Edit ‘autogollark’
This commit is contained in:
parent
dfabfc58fe
commit
e55f9f5632
@ -13,7 +13,9 @@ Autogollark is much [[safer]] than [[instruction-tuned]] systems optimized based
|
|||||||
* Due to general personality stability. Need finetune or similar.
|
* Due to general personality stability. Need finetune or similar.
|
||||||
* One proposal: use internal finetune to steer big model somehow.
|
* One proposal: use internal finetune to steer big model somehow.
|
||||||
}
|
}
|
||||||
* Increased autonomy (wrt. responses).
|
* {Increased autonomy (wrt. responses).
|
||||||
|
* Use cheap classifier to evaluate when to respond.
|
||||||
|
}
|
||||||
|
|
||||||
== Versions
|
== Versions
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user