News for hackers. Stuff that matters.
Re:Can LLMs write better code if you keep asking them to "wr... by dgacmu on Friday January 03, 2025 @11:06AM (#42586790)
But what's interesting about this is that there's a tradeoff in the total computation performed by the "fully parallelized" version of this and a sequential one. Without the user knowing this, it's kind of impossible to get the optimization you want: Do you want a minimum work solution or a minimum wall-clock-time solution?

If you want a better fully parallelized one, you do this:

Repeat a few times in exponential progression on k:

Process, in parallel, the first k entries in the list (let's start with 1000). Find the min and max whose digit sums = 30.

In parallel, filter the remaining list to eliminate entries that would not improve upon the min/max thus found.

k *= 10 and repeat until done.

I would wager against the LLM identifying this solution without prompting from the user (or reading this comment).

There are no comments on this comment yet.