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

Edit ‘autogollark’

Browse Source
This commit is contained in:
osmarks 2025-01-21 21:09:03 +00:00 committed by wikimind
parent 069d294af2
commit 32e0d7904b
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
autogollark.myco
View File

@ -12,6 +12,7 @@ Autogollark is much [[safer]] than [[instruction-tuned]] systems optimized based
* {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. 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. * 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.
* Is GCG code salvageable? NanoGCG, maybe.
} }
* {Increased autonomy (wrt. responses). * {Increased autonomy (wrt. responses).
* Use cheap classifier to evaluate when to respond. * Use cheap classifier to evaluate when to respond.