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

Edit ‘autogollark’

Browse Source
This commit is contained in:
osmarks
2025-12-24 18:22:49 +00:00
committed by wikimind
parent c12ef440db
commit bf8062da35
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
autogollark.myco
View File

@@ -38,7 +38,7 @@ Autogollark currently comprises the dataset, the search API server and the [[htt
* MCTS over conversations with non-gollark simulacra? Should find //something// to use spare parallelism on local inference. Best-of-n? https://arxiv.org/abs/2505.10475
* {Longer context, mux several channels.
* {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.
* Context length issues, and subquadratic models are sort of bad, though maybe we can "upcycle" a midsized model to RWKV. This exists somewhere. Not sure of efficiency.
* Context length issues, and subquadratic models are sort of bad, though maybe we can "upcycle" a midsized model to RWKV. This exists somewhere. Not sure of efficiency. Inference code will be awful.
}
}
* Train on e.g. Discord Unveiled (local copy available).