logoalt Hacker News

eruyesterday at 8:34 AM1 replyview on HN

Why do you need a small model to pick promising candidates? Why not a bigger one?

(And ideally you'd probably test first, or at least try to feed compiler errors back etc?)

Overall, I mostly agree.


Replies

yogthosyesterday at 1:20 PM

mostly an issue of speed and resource usage, if the model is too big then simply running the tests will be cheaper