Link: https://ea.rna.nl/2024/04/12/microsoft-lays-the-limitations-of-chatgpt-and-friends-bare/
From R&A IT Strategy & Architecture
Microsoft researchers published a very informative paper on their pretty smart way to let GenAI do ‘bad’ things (i.e. ‘jailbreaking’). They actually set two aspects of the fundamental operation of these models against each other.
