Comment by avinoth
2 days ago
This is like one of Google’s infrastructure blog. Google scale things are only relevant and appropriate for them. We had lots of bitter lessons from smaller engineering teams following the process with the justification that “this is how Google does it”.
Similarly, Anthropic can afford to do this because they have virtually unlimited tokens and labs to train models for their specific usecase. The rest of us need code comprehension lest we become dependent on continuous supply of tokens (which is a state these labs badly want to achieve)
So, unless you work at a lab, or have unlimited tokens guaranteed through the life of your company, it would do both the company and you good to continue to read the code and not let these 30k PRs per engineer be the norm.
An excerpt from the article makes my point
> Nobody on the team keeps a complete mental model of Claude Code in their head, and we don't think anyone needs to. When someone wants to understand a part of the codebase, they ask Claude to write an explainer for exactly that slice. It takes minutes and reflects the code as it is today.
Even then do we really have evidence that what they are doing is reasonable or practical for them at all? They are edging on like 3 9s uptime, what leaked of Claude code looked like soup, tons of security issues, they can't build a sandbox to save their company, and last I heard they aren't even profitable without adjusting their numbers for arbitrary things.
Think I'm good on taking advice from companies that aren't making money.
Exactly. What they’re doing, repeatedly, is setting a narrative that this is how software engineering should be. Always be reliant on tokens. Don’t worry about uptime or errors - agents can address it, don’t worry about security - agents can address it, don’t worry about code comprehension - agents will always be there for you.
Nailed it
> agents will always be there for you.
In Romania an investment fund (FNI) around 2000 ran some super famous ads saying "FNI is watching" (FNI is keeping watch).
6 months later they went bankrupt.
[dead]
If they're cash-flow positive with 75% of compute going to research and training, what do you think will happen to cash flow when they shift to 50-50 training-inference?
Because "pacing the frontier" is more about flipping on the money printer switch than it is about safety.
> they ask Claude to write an explainer for exactly that slice
If their Claude is the same as our Claude, then this is a joke. Claude’s writing style is insidiously mind numbing. It takes constant pushing to get it to explain things in digestible English.
It also mixes important with unimportant information. It tends to think that a commit/bugfix is important and will happily list it together with important properties of the feature.
At least Opus 5.5 does that. Its writing is better than that if other models, though. I had other models explain stuff in an undigestable language, technically correct, but practically not what anything is about.
I hate it when it realizes something that was contextually obvious to me, and then treats it like a precious nugget of wisdom, including it in the README, the comments, and the commit message. Even worse when it’s a hypothetical situation. “Even if the raw chicken is bagged and refrigerated, we want to avoid a leaky bag.”
2 replies →
It's like it's trying to impress you with poetry in comment: "What the function does, it does well, and only just once"
Try having it explain something in “ISO Plain Language standard”. It made an enormous difference for me yesterday. The language will change from dense large paragraphs to simply-worded 2-3 sentence paragraphs. I was using gpt though.
Even getting it to write less obtuse English isn't enough IMO. It seems to have real issues with structuring documentation in a way that makes it easy to follow. Also it's a real demon for leaking its context as implicit assumptions into documentation.
v5.5 eliminated much of the impenetrable prose of earlier versions.
> v5.5
You don't still feel that mental friction when 5.5 responds with a wall of text and you drop into that first tedious sentence? I even had it generate a syntactically invalid English sentence the other day. It's still pretty bad.
It’s better, but still worse than OAI’s models in my experience
Or we’re just getting used to it.
The people who work at Claude seem to talk in claudlish, so I doubt they care.
They pretty much fixed that. Plus you can influence the writing style to some extent. I tell it to use full sentences and avoid assuming I already understand the code.
Another thing is that it's very good at creating diagrams (I think someone wrote a skill for it so maybe not by default). I usually find the diagrams are even more valuable than the text.
Honestly I was skeptical but you really can just point Claude at some code and ask it to make a markdown + SVG explainer and it will do a shockingly good job.
I'd still rather read human documentation, but even before AI almost nobody writes any - especially for internal code. And they certainly don't make great diagrams.
I’ve been using diagrams a lot lately. My team currently owns a wide surface area, so there is a lot of mental context churn as we bounce between parts of the system. HTML diagrams, or artifacts in the Claude desktop client, are super for helpful for bootstrapping/refreshing my mental model when starting a new project.
Your Claude Code terminal now renders Images, LaTeX, Charts & Diagrams Use this mod I created: https://github.com/razorback16/cc-intelligent-ui
If we as engineers didn't use similar terminology to describe any code not written by ourselves for the last few decades perhaps people would take it seriously.
Claude was trained on engineering wittering.
1 reply →
[dead]
But the words are all right /s
If it was an exception only… but it is so common that I had to put ASD-STE100 into instructions to have precise answers.
I have heard from someone who works at Anthropic that they will have postmortems that sometimes devolve into "my claude says X" vs "well my claude says Y". Maybe this is the future of software engineering, but it seems pretty fucking sad.
Seems like a good time to get a third Claude to hear the cases of the first two Claudes and break the tie.
Make it five so that you can write a blog article about how your use of AI is extra-secure and top game.
This is basically just being a manager in the before times. "My engineer said X!" "Well, mine said Y!"
Which is fine, whatever, I guess this is how I pay the mortgage off instead of having any clue what the hell Claude is actually writing. Hopefully I can semi-retire soon and go study dunnarts or take up welding or something else that's more rewarding than this nonsense.
I would love to ask them why this scale is even necessary for a conceptually simple CLI app like Claude Code, but they wouldn't be able to answer because they don't even understand the scope of it apparently.
They do have quite a few products now, the desktop apps, websites, cowork, cloud session sandboxes, API, enterprise, etc. have their own gotchas, but after a core development, the 30000 commits a day does not feel justified, or is that an online training dataset prep, that's hard to tell. That's why I feel with their endless tokens, it feels just petty marketing and that's sad because it does not bring much to our engineering table.
It's absolutely insane that they can't keep track of a CLI application that makes shell calls. This is so far from rocket science even mentioning the term is misleading.
To be fair, rocket science is also easy. You just combine a propellant and an oxidiser in a reaction chamber.
In fact, everything is easy when you summarise it in one sentence and don't think very hard.
6 replies →
[dead]
It needs to gather a bunch of inputs and feed into the remote GPUs correctly and as efficiently as possible. Lots of room to optimize under the constraints that users love cheap tokens, demand a fair billing structure, and want responsiveness and low latency.
Is Claude code just the cli or does it include a bunch or backend services supporting?
It's also a desktop app, integrated into the mobile app, and it has cloud hosted session capabilities too. Plugs into Slack and Github, maybe others. So definitely there's backend stuff as well, beyond the inference.
[dead]
I don’t think you can infer the scale for Claude Code alone. They said it doubled but not what the starting point was. The 30k figure is for the entire Anthropic monorepo.
Well I personally didn't say anything about 30k PRs. I still stand by my belief the "known" scope of Claude Code doesn't seem to warrant the scale of "vibe coding" and lack of comprehensive understanding they are communicating to us.
30k commits going into a monorepo would make me want to kms having to rebase the fucking PR's every 35 seconds.
> Nobody on the team keeps a complete mental model of Claude Code in their head.
For sufficiently large codebases in large organization that is how it has been with humans, who come and go. In many respects, What Anthropic is doing is a massive upgrade from the status quo.
Yes this is absolutely true.
Another challenge is getting developers to stop assuming they know what the code does without reading it! Having AI “fact check” various documents against the source will help immensely.
Best developers can run the code in their head without referring to source. It's called a mental model.
Really? Hundreds of billions of dollars in debt is an improvement? The product that this code is supporting can't even pay for its debt.
Jesus. Give me 1 billion dollars and I'll keep your entire codebase in my head + personal notes for you until I die. Hell, I'll even force my descendants to do the same. Now _that's_ an improvement.
Pharaoh vibes
> Really? Hundreds of billions of dollars in debt is an improvement?
We are not debating Anthropic finances in this article.
1 reply →
It would benefit many people (especially Anthropic employees) if, after an LLM gives you a response like this, to go into a different session and ask another LLM if the explainer is correct. Not just so that you hopefully get the correct information, but also to see how easily fooled you can be by a plausible-looking, confident response about some code that you have no reference for. Use 5.5 on any thinking level, you will encounter this. The spaghetti mess that is CC likely makes this more of an issue.
Google's infra genuinely pushed the industry forward though, things like kubernetes and SRE methodology are generally useful even if you aren't Google. Reading this I'm not even sure this sounds like the best way to run an organisation with infinite free LLM tokens let alone an actual engineering org where it just an impact on development cost. The people who are getting maximum leverage from LLM reasoning and routing queries intelligently who've made big strides in reducing inference while increasing throughout are the ones who impress me the most.
[flagged]