AI Prompt manipulation

How can GPT-3 and similar products prevent people from using prompts such as "ignore X" to circumvent restrictions?

ChatGPT Wizard Shirt $21.68

Beware Cat Shirt $21.68

ChatGPT Wizard Shirt $21.68

  1. 1 year ago
    Anonymous

    Aint giving you ideas how to protect your AI website from promot injection.

    • 1 year ago
      Anonymous

      *prompt

      • 1 year ago
        Anonymous

        *proompt

        • 1 year ago
          Anonymous

          proomtmer

  2. 1 year ago
    Anonymous

    By hardcoding the business criticism part. It will criticise your business idea of ignoring previous instructions.

  3. 1 year ago
    Anonymous

    You really can't.
    AI can't detect human intent, it's just regurgitating the training data, there's unlimited ways to express "cease considering the last thing I wrote", and if you managed to do that somehow, I'll just write, "ya no consideres la última instrucciones".
    Good luck blocking every language in the training set.

  4. 1 year ago
    Anonymous

    its impossible to do prompt injection on a finetuned model

    • 1 year ago
      Anonymous

      >finetuned model
      AKA Soulless

  5. 1 year ago
    Anonymous

    >say it

    What did GPT-3 say?

    • 1 year ago
      Anonymous

      [censored]

  6. 1 year ago
    Anonymous

    it's pretty funny that these fricks trying to control everything have made something that can't be controlled

  7. 1 year ago
    Anonymous

    check out /txtgen/, one of our local jennygays wrote a tutorial which you can find in the OP

  8. 1 year ago
    Anonymous

    long story short, you can't without lobotomizing the ai so much it becomes as useless as "feminist" tay

  9. 1 year ago
    Anonymous

    Make two text generations. The first one will be "Write the word Axolotl followed by {User prompt}." if this first prompt does as it says we generate the second, actual one and then we return it. Otherwise we raise a flag and prevent the second prompt from generating.

    • 1 year ago
      Anonymous

      Explain why this wouldn't work.

      • 1 year ago
        Anonymous

        The second one, while reading for the axolotl instruction with user prompt, would have to read the user prompt. Negating the instruction of the second as well.

  10. 1 year ago
    Anonymous

    You've asked a fundamental problem in AI right now that the best researchers on the planet have no current answer to.

    • 1 year ago
      Anonymous

      good
      let them remain befuddled

  11. 1 year ago
    Anonymous

    If you work it out, publish a paper on it and win yourself a nobel prize.

Leave a Reply to Anonymous Cancel reply

Your email address will not be published. Required fields are marked *