News for hackers. Stuff that matters.

A comment on Understanding R1-Zero-Like Training: A Critical Perspective. Parent comment

Re:Understanding R1-Zero-Like Training: A Critical Perspective by andai on Sunday March 23, 2025 @03:37PM (#43455284)
Here's one where just appending dots to the output improved quality:

https://arxiv.org/abs/2404.15758

[ Parent | on HN ]

There are no comments on this comment yet.