• meteokr@community.adiquaints.moe
    link
    fedilink
    arrow-up
    5
    ·
    7 months ago

    Would the red team use a prompt to instruct the second LLM to comply? I believe the HordeAI system uses this type of mitigation to avoid generating images that are harmful, by flagging them with a first pass LLM. Layers of LLMs would only delay an attack vector like this, if there’s no human verification of flagged content.

      • meteokr@community.adiquaints.moe
        link
        fedilink
        arrow-up
        1
        ·
        7 months ago

        I don’t think that can exist within the current understanding of LLMs. They are probabilistic, so nothing is 0% or 100%, and slight changes to input dramatically change the output.