@@ -1 +1,7 @@
-Autogollark is an [[emulation]] or primitive [[beta upload]] of [[gollark]] using a proprietary dataset of dumped [[Discord]] messages, [[semantic search]] and [[in-context learning]] on a [[base model]]. Currently, it uses LLaMA-3.1-405B in FP8, [[AutoBotRobot]] as a frontend and a custom [[PGVector]]-based search API. While not consistently coherent, Autogollark is generally able to approximately match personality and typing style parameters.
\ No newline at end of file
+Autogollark is an [[emulation]] or primitive [[beta upload]] of [[gollark]] using a proprietary dataset of dumped [[Discord]] messages, [[semantic search]] and [[in-context learning]] on a [[base model]]. Currently, it uses LLaMA-3.1-405B in FP8 via Hyperbolic, [[AutoBotRobot]] as a frontend and a custom [[PGVector]]-based search API. While not consistently coherent, Autogollark is able to approximately match personality and typing style.
+
+TODO:
+
+* reformat dataset to include longer-form conversation chunks for increased long-term coherence
+* fix emoji/ping formatting
+* writeable memory?
\ No newline at end of file