Edit ‘autogollark’
This commit is contained in:
@@ -20,7 +20,9 @@ Autogollark currently comprises the dataset, the search API server and the [[htt
|
|||||||
* Use cheap classifier to evaluate when to respond.
|
* Use cheap classifier to evaluate when to respond.
|
||||||
* Should also allow unprompted messages somehow (polling, rerun after last message?).
|
* Should also allow unprompted messages somehow (polling, rerun after last message?).
|
||||||
}
|
}
|
||||||
* Tool capabilities (how to get the data? Examples in context only?!).
|
* {Tool capabilities (how to get the data? Examples in context only?!).
|
||||||
|
* Synthetic via instruct model.
|
||||||
|
}
|
||||||
* {Local finetune only? Would be more tonally consistent but dumber, I think.
|
* {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.
|
* Temporary bursts of hypercompetence enabled by powerful base model are a key feature. Small model is really repetitive.
|
||||||
* Can additionally finetune on "interesting" blog posts etc (ref https://x.com/QiaochuYuan/status/1913382597381767471).
|
* Can additionally finetune on "interesting" blog posts etc (ref https://x.com/QiaochuYuan/status/1913382597381767471).
|
||||||
|
|||||||
Reference in New Issue
Block a user