you are viewing a single comment's thread
view the rest of the comments
[–] 17 points 1 month ago (2 children)

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

  • source
  • hideshow 2 child comments
  • [–] 2 points 1 month ago* (1 child)

    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.

  • source
  • parent
  • hideshow 1 child comment