News for hackers. Stuff that matters.

A comment on I hated writing–until I learned there's a science to it(2024). Parent comment

Re:I hated writing–until I learned there's a science to it(2... by embedding-shape on Friday May 29, 2026 @07:25AM (#48321741)
> How do LLMs do it? They don't learn by writing a lot they learn by reading a lot.

Literally they learn by both, training process is filled with "exercises" for the weights to be shaped by, not just "seeing" tokens :) At least the typical LLM that outputs tokens have to actually "practice" doing so.

[ Parent | on HN ]
Re:I hated writing–until I learned there's a science to it(2... by galaxyLogic on Friday May 29, 2026 @02:27PM (#48327293)
True. Just saying we learn not only by lots of trial and error, but also by trying to imitate others.
[ Parent | on HN ]