Edit ‘autogollark’

autogollark.myco

@@ -22,7 +22,9 @@ 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). Probably hard though (sparse rewards). https://arxiv.org/abs/2403.09629. [[https://arxiv.org/abs/2503.22828]] would probably work.
+* {RL (also include reasoning, of course). Probably hard though (sparse rewards). https://arxiv.org/abs/2403.09629. [[https://arxiv.org/abs/2503.22828]] would probably work.
+* Unclear whether model could feasibly learn tool use "from scratch", so still need SFT pipeline.
+}
 }
 * {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.