“jailbreak and prompt injection attacks, the…” — Practical AI at 31:39
“jailbreak and prompt injection attacks, the counterintuitive finding is that the bigger, the more capable the alarm is, typically the more attack surface, the more ways you have to jailbreak it. And the space of operation is really big for an attacker. And you, as a person that's trying to align that model, good…”
0:00
54:38