11 lines
738 B
Plaintext
11 lines
738 B
Plaintext
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
|
|
|
|
* reformat dataset to include longer-form conversation chunks for increased long-term coherence
|
|
* fix emoji/ping formatting
|
|
* writeable memory?
|
|
|
|
== Emergent capabilities
|
|
|
|
Autogollark has emergently acquired some abilities which were not intended in their design. |