cannot be solved for static pre-trained models, it remains to be seen whether there are other model architectures that can resist jailbreaking the way humans are resistant to brainwashing (which might mean improving their ability to resist such attempts)
tachikoma
Apparently the government is against moving the AI frontier until jailbreaks are solved. For the uninitiated, jailbreaks have existed since the beginning and as far as we know so far, cannot be solved. They are asking for technical alignment and pretending it’s a casual bug patch.
