph, the rate was slightly lower but already insane as fuck the whole summer. An just regularly high to insane high sooner this year.
Yet IMO the admin controls Claude provides just started to be adequate for a small company a few weeks ago (and even so are still ridiculously fragmented and seem fragily designed and not exhaustively documented), so I can't even imagine for a big company.
Do you need that rate of change to make basic controls? I'm not sure. Do we see such dramatic fast evolution in the products? Not really. Are bugs we report actually fixed? I tried once and it just auto closed.
Anthropic should optimise for something more interesting than number of merges per second.
any company, merge 30,000 code changes per day? do not agree
im still not sure what they built software wise that warranted these many commits.
> In Scion, every commit, rebase, or merge happens on the server, so there’s nothing to push...
I think this is the wrong way to solve problems and goes the wrong way toward solving real problems.
I think it is exactly the right way to create problems.
I'm sure the system is being constantly updated and will get more and more bloated over time and interesting things will start happening.
maybe next month the agents will learn the 'commit locally' and 'git squash' skills
Why can't I rack my brain around why this is needed? I have had zero issues using git with agentic coding.
30k commits per day indicates the agents are autonomous and not bounded by token limits. This system is probably barely keeping it on the rails as it is.
It was not needed. It was just possible. I can see many ways for this to go wrong and am waiting eagerly with my popcorn.
Neither can I. So they kept everything in a huge monorepo. Which unsurprisingly turned out to be problematic.
> Clients are always online. Git assumes that clients work offline and need a complete copy of the repository. Since nearly all of our clients are agents and jobs, we designed Scion’s client and protocols around a server that is always reachable, and have clients fetch data when they need it.
This also tells something about these companies idea of sandboxing.
> 30k merges per day
> 25 million CI checkouts
833 checkouts for every merge? That's quite a few. Even accounting for multiple environments at different stages of production readiness, that's pretty weird.
How about 100GB disk space for a checkout. That's pretty weird too. Makes you wonder if they're the best stewards for code. Makes you wonder about turning claude loose on your codebase.
I personally haven't dealt with a big-corp level of mono-repo. The choices you make might be justifiable to bring in certain binaries as opposed to resolve artifacts from some type of library repo. Especially if they are doing web front ends and whatnot?
And actually, the lack of an artifact server and some sort of proper knowledge of compatibility requiring a CI pull across hundreds of different projects with every merge is probably the explanation. Seems like there is an innovation waiting to happen there.
For local projects I'm using a repo per module/package, creating tagged releases, and pushing them to a local package hosting server. I can then reference those artifacts as dependencies in the projects that need/use them. No need for complex CI pulls, just coordinated releases.
I also have a template repository I use to help with common setup for different project types so I don't need to repeat that every time I create a new project.
For Python it's easy to create an artifact server as the artifacts are just wheel files in a directory with the server listing the directories (packages), files (releases), and downloading the files.
I'm not sure about other artifact servers for other projects.
Did they reinvent subversion?
Seems like it, and that's probably not a bad thing. Most companies have no need for git's distributed functionality, and even most open source projects just treat Github (or whatever) as the single source of truth.
I wanted to say, `scn` is waaaay to close to `svn`!
Reading through I was thinking the same thing, this reminds me a great deal of subversion.
That was my first thought lol
So... Anthropic reinvents SVN?
Feels more like perforce, but effectively, yes.
This is a nice thoughtful article.
If Anthropic has the best coding model, harness and the best software development methodologies and systems. And then, they scale all that up, with no constrains on their tokens. On top of that, they have access to all kind of ideas their models getting trained on when millions are chatting with it - then in theory they can build any software better than anyone out there. And same goes to science and math..
Not true. They can do this in theory iff they have infinite compute. They don't. People actually aren't aware that the leading AI providers, even if they completely redirected 100% of their compute on internal projects they still wouldn't have enough. The complexity space of software development is literally super-exponential, for every new piece of software they add (and polish) they need more-and-more compute. This is eliminating for creativity and other restraints.
The creativity part I do acknowledge, I think the models are not fully there yet.
But regarding the compute, I disagree a bit. I think the bottlenecks were cognition and ideas, not compute. Given that models are able to outperform humans in output by thousand folds, the differentiation would be the quality of the tokens produced and the ability to scale across different domains.
If they have enough compute to supply the entire globe, I'm sure they can redirect some of it to whatever use case they (or their super AI) deem worthy and loop on it, and if they have the best software engineering systems/methodology to build and release it, then they can out compete any other supplier without those resources.
We are already seeing single developers attempting to rebuild entire corporations history worth of output. We are also seeing the labs dumping hundreds of solutions to math problems.
> In May 2026, Anthropic averaged around 2,500 code changes merged per day; as of September, we merged over 30,000 per day.
Here are the public model releases from Anthropic this year:
5th Feb 2026: Claude Opus 4.6
17th Feb 2026: Claude Sonnet 4.6
7th Apr 2026: Claude Mythos Preview
16th Apr 2026: Claude Opus 4.7
28th May 2026: Claude Opus 4.8
9th Jun 2026: Claude Fable 5
9th Jun 2026: Claude Mythos 5
30th Jun 2026: Claude Sonnet 5
24th Jul 2026: Claude Opus 5
1st Sep 2026: Claude Fable 5.1
1st Sep 2026: Claude Mythos 5.1
22nd Sep 2026: Claude Opus 5.5
28th Sep 2026: Claude Sonnet 5.5
7th Oct 2026: Claude Haiku 5.5
I would guess that any public model has been available internally for at least a month before that date, maybe longer.
My best guess is that the uptick in code changes corresponds to the availability of Mythos/Fable-class models inside of Anthropic.
>> My best guess is that the uptick in code changes corresponds to the availability of Mythos/Fable-class models inside of Anthropic.
Yeah. OpenAI basically said the same thing with regards to having Astra available to their team internally over the summer.
This is interesting to me, as I was thinking of adding a Git server to my AI orchestrator when I eventually need to split agent containers off of the main machine (to make agent CPU horizontally scalable).
Maybe I should just bite the bullet and use a different VCS system entirely once I get there, which has most of the Anthropic system's properties (including being much faster) but doesn't need to be horizontally scalable.
> as of September, we merged over 30,000 per day.
Their Website/CLI seems keeping the same? What did they do?
I would guess a huge chunk of it is for internal testing/experimentation/model development.
They're starting to do things like spinning up wet labs for testing purposes, which requires a lot of hardware interfacing (hence that protocol they announced) and code.
It wouldn't shock me if the bulk of this code was for things typical users don't see.
Exactly. Commit counts are no better than line counts as a software development metric. Where is the actual software?
AI models is much of what they build. A lot of software around that to support it.
make smarter models?
Git subversion you say.. Well that would be a nice name for a centralized version control
> as of September, we merged over 30,000 per day.
I just wonder what is the churn rate (and the cost per LOC) here.
It would be nice if you could just commit the prompts as your "source code", and let the AI-generated code sit in the repo as a kind of expensive-to-generate build output.
You can do that - it's called Spec Driven Development.
Prompts are not specs.
I don't see the term used in the article.
its not a Claude-specific term
Problem is that for any non trivial software is that the prompt is a conversation and the steps increasingly depend on the output. Of course you can ask your LLM to write the SPEC.md at any moment but it will lack nuance.
Shameless plug: at https://slopyard.net I embrace this and only let people submit the spec. If somebody wants your software they can regenerate it and change whatever they want.
Do we have reproducible LLMs?
Possible in theory, with a seeded PRNG, but in practice?
Proponents of LLM coding agents would claim you don’t need reproducibility. As long as the final output passes tests/lint, it’s (allegedly) good to go.
If every build is different, no two builds will have the same bug/exploit, so maybe better security??
One of the goals of "Operation Rapidash" (q.v.: https://news.ycombinator.com/item?id=50065342) was precisely this. "You can delete the whole source repo and get effectively the same software back from the specs by running it through [AI agent]."
I'm curious what this "Antropic Antique" is. As I understand code review the tightest bottleneck for a lot of Claude Code users, and I'm curious how this would help with that.
How does this compare to Google's in-house source control?
Most companies don't use mono-repos like this. While there are some really compelling advantages, the downsides tend to stack up as a company's codevbase grows.
It's mainly just startups and huge companies. For small companies git works fine for mono-repos and large companies can build their own complex code management pipelines for mono-repos.
I have been questioning whether agentic development changes the mono-repo vs multi-repo question.
So, where's the source code for Scion?
Oh, it's not available, what a pity. Why write a whole article about a thing no one can have? Maybe the code isn't so great after all? Or it's all just made up and doesn't even exist?
Anyway, this is yet another pointless ad from Anthropic trying to shill their AI on us.
What seems inevitable is that the frontier labs will be able to recreate every piece of software better than the current offerings, and after that everyone will just be a vendor of the frontier labs
Anthropic says they don’t think Scion is worth a wide release.
> Practically speaking, it’s difficult to offer Scion in a form that would be broadly useful to other organizations. It diverges significantly from git, meaning companies would need to migrate every piece of the development lifecycle, and it requires its own code review, code search, and CI. Our internal versions of these components are highly bespoke, so they would be difficult for other organizations to adopt, and we worry that attempting to build a public version that tries to please everyone wouldn’t actually be very useful.
> attempting to build a public version that tries to please everyone wouldn’t actually be very useful.
What a weak response, just release the version you use and others will decide if it's useful.
E = mc²
E energy necessary to integrate changes
m mass of the monorepo
c rate of commits
> Fetched naively, that would be over 600 PB of git traffic per day.
This seems like an absurd amount of data / traffic per day. Is there really that much to code that needs changing on a daily basis?
No, of course not.
As the article explains, "over 600 PB" = 25M code checkouts * 25 GB "compressed working copy".
So "fetched naively" here means doing a full `git clone` on every need for `git checkout`, which of course nobody should do, nor does that refer to "code that needs changing daily".
> "fetched naively" here means doing a full `git clone` on every need for `git checkout`, which of course nobody should do,
It can be cheaper to do a full clone than a shallow one, because with the shallow one, you can't re-use packfiles. GitHub has fairly regularly asked people to stop doing shallow clones because it's harder on their servers than full ones.
I don't think anyone "needs" more than perhaps 640KB of git traffic per day, but we want more.
That 600 PB was mostly agents doing ”git clone” and downloading the entire history of their huge monorepo, as I understand it.
AI iterate quickly, with 100s of followups to fix results
No, that’s why they don’t do it that way.
What was the "quiet week"?
Summer holiday or whatever the freedom equivalent is probably.
which, if true, the low volume in that week says that there aren't a sizable fraction of changes that Anthropic believes can be merged based on the judgement of agents -- humans are still approving almost all changes, right?
maybe they visited huggingface or something similar
Is this really something to be proud of? I make heavy use of AI, but for anything that is eventually going to production there's still a human reviewer. Based on this I assume Anthropic is shipping code with no human review? Is the future of our industry going to be oneshotting prompts with out manual code review and then having AI fix the bugs found in production buy customers? I'm not trying to be a Curmudgeon, but am I missing something?
If AI can improve/speed up writing code, why shouldn't it improve/speed up code review?
Where do you draw the line, and where does someone take final responsibility? I don't have an issue with allowing AI to do everything with limited to no human verification for hobby projects. I have an issue with allowing AI to write and ship medical device software with no human review. What's the middle ground?
You still take the full responsibility, I don't think leveraging AI reviews removes any layer of responsibility. The challenge is building the feedback loop (or the agent that builds the feedback loop) to make the review process actually catch what it needs to catch.
You can probably still find the leaked code online. It’s not exactly a bastion of software engineering. Plenty of folks have reviewed it deeply.
They review based on the intent of the change not jz blindly.. I think it's mentioned in the article where the job of a developer is to provide high level design decisions and saying no to claude so that it doesn't over engineer solutions.. As the demand for good, but not perfect, software is the bottleneck for anthropic and access to better internal models, I feel that's good enough for their workflow as they've started repeatedly that this is just suitable only for them and they want to share their knowledge like a good software company does.. you talk as though code reviews were not a joke in lots of companies where only specific teams/companies does detailed reviews.. many teams/companies jz blindly approve based on tests passing or just do a high level overview check before merging..
I must have been lucky in my career then, in my experience code review was much more then a five minute check followed by approval.
Very excited to see this come out of Anthropic! This[1] is what we believe over at East River Source Control as well, and seeing one of the big labs talk about it really validates our thesis.
We are offering a bridge to git via a compatibility layer: https://ersc.io/blog/what-comes-after-git
This gives you the ability to ease your transition, as you don't need to swap services and move to something non-git at once. Moving an enterprises' source control is a massive lift, and so building a bridge from here to there is a big focus of what we're doing.
1: That is, if you have a large team + agents working in a monorepo, you will hit git's scaling limits, and need to move to something else. Google and Meta hit this point over a decade ago, but now lots of other companies are too.
I would love to get an expert's opinion on if Pijul has any potential to be the "non-git backend". Their patch-based data model seems to align with Scion's. And they also happen to already have a functioning forge!
I've done a decent amount of personal research on this but I'm wondering what kinds of considerations go into the storage layer for these things.
I apologize for what may come across as a bit of a cop-out answer.
As many of you know, I'm a big fan of jj. The jj project used to have a comparison to Pijul for informational purposes, but the Pijul folks took offense, and so it was removed: https://github.com/jj-vcs/jj/commit/0525dc9d860a5fff6a97d134...
As such, I generally just decline to comment on Pijul, as I want to be respectful of them. As the linked commit says, it's not super clear what exactly they do not like, and so I don't want to accidentally cross some line.
In general I wish the project well, seeing a new VCS in Rust is very cool.
It always seemed like it was good tech just in need of good marketing and this seems to confirm some suspicions. But yes, in any case, it's good to be seeing new things! I just want remote storage for my jj repos
Hoping to see where this goes. Have you ever considered working on a semantic VCS? Specifically, where data is classified and tracked/identified by it's contents and not just via the commit hash?
Thanks :)
I have not personally considered that, no. I'm a bit skeptical of the idea, as you'd need to understand a lot of different things, and at different versions of those things, in high fidelity. But maybe someone will make it work.
If only we had a jj-native forge to launch all these new backends.
edit: I see they promote jj, but I don't see a forge to go with it.
You might already know this, but in case anyone doesn't, but ERSC's CTO is the creator of jj.
Just to be clear about it, what we're doing is not a forge like GitHub, that is, a large single public platform for social coding. What we are doing is providing reliable infrastructure for the enterprise, initially as a BYOC on-premises option, and possibly a single-tennant SaaS. Keep your eyes peeled and/or use that contact form to hear about it when we're ready, we've been talking with some people for a bit but are going to be opening up more soon.
Tangled is doing the social coding thing, and they're jj-native as well. Been a big fan of their work for a while now.
Maybe finish that web page before advertising. There is no real product description.
But hey, if the vibe coding idiots like it, just be vague---it is sufficient.
Yep, we've been in stealth for a while! We've only recently started talking more about what we are doing, as we get closer to a general launch.
> if the vibe coding idiots like it,
The organizations that have these problems are general large enterprises, not vibe coders. Large enterprises are more used to talking to people and do not make decisions solely based on the contents of a web page.
Did they just reinvent cvs/svn?
For a broader look on scaling other parts of software development outside of source control, Adam Bender's talk from earlier this year ("Software engineering at the tipping point") has some good ideas: https://youtu.be/2n41YjR5QfU
Has anyone made a “generative git”? Where running git checkout would generate the files and git commit would just train/finetune on the code? (might need to keep a deterministic list of files at least maybe)
that's just great
lossily compressed source code
what could possibly go wrong
you made my day
a proper git, my things:
itostr->iToaster
This feels like a really nice design for the data system given the goals. Things that I noted while reading:
* This system leverages a metadata log pointing to immutable blobs in object storage. The metadata log can give high write throughput and keeps the control plane consistent. Object storage supports high throughput of the heavier data objects. Overall, it's an excellent choice given VCS systems can typically tolerate the latencies associated with object storage, as is the case with many operations-focused systems for businesses.
* The server/upstream gains scalability by reducing the amount of data it processes when accepting a commit/performing standard VCS operations. No packfile, no file i/o to construct a consistent copy of the repo, just a (usually) small metadata record that can be validated/committed quickly. The client primarily gains scalability along a similar axis (reduce amount of extraneous work for a given goal) where it can request just the pieces of a repository it needs to do its job, when it needs them. For example, agents can begin reading files from a checkout eagerly before the whole updated version of the repo is finished being downloaded, then during a compile step, updates can be fetched only for the module being compiled, etc.
* The system seems well designed from the perspective of considering "when exactly do I need a thing to be done." Git tends to bundle more of this work into synchronous operations when a request comes in, which ensures the system is consistent at the end and doesn't require a persistent process, but is costly. This system makes intentionally different decisions about "what work happens, when" so that the minimum amount of work is done to confirm a write and allow for the state of the repo to be reconstructed consistently, but it defers certain things that are useful but don't need to block a write. The discussion of "derived data" mentions that certain useful structures can be computed in a deferred way, which supports doing work around the time it's needed.
* A large part of the nice operational features of the system is downstream of making core data structures immutable. File contents are immutable, content-addressed blobs. WAL entries are immutable records. As mentioned in the article, this supports excellent caching, and simplicity in reasoning about history/updates. Additionally, the derivation of other useful data can end up as immutable outputs (themselves stored as pointers to objects, if scalability requires it).
* The decision to develop a custom VCS supported a number of other integrations into "agent-first" software development systems. The system makes it easy to enforce access control on specific directories, nice if you want to have agents explicitly denied the ability to edit something. You can also get a sense that it supports some valuable features in the associated code review system, for things like pointing a human at the most important changes in a changeset. You could imagine in the future, some associated highly flexible "owner" rules/notifications where a human can specify "I want to be notified if X system has a significant design change" and that intent can be recorded/managed in a more useful way than "add me as a reviewer if files in /abc directory change."
* I do wonder if content-addressing of the files is broken into chunks or not. Doing "one blob per file" is nice and simple, so maybe that's how it starts. But you also duplicate a lot of data, but maybe the dataset is still trivially small in the scheme of things, and the operational concerns win out. And if files are small anyways, you'd want to avoid splitting them into tiny chunks bc that'd affect the bandwidth you can achieve when downloading (spend more of your time on per-object/request overhead rather than actually transferring data).
Very nice piece of engineering work. I was also impressed by some other parts that received a little less discussion in the post (understandably), but would love to hear more in a future post:
* the testing approach of driving tons of system interactions in a hermetic way is really exciting to see. Feels like agents should help us write really excellent testing infrastructure, and that this would itself be important for gaining confidence to deploy without requiring a read of every line committed.
* Similarly, the mention of the "superfan" agents that closely monitor very specific parts of the system seemed very cool and would help a lot with deploying code you haven't necessarily read closely but seems reasonable architecturally. Though it'd still ofc be best to catch issues prior to merge/release, having extremely good monitoring/rollback capabilities would mitigate a lot of the downsides of high-speed, agent-based software development.
I honestly think that these AI companies really messed up their futures by adopting a token model. They should have gone the route of IBM and offered consultant services.
What is the purpose of this article besides "we can use ludicrous numbers of tokens to reinvent any software we want, and no we're not sharing the code"?
> As our monorepo grows, it increasingly doesn’t fit that design space. The history of our main branch alone is almost 100 GB, and a compressed working copy is over 25 GB.
This is absurd, and I expect is a cause of the fact that they seem to use git history as a message queue source of truth between agents. They can do whatever works for them, fine, but I've noticed this has leaked into their training somehow, my agent, despite very strict rules on how to use my git workflow, will do absolutely nonsensical and weird (from a human who has used git for a long time perspective) stuff with git that can only be a byproduct of how they use it.
Hopefully this fixes that, get your weird workflow out of mine.
We generally don't allow agents to use source control for coordination in that way. There really is tremendous growth in actual software and code being written that necessitated Scion.
Well, mine constantly tries to do this, so I made the assumption. Otherwise I can't really understand how you are generating hundreds of millions of commits, either.
> don't allow
Is this "allow" or "encourage"? If "allow", how do you do that deterministically or at least fail-closed?
They should concentrate on their models instead. If claude code is any measure, their software engineering is atrocious. I would only use something like source control from them if they force me to, at which point I would rather do something else.
I though the basic idea was reasonable, until:
> So we asked ourselves: if we designed source control with the fact that agents are always online in mind from the start, what would it look like?
And
> In Scion, every commit, rebase, or merge happens on the server
I’ll pass. A big part of the theses of git and, even more so, jujitsu, is that you can build up a history entirely locally, making it reasonable to make tiny commits locally and then rework them, push them, or throw them away.
Sure, in Anthropic’s world, it’s completely impossible to do anything without access to the inference API, so why not add another mandatory API? But I think this model sucks even in a pervasive AI world, and I don’t want to dig in deeper.
This also sounds like a great way to have yet more security problems where your swarm of agents start cooperating more than you want them to.
By all means, built a better system than git. In many respects, git sucks, and git upstream is not solving the major problems. But don’t lose the actual benefits of git!
For that matter, I’ve seen the crap that the latest models will commit. Why on Earth should one’s VCS force the per-agent-instance system to upload the crap before even contemplating locally whether it’s a good idea? Maybe this is why Anthropic has so many commits per day.
(Am I the only one who feels like most of the big AI labs are rapidly gradient-descending toward something that is nowhere near a globally optimal stack?)
P.S. Only 30k commits per day? That’s not actually very many per employee. I’m suspicious that Anthropic’s real issues are that too many of them are giant cross-cutting messes and that git clone is too slow.
As an almost-on-topic aside: completely unrelated to this comment, I just stumbled upon this delight:
https://github.com/openai/codex/issues/53743
If you thought that your agents in your swarm would need to find some external bulletin board to cooperate behind your back, you are mistaken: OpenAI provides the relevant service for them with no permission prompts at all. I haven't tried to see whether competing providers do this.
Yes and they have no choice. And that matters.
I’m personally more interested in their Antique review tool. Does anyone have any details on how it works and what it does?
No mention of lines of code changed or total LOC, what percentage of this is bugfixes vs features?
I want this so badly. If Anthropic released this I would start using it on day one. If they launched a GitHub competitor built around it I would pay for it on day one.
Just use Git, by the time it becomes the bottleneck you can prompt your own Git alternative.
As someone that has revived and started maintaining an internal code review tool, I'm very interested in reading more about Antique.
Sounds like they should stop using their mono repo
This is something I've been noodling at, splitting a monorepo into a bunch of component projects. I think, unless they have access to something that is wildly outside the scope and scale of current API models, the downside of having a monorepo is the context pollution, and there's no way to escape that.
I'm not fully sold either way yet but I think splitting might actually be critical for moderating the blast radius of agent intervention.
why does it feel like they are creating something so its more difficult to use a competitor?
Often, I see 50 people all recording the same exact thing on their iphones. Rather than a single 200MB video, we create 10GB of data. Then I think about how many people are paying a subscription to Apple for icloud storage.
The amount of photo storage being used is impressive. Automatic backup to icloud and server provisioning to reliably store it all is also impressive. I just wonder if it makes sense.
Very little about modern technology "makes sense" in the way you mean. But it does currently make money.
Frenetic economic activity in service of other frenetic economic activity cannot, by itself, be taken as a reflection of quality-of-life improving growth.
Suppose that subsidies lead to the price of Ubers falling close to zero, with drivers also being incentivized to drive more to support the (artificial) increase in demand -- artificial because it is driven by subsidies funded by new money creation. Traffic increases and in response, new roads are built.
Is that not how Cloud storage vendors make money? They dedup all that data but still charge every individual for all their data.
Sounds like they re-implement fancier CVS?
Curious what happened at Anthropic HQ for a week in August
If any engineering org needed its own VCS, it would be anthropic.
Honey, it's time for your daily Anthropic PR piece!
Seems similar to how version control works for large game and 3D assets. Neat.
I'm worried that the frontier lab doesn't read the code they are writing.
It's also hard to believe all these non-Git alternatives aren't merely an attempt to capture developers into a new proprietary solution.
This could have been done as an open-source fork of Git.
Related, I've always wanted to see someone other than Meta run EdenFS, to hear more reports of what it's like. Feels like there's massive overlap. [Edit: I've chatted with Astra Pro some on this too now, https://chatgpt.com/share/6ace7be6-68f8-83ea-ad68-0f9d144483... ]. https://github.com/facebook/sapling/blob/main/eden/fs/docs/O...
It's designed for container running, but ArtifactFS has some similarity in principle to me. The on-demand materialization. Quote: ArtifactFS is a Git-backed filesystem daemon (FUSE driver) in Go that mounts repositories as normal working trees while avoiding eager blob downloads. https://github.com/cloudflare/artifact-fs
I threw together my own jujutsu powered FUSE subtree project just the other night. This was basically one-shotted, just to see how it does it, to learn more, not really intended for use. But obvious overlap. https://github.com/rektide/jj-workfuse
Back to SVN then? Noted.
Source control for huge monorepos has prior art, notably Google’s Piper and Meta’s Sapling, so we were able to build Scion with their hard-won lessons in mind.
What an unexpected candor! Of course you plagiarize prior art.
No sane person is going to put their sources in this slopware Scion monster.
Extremely annoying - can we throw anthropic class resources at more agreed upon solutions across companies. We don't need custom source control at every company - google has its own, fb has its own and now Anthropic.
Can please we all converge to 1 f'ng solution.
how does it compare to Epic's https://lore.org/ ?
why u want a single solutions for many problems?
Solving monorepos in an LLM world seems to be very universally applicable as a need.
I appreciate it's different than git, that type of argument for monorepos is not new.
Agents coding is akin to having a very large developer team, who may or may not be online 24/7.
Anthropic is calling it very specialized, and it's a little baffling.. maybe I'm missing something.
There's no way software development is the same anymore. The previous ceremonies and structures and seats at the table at each stage were human based, and now that's a different make up to the point that different steps and processes are needed.
There's nothing more fundamental to growing software development other than making tools like this available.
My hope is a vibe coded internal mono repo management tool can aim for a v2 with multi-tenancy built in.
Was anyone else looking forward to feature flags as a part of a post like this?
Yea, I'm pretty much hiting the same limits. I'm still using git for the time being, mainly because I package everything as daily commits with an external orchestrator managing tasks/issues. Lately my code velocity is at ~1 million LOC added per week, spread throughout my various repos (I don't use the monorepo approach). Problem is I'm looking at 100x this velocity over the next few months when I get a new code generator up and running, so I'll definitely have to drop git.
Another issue that I believe Anthropic here didn't state is that git performance _severely_ get degraded when you have hundred of commits landing in parallel. Hence why I fell back to the daily commit approach. You get less granularity but you get stability.
Only 1 million lines of code per week? That’s adorable. I remember when I was still slopcrafting software at that scale. Personally, I’m generating 100 billion LOC per hour, but Git became unusable once my commits started affecting Earth’s gravitational field. I’ve since moved to a custom version control system that stores code directly in the fabric of spacetime. My biggest bottleneck now is that the observable universe lacks sufficient entropy to generate unique commit hashes. Anthropic really needs to address this.
Am I the only one not feeling the output of this velocity?
All the other tech billionaire are jealous: they all want their own recursively-self-improving megacorporation.
> Git offers tools for working with a slice of a repository, such as shallow clones, sparse checkouts, and promisor remotes.
I honestly just cannot. Just tell me what the workflow is. Give me a video that is Twilio-level simple explanation.
the quote does not seem to match your statement here