diff --git a/autogollark.myco b/autogollark.myco
index 83cca3b..89808f9 100644
--- a/autogollark.myco
+++ b/autogollark.myco
@@ -25,7 +25,7 @@ Autogollark currently comprises the dataset, the search API server and the [[htt
 * {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. [[https://arxiv.org/abs/2505.15778]] [[https://arxiv.org/abs/2505.24864]] [[https://arxiv.org/abs/2509.06160]]
 * Unclear whether model could feasibly learn tool use "from scratch", so still need SFT pipeline.
 }
-* https://arxiv.org/abs/2310.04363 can improve sampling (roughly) //and// train for tool use.
+* https://arxiv.org/abs/2310.04363 can improve sampling (roughly) //and// train for tool use. However, it seems really annoying.
 }
 * {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.