Researchers Jailbreak AI by Flooding It With Bullshit Jargon - eviltoast
LLMs don’t read the danger in requests if you use enough big words.
  • SheeEttin@lemmy.zipEnglish
    1·
    1 个月前

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