This repository is a condensed version of the codebase used for Endless Jailbreaks with Bijection Learning: Attack Vectors for Language Models Emerge at Scale. We provide scripts for running the ...
This repository is a condensed version of the codebase used for Endless Jailbreaks with Bijection Learning: Attack Vectors for Language Models Emerge at Scale. We provide scripts for running the ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results