AI Dynamics

Global AI News Aggregator

About

PromptSonar Limitations: Non-English Jailbreaks Detection Gaps

The README says that it doesn't handle "Non-English jailbreaks" which I think means it's of very little value https://
github.com/meghal86/promp
tsonar?tab=readme-ov-file#known-limitations–v010
… Also it appears to mainly work using regular expression? That doesn't look robust to me at all

→ View original post on X — @simonw