Comment Comment by deepsquirrelnet Ask an llm to pick a random number from 1-10. My money is on 7.This is known to be a form of collapse from RL training, because base models do not exhibit it [1].1. https://arxiv.org/abs/2505.00047 parent deepsquirrelnet 8 months ago
This is known to be a form of collapse from RL training, because base models do not exhibit it [1].
1. https://arxiv.org/abs/2505.00047