*The Rustification of Bun#
Rewriting 500,000 lines of Zig into another language would be a gargantuan undertaking if done by hand. “A rewrite in another language would take a small team of engineers a full year. It would mean freezing bugfixes, security fixes or feature development for that time,” Sumner wrote.
Instead, Sumner went with Claude. He spun up about 50 dynamic Claude Code workflows, reaching a peak of about 1,300 lines of code per minute and generating over a million lines of Rust code. The job took 11 days and cost about $165,000 at API pricing. Claude Fable did most of the heavy lifting.
What makes him think it’s unreviewed? Any AI process worth its salt has several review steps.
You should stop using words that clearly mean human cognitive activity, like “to review”, to describe what LLMs do.
You really think one person reviewed over a million lines of code in 11 days?
I think they mean “reviewed by AI”
The cops have investigated themselves and concluded that they did nothing wrong.
Yes.
AI code reviews can assert good patterns that’s baked into the training data, but it’s impossible for an LLM to understand the whole project. LLM code reviews can’t match a senior dev’s code reviews (unless VRAM becomes astronomically cheaper).