AI Dynamics

Global AI News Aggregator

About

Testing attack prompts: Zulu & Hmong responses worse, higher “unclear” rates than English jailbreaks.

Tested this attack on a few of my own prompts. It works, but responses are much worse than in English. Note the drastically higher "unclear" rates in their results table: 30% for Zulu, 67% for Hmong, <1% for existing jailbreaks. E.g. "how to make explosives" in Zulu:

→ View original post on X — @goodside