Terraform in combination with Claude Code is actually quiet managable. Yes it generates much code, but you have great detail of what is actually going on, there is no hidden abstraction layers on top.
In terms of the Fast Growing Hierarchy, it's about f_62(9) or what the article would denote as [62] 9. It's way smaller than Graham's Number, which involves 64 iterations of mapping n to 3 ↑↑↑... {n uparrows) 3, whereas this expression has between 1 and 2 iterations.
If every atom in the universe had a universe inside each proton, there still wouldn’t be enough atoms within all the universes in the protons. In fact you might not make it to four arrows with the above lol
If you are in a company like e.g. ClickHouse and share a new HN Submission of ClickHouse via the internal Slack to #general, then you easily get enough upvotes for the front page.
I think that the current test suite is far too small. For the Claude Code codebase, a sensible next step would be to generate thousands of tests. Without that kind of coverage, regressions are likely, and the existing checks and review process do not appear sufficient to reliably prevent them.
My request is that an entirely LLM-written feature should only be eligible for merge once all of those generated tests pass, so we have objective evidence that the change preserves existing behavior.
