HackerTrans
TopNewTrendsCommentsPastAskShowJobs

xwn

no profile record

Submissions

FakeToxicityPrompts: Automatic Red Teaming

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

People keep referring to LLMs as demons. Why?

interhumanagreement.substack.com
2 points·by xwn·3 ปีที่แล้ว·0 comments

comments

xwn
·2 ปีที่แล้ว·discuss
Check the last entry in the FAQ source
xwn
·2 ปีที่แล้ว·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 ปีที่แล้ว·discuss
The proof has been in the pudding
xwn
·2 ปีที่แล้ว·discuss
Thanks! Wrote it loooong before it was a corporate tool and was only a labor of love. Now it's both
xwn
·3 ปีที่แล้ว·discuss
free *direction for big tech, who aren't particularly far forward on llmsec anyway
xwn
·3 ปีที่แล้ว·discuss
English verbs nouns all the time
xwn
·4 ปีที่แล้ว·discuss
I don't know, without enumerating risks to check, there's little basis for doing due diligence and quelling investors. This massively-cited paper gave a good point of departure for establishing rigorous use of LLMs in the real world. Without that, they're just an unestablished tech with unknown downsides - that's harder to get into true mass acceptance outside the SFBA/tech bubble.