LLMs don’t read the danger in requests if you use enough big words.
  • iAvicenna@lemmy.worldEnglish
    1·
    3 days 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.zipEnglish
      1·
      3 days ago

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