diff --git a/autogollark.myco b/autogollark.myco
index 22a460d..dff3dd9 100644
--- a/autogollark.myco
+++ b/autogollark.myco
@@ -38,7 +38,7 @@ Autogollark currently comprises the dataset, the search API server and the [[htt
 * MCTS over conversations with non-gollark simulacra? Should find //something// to use spare parallelism on local inference. Best-of-n? https://arxiv.org/abs/2505.10475
 * {Longer context, mux several channels.
 * {No obvious reason Autogollark can't train (and run inference!) on every channel simultaneously, with messages sorted by time and other non-Discord things (tool calls?) inline. Not good use of parallelism but does neatly solve the when-to-respond thing.
-* Context length issues, and subquadratic models are sort of bad, though maybe we can "upcycle" a midsized model to RWKV. This exists somewhere. Not sure of efficiency.
+* Context length issues, and subquadratic models are sort of bad, though maybe we can "upcycle" a midsized model to RWKV. This exists somewhere. Not sure of efficiency. Inference code will be awful.
 }
 }
 * Train on e.g. Discord Unveiled (local copy available).