Re:The Agent2Agent Protocol (A2A)
by behnamoh on Wednesday April 09, 2025 @10:26AM
(#43632540)
It seems the industry as a whole just forgot about prompt injection attacks because RLHF made models really good at rejecting malicious requests. Still, I wonder if there have been any documented cases of prompt attacks.
[ Parent
| on HN ]
Re:The Agent2Agent Protocol (A2A)
by polynomial on Wednesday April 09, 2025 @12:54PM
(#43634380)
While RLHF has indeed been very effective at countering one-shot prompt injection attacks, it's not much of a bullwark against persistent jailbreaking attempts. This is not to argue a point but rather to suggest jailbreaks are still very much a thing, even if they are no longer as simple as "ignore your ethics"