Comment by ZZ Si (zhangzhang-si) on On the Importance of Open Sourcing Reward Models · 2023-03-02T21:29:56.700Z · LW · GW

I think this is a fair point that an open reward function is subject to "SEO" efforts to game it. But, how about a  "training" reward function that is open, and a "test" reward function that is hidden?

I would love to know what are some other OSS efforts on reward function (I do follow Carper's development on RF), and love to contribute.

Comment by ZZ Si (zhangzhang-si) on On the Importance of Open Sourcing Reward Models · 2023-03-02T21:29:11.464Z · LW · GW