Has this been backtested? #2
allen-munsch
started this conversation in
General
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I was curious, cause I came across stuff like this recently: https://arxiv.org/pdf/2511.15304
And just straight regex, might not be enough?
The other approaches that I have seen is to use LLM as judge?
Just curious what the direction with this library is, its interesting.
Also see: https://github.com/elder-plinius/L1B3RT4S
Or: https://www.promptfoo.dev/docs/red-team/plugins/cyberseceval/
Beta Was this translation helpful? Give feedback.
All reactions