• besselj@lemmy.ca
    link
    fedilink
    arrow-up
    14
    ·
    20 hours ago

    LLMs cannot differentiate between data and instructions. Such laws would be no better than the “guardrails” that major companies already try to use.

    • Pamasich@kbin.earth
      link
      fedilink
      arrow-up
      1
      ·
      3 hours ago

      It’s not like instructions are the only way to enforce rules on an LLM. Just have its output pass through a filter that checks it for the rules. If it passes, the response moves on to the user. If it fails the filter, the LLM gets prompted to try again.