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

Edit ‘autogollark’

Browse Source
This commit is contained in:
osmarks
2025-04-20 20:10:51 +00:00
committed by wikimind
parent d635336681
commit 596245c885
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
autogollark.myco
View File

@@ -22,7 +22,7 @@ Autogollark currently comprises the dataset, the search API server and the [[htt
}
* {Tool capabilities (how to get the data? Examples in context only?!).
* Synthetic via instruct model.
* RL (also include reasoning, of course).
* RL (also include reasoning, of course). Probably hard though (sparse rewards).
}
* {Local finetune only? Would be more tonally consistent but dumber, I think.
* Temporary bursts of hypercompetence enabled by powerful base model are a key feature. Small model is really repetitive.
@@ -30,7 +30,7 @@ Autogollark currently comprises the dataset, the search API server and the [[htt
* Decision theory training data (synthetic, probably) (ref https://arxiv.org/abs/2411.10588).
* Pending: XEROGRAPHIC BIFROST 3.
}
* MCTS over conversations with non-gollark simulacra? Should find //something// to use spare parallelism on local inference.
* MCTS over conversations with non-gollark simulacra? Should find //something// to use spare parallelism on local inference. Best-of-n?
* Longer context, mux several channels.
== Versions