diff --git a/autogollark.myco b/autogollark.myco index f3df5fc..354f02b 100644 --- a/autogollark.myco +++ b/autogollark.myco @@ -22,6 +22,7 @@ Autogollark currently comprises the dataset, the search API server and the [[htt } * {Tool capabilities (how to get the data? Examples in context only?!). * Synthetic via instruct model. +* RL (also include reasoning, of course). } * {Local finetune only? Would be more tonally consistent but dumber, I think. * Temporary bursts of hypercompetence enabled by powerful base model are a key feature. Small model is really repetitive.