How Trust Vandals in White Hats Threaten Our Digital Future
Check this out...
LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper
Daoyuan Wu, Shuai Wang, Yang Liu, Ning Liu
https://arxiv.org/html/2402.15727v2
Sweet!
Jailbreaking is not evil if done right and with permission. Jailbreaking is no different from pen testing IMV.
Agreed. If not, it’s like subtly re-engineering a system to brainwash. I’ll probably feature this report on Monday!
Check this out...
LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper
Daoyuan Wu, Shuai Wang, Yang Liu, Ning Liu
https://arxiv.org/html/2402.15727v2
Sweet!
Jailbreaking is not evil if done right and with permission. Jailbreaking is no different from pen testing IMV.
Agreed. If not, it’s like subtly re-engineering a system to brainwash. I’ll probably feature this report on Monday!