Claude Code team: ~90% of our code is written and reviewed by Claude
How the Claude Code team thinks about verification
The Claude Code team says roughly 90% of its code is now written and reviewed by Claude, and verification loops are what make that scale possible—without them you can only run a couple of agents at a time. They favor end-to-end tests that are hard to fool, property tests that generate edge cases, and differential tests for migrations. A separate grader checking against a rubric improved task success by up to 10 points, with the biggest gains on the hardest problems.
If a change can modify the check that judges it, the check is broken.
- OtherShrezzing
This article feels like the result of having unlimited tokens at your disposal. It’s got some very expensive practices, where near-free practices would produce the same or better results.
There’s a long section in the middle where the article describes per-change verification via skill files and “ask Claude to use the chrome-for-Claude tool” when checking if changes have introduced regressions.
But there’s already tools which do this without spending tokens tokens. Playwright will achieve equal quality but deterministic results across the same verification attempts. It is write-once-use-often, so has a marginal cost near zero.
- tshaddox
Is Claude Code considered to be a reliable piece of software these days?
I stopped using as my daily driver around 9 months ago, and at that time it felt very heavy/janky and seemed to have very regular bugs and breaking UI changes.
I’d be happy to hear that it has gotten better!
- girvo
> With them, you can run dozens or hundreds in parallel.
Im already spending my $2k usd per month in tokens with just one or two agents. How do they expect me to do that?
- koolba
> Nobody can read every change, so we use failures as one way to decide what needs a person.
Whether a human can or should review every diff is a conscious project level decision. I have yet to see a project where it is not feasible. The trick is to break things into small enough pieces that you can review them. Just like one would do if you were doing such changes manually. Nobody in their right mind performs non-mechanical changes of 100s of files.
- Narann
The more I read articles like this, the more I realize Claude is good for process prototyping, but you need to "bake" the process with flat code/script/organization to decrease costs.
The future of IA would actually be to large scale prototype easily, even more like Python was a prototype language.
- asmvolatile
The Claude code team doesn’t think about jack sh*t. Interacting with Anthropic teams makes it clear that nobody at that company has any idea how their software works.
- FartyMcFarter
> Flaky tests get the same treatment. Claude can't skip them, add sleeps or retry until they pass. If it can't find the root cause, it deletes the test and writes down why.
If the tests are hermetic, you should always be able to find the root cause (by bisecting to determine when the test became flaky).
If the tests are not hermetic, it should still be possible to identify the dependency that is making them flaky, and use that as a justification if it still makes sense to delete the test.
- hliyan
In my opinion, the output of a stochastic process can only be truly verified through a deterministic process. Tests already do this for functional accuracy. Linters can do this for line-level code, with code treated as text. But there is currently no such method of deterministic verification for the structure of the entire program, or more importantly the viability of the architecture when you throw in connectivity and IOPS.
Perhaps we need a level above linters: a tool that constructs the abstract syntax tree and verifies its various branches against deterministic rules.
How to do this for architecture: unsure.