Jailbreaking ChatGPT opens it up beyond its safeguards, letting it do and say almost anything. From insults to deliberate lies, here's how to jailbreak ChatGPT.
  • BradleyUffner@lemmy.worldEnglish
    2·
    8 months ago

    As long as the security for an LLM based AI is done “in-band” with the query, there will be ways to bypass it.