Comment on Someone got Gab's AI chatbot to show its instructions

• Silentiea@lemmy.blahaj.zone ⁨7⁩ ⁨months⁩ ago

  It would see it. I’m merely suggesting that it may not successfully notice it. LLMs process prompts by translating the words into vectors, and then the relationships between the words into vectors, and then the entire prompt into a single vector, and then uses that resulting vector to produce a result. The second LLM you’ve described will be trained such that the vectors for prompts that do contain the system prompt will point towards “true”, and the vectors for prompts that don’t still point towards “false”. But enough junk data in the form of unrelated words with unrelated relationships could cause the prompt vector to point too far from true towards false, basically. Just making a prompt that doesn’t have the vibes of one that contains the system prompt, as far as the second LLM is concerned

  source

  • sweng@programming.dev ⁨7⁩ ⁨months⁩ ago

    Ok, but now you have to craft a prompt for LLM 1 that

    1. Causes it to reveal the system prompt AND
    2. Outputs it in a format LLM 2 does not recognize AND
    3. The prompt is not recognized as suspicious by LLM 2.

    Fulfilling all 3 is orders of magnitude harder then fulfilling just the first.

    source

    • Silentiea@lemmy.blahaj.zone ⁨7⁩ ⁨months⁩ ago

      Maybe. But have you seen how easy it has been for people in this thread to get gab AI to reveal its system prompt? 10x harder or even 1000x isn’t going to stop it happening.

      source

      • sweng@programming.dev ⁨7⁩ ⁨months⁩ ago

        Oh please. If there is a new exploit now every 30 days or so, it would be every hundred years or so at 1000x.

        source

        • -> View More Comments