Discover the new "Deceptive Delight" technique for jailbreaking AI models, posing significant cybersecurity risks.
  • remi_pan@sh.itjust.worksEnglish
    1·
    5 days ago

    If the jailbreak is about enabling the LLM to tell you how to make explosives or drugs, this seems pointless, because I would never trust a IA so prone to hallucinations (and basicaly bad at science) in such dangerous process.