Edit ‘autogollark’

This commit is contained in:
osmarks 2024-10-10 09:11:12 +00:00 committed by wikimind
parent 580cff6382
commit b35fe1b23d

View File

@ -1,7 +1,11 @@
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 base 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.
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, the system uses LLaMA-3.1-405B base 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:
== TODO
* reformat dataset to include longer-form conversation chunks for increased long-term coherence
* fix emoji/ping formatting
* writeable memory?
* writeable memory?
== Emergent capabilities
Autogollark has emergently acquired some abilities which were not intended in their design.