Edit ‘autogollark’
This commit is contained in:
parent
e50db21dee
commit
d8fc0ecc80
@ -11,7 +11,7 @@ Autogollark is much [[safer]] than [[instruction-tuned]] systems optimized based
|
|||||||
* Writeable memory?
|
* Writeable memory?
|
||||||
* {Fix lowercasing issue.
|
* {Fix lowercasing issue.
|
||||||
* 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. Possibly: use its likelihood (prefill-only) to evaluate goodness of big model output wrt. gollark personality, and if it is too bad then use finetune directly.
|
||||||
}
|
}
|
||||||
* {Increased autonomy (wrt. responses).
|
* {Increased autonomy (wrt. responses).
|
||||||
* Use cheap classifier to evaluate when to respond.
|
* Use cheap classifier to evaluate when to respond.
|
||||||
|
Loading…
Reference in New Issue
Block a user