Sankar Harilal

@sankar_harilal

@uwcse

following
followers

Paper author says reinforcement learning can teach language models new capabilities

The author says toy experiments also show that post-training with random rewards does not improve capabilities except under very particular circumstances.

3 Sources, 38d ago, first seen 38d ago

Sankar Harilal (@sankar_harilal) · Digg

Featured in

Paper author says reinforcement learning can teach language models new capabilities

Featured in

Paper author says reinforcement learning can teach language models new capabilities