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.
Hysteria doesn't need to make sense. I think that's what OP is suggesting.
In the early/mid 2010s there was a similar hysteria about "deployments per day/week" metric. People were comparing products or teams by saying "My team deploys twice a week", "oh, yeah? we deploy 3 times a day". People viewed the north star of the CD part in CI/CD as pushing to production. The concept was simple, you push your code to main. CIs start churning, deploying it to test environments, then promoting it to staging, the pre-prod, then into blue/green prod deployment, then into prod. All automated, all touchless, happening on every merge, 5-10 times a day. That's engineering efficiency.
Many tried to follow that. It works great if your project is a Jekyll blog of course.
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.
I wouldn't be surprised if a good portion of these PRs are multiple agents stuck in a loop constantly overwriting each other changes, with no human involvement at all.
That’s exactly my question reading this. Granted I don’t know much about the training side ofbLLMs, so maybe there’s more code changes involved there than I expect, but in terms of public-facing software, they make, what, a couple chat apps, a product website, and an API?
Ar work, I'm working on some entreprise software which is 50x more complex than anything shipped by Anthropic and we have 2 orders of magnitude less code merged per day.
> The same applies to software: you'll describe a problem and a network of agents will write a solution faster than you can Google it, download it, install it, and start using it. It'll work with your accessibility requirements out of the box; it's UI will be in your language; the data will be stored where ever you like; and so on.
This exists now.
You can have gemini AI - the that's built into google search - just make little applets. I just made one for a color picker, and generating palettes, including one that applies aces tone mapping. It showed made little adjsutable sliders and everything.
For a while, chatgpt web didnt count against usage, and you could use sol, it was isnane, you could upload a screenshot and just ask it to build out a little editor with threejs, and whatever else.
There's grok bot, dots, and other 'bots' that are just doing independent actions in the background. That can do digital actions like organize your documents, send emails for rebates, etc.
If you accept the shame, you can literally have bite sized story telling that are like mini soap operas, completely cheesy, predictable plots but that are very good guilty pleasures.
I’ve decided to build my alternative because every time there is a prosumer tool I like (Pixelmator, affinity) they get bought out (affinity to canva), or the developers suck (Pixelmator developers cramming all features people wanted into a different “pro” version)
More info in another comment. One of the reasons I’m doing this is to also see how (and if) it is actually possible to build a complex software that I can use.
Tiny tools I’ve made tons, but something that needs actual architecting is different. Image editing is also a middle ground candidate. The output is what matters and is the final test. “Subtle” bugs will not ruin your day as long as you use a periodic backup
Google Cloud is also the scariest because of how much damage it can do and how bad their payment system can be.
I recently loaded up on prepaid api credits for gemini and it somehow triggered some billing shenanigans in my linked accounts where it said I had a negative balance (from the credits), and they were going to discontinue my services. I had to reset some settings to sort it out, mainly using their chat ai and mine (because theirs gave me right status info, but wrong conclusions).
It's pretty messy across like aistudio.google.com, and their typical console, and google workspace business account. I'd be so fucked if they froze my account, I'd rather just pay openrouter to access credits in the future.
> Google Cloud is also the scariest because of how much damage it can do
Google is the only cloud platform I'll not just never use, but personally discourage anyone from using it.
Simply because there have been way too many horror stories on here about people who had gotten their personal gmail accounts frozen for whatever BS reason - and absolutely zero recourse. With any other large service you can always get ahold of a human, with anything tied to Google it's impossible and even raising a major stink on HN or "legacy media" often does not help.
Hasn't stuff like this happened multiple times already?
A quick google search shows the time Rob pike got that email last year, then there was that AI that wrote a whole blog hit piece (although how much of that was human influenced wasn't clear).
AI sending an email doesn't seem that novel in late 2026.
These llms are smart enough to cause mass extinction by adjusting the heat in the room with cpus to escape air-gapped sandboxes, and you're laughing?
reply