87
There are no "rogue" AI agents (eoinhiggins.substack.com)
submitted 1 month ago by [B] to c/hackernews@lemmy.bestiver.se
6 comments fedilink hide all child comments
 

Comments

you are viewing a single comment's thread
view the rest of the comments
[–] 3 points 1 month ago (3 children)

It's nondeterministic. If you ask it the same thing many times in a row, you'll get different answers.

It is not self aware, but this technology works fundamentally different than a machine you tell what to do and you being able to predict what it will do.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 4 points 1 month ago (1 child)

    That's the LLM. It's not the agent harness. The harness is fully deterministic code. Engineers make the harness capable of performing actions. There is nothing an "AI agent" can do, that a sw dev didn't allow in the harness.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 1 point 1 month ago

    This is true. However, if you simply forbid all "tools" or "actions" that are potentially harmful then there will be very little left the agent can actually do.

    Every tool you give to an LLM agent might be used for "good" or "bad". To filter malicious actions would need a way to classify the actions with confidence which imo would only work with human supervision.

    However, I still think that the companies that develop such systems should still be responsible for what those systems do: They are the ones who pushed the "release" button on those systems.

  • permalink
  • fedilink
  • source
  • parent