Some numbers from this experiment that broke my brain:
$10,600 vs. $1,300 for similar quality
Same 100% test score: 64k LOC vs under 10k
Peaking at 1,000 commits per second
We had a team of agents rebuild SQLite from its 835-page manual.
It created a replica in Rust which passed 100% of a held-out test suite.
Interestingly, cost varied 15x depending on which model mix we used.
显示更多
