Relevant further context: Gray Swan’s Cygnet-8B Llama finetune (which uses circuit breakers and probably other safety training too, and had impressive seeming 0.0 scores in some red teaming evals in the paper) was jailbroken in 3 hours: https://x.com/elder_plinius/status/1813670661270786137
Relevant further context: Gray Swan’s Cygnet-8B Llama finetune (which uses circuit breakers and probably other safety training too, and had impressive seeming 0.0 scores in some red teaming evals in the paper) was jailbroken in 3 hours: https://x.com/elder_plinius/status/1813670661270786137