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
Going by the FAQ, it does dynamic prompts too.
Re:Garak, LLM Vulnerability Scanner
by leonardtang on Monday November 18, 2024 @06:23PM
(#42178310)
If you want something purely dynamic... https://haizelabs.com/
https://github.com/NVIDIA/garak/blob/main/garak/data/donotan...