Comment on Researchers Jailbreak AI by Flooding It With Bullshit Jargon
SheeEttin@lemmy.zip 2 days agoNo, those filters are performed by a separate system on the output text after it’s been generated.
Comment on Researchers Jailbreak AI by Flooding It With Bullshit Jargon
SheeEttin@lemmy.zip 2 days agoNo, those filters are performed by a separate system on the output text after it’s been generated.
iAvicenna@lemmy.world 1 day ago
makes sense though I wonder if you can also tweak the initial prompt so that the output is also full of jargon so that output filter also misses the context
SheeEttin@lemmy.zip 1 day ago
Yes. I tried it, and it only filtered English and Chinese. If I told it to use Spanish, it didn’t get killed.