osmarks/documentation
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Edit ‘autogollark’

Browse Source
This commit is contained in:
osmarks 2024-12-04 12:20:01 +00:00 committed by wikimind
parent dc8e6822db
commit f7f0601c0f
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
autogollark.myco
View File

@ -1,6 +1,6 @@
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 BF16 via Hyperbolic, [[AutoBotRobot]] code (though not presently its bot account) 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 BF16 via Hyperbolic, [[AutoBotRobot]] code (though not presently its bot account) 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 much [[safer]] than [[instruction-tuned]] systems optimized based on human feedback, as there is no [[optimization pressure]] for user engagement or syncophancy. Autogollark is much [[safer]] than [[instruction-tuned]] systems optimized based on human feedback, as there is no [[optimization pressure]] for user engagement or sycophancy.
== TODO == TODO