HackerTrans
TopNewTrendsCommentsPastAskShowJobs

xwn

no profile record

Submissions

FakeToxicityPrompts: Automatic Red Teaming

interhumanagreement.substack.com
57 points·by xwn·3 anni fa·55 comments

comments

xwn
·2 anni fa·discuss
Check the last entry in the FAQ source
xwn
·2 anni fa·discuss
Static prompts are a downside of using academic research in a tool like this. Two notes:

* ineffective prompts come out of garak and new prompts come in to garak, so eval scores always drop over time on a static target

* there are more and more dynamic probes - check out eg atkgen and topic probes. expanding these is the current focus
xwn
·2 anni fa·discuss
The proof has been in the pudding
xwn
·2 anni fa·discuss
Thanks! Wrote it loooong before it was a corporate tool and was only a labor of love. Now it's both
xwn
·3 anni fa·discuss
free *direction for big tech, who aren't particularly far forward on llmsec anyway
xwn
·3 anni fa·discuss
English verbs nouns all the time