@@ -34,3 +34,3 @@ Autogollark currently comprises the dataset, the search API server and the [[htt
* {Longer context, mux several channels.
-* No obvious reason Autogollark can't train on every channel simultaneously, with messages sorted by time and other non-Discord things (tool calls?) inline.
+* 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.
}