xwn

vor 2 Jahrendiscuss

Check the last entry in the FAQ source

vor 2 Jahrendiscuss

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

vor 2 Jahrendiscuss

The proof has been in the pudding

xwn

vor 2 Jahrendiscuss

Thanks! Wrote it loooong before it was a corporate tool and was only a labor of love. Now it's both

xwn

vor 3 Jahrendiscuss

free *direction for big tech, who aren't particularly far forward on llmsec anyway

xwn

vor 3 Jahrendiscuss

English verbs nouns all the time

xwn

vor 4 Jahrendiscuss

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.

Submissions

FakeToxicityPrompts: Automatic Red Teaming

People keep referring to LLMs as demons. Why?

comments