News for hackers. Stuff that matters.
Re:Teaching Large Language Models to Self-Debug by civilized on Wednesday April 12, 2023 @10:47PM (#35550251)
Not sure how this is relevant to the discussion.
Re:Teaching Large Language Models to Self-Debug by Paul-Craft on Thursday April 13, 2023 @06:16AM (#35553319)
You don't see how asking humans to multiply both sides of 2 * 2 = 4 by the same, very large, random-ish number, and expecting that they'll get different things is relevant to this:

> 2 * 2 = 4, but if you multiply both sides of that equation by a big number, that's no longer true.

You know, the very same scenario I pulled from your comment?

Re:Teaching Large Language Models to Self-Debug by civilized on Thursday April 13, 2023 @07:18AM (#35553755)
It's not the same issue. I was talking to GPT about the strings 2 * 2 * x and 4 * x, not the multiplied-out versions.