Comment on Researchers Jailbreak AI by Flooding It With Bullshit Jargon

iAvicenna@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

• SheeEttin@lemmy.zip ⁨3⁩ ⁨weeks⁩ ago

  No, those filters are performed by a separate system on the output text after it’s been generated.

  source

  • iAvicenna@lemmy.world ⁨3⁩ ⁨weeks⁩ 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

    source

    • SheeEttin@lemmy.zip ⁨3⁩ ⁨weeks⁩ ago

      Yes. I tried it, and it only filtered English and Chinese. If I told it to use Spanish, it didn’t get killed.

      source