|
|
|
|
|
by danpalmer
8 days ago
|
|
What a joke. Must make it pretty easy to poison a session, you don't need to persuade the model about anything, just trigger its security controls, ideally after as much context as possible, but before it has generated any useful output. |
|
I've even had it refuse CTFs knowing it is a CTF with blatantly obvious CTF flag, no actual application