vman512

That's my secret Captain, I'm always prompting

my advice: treat debugging as your core competency. When you get stuck, avoid asking for help until you've tried pretty hard to solve it yourself. If your any of your peers gets stuck with an interesting problem, go help if you have spare time

How sand people talk

Sounds right. The policy for rejection can depend on what you want - you might accept the top K highest probability tokens or top P probability mass. Or you can do something like importance sampling and probabilistically reject based on the ratio of likelihoods

It's pretty easy to get to O(N^(3/2)) at least, since that is sqrt(N)^3

Imagine an algorithm that re-arranges a list into a sqrt(N) by sqrt(N) grid, and does O(num_columns^2) work for each row.