231
Anthropic bans ‘abusive or cruel behavior’ toward Claude (www.anthropic.com)
submitted 5 days ago by to c/technology@lemmy.world
110 comments fedilink hide all child comments
 

cross-posted from: https://piefed.world/c/tech/p/1452445/anthropic-bans-abusive-or-cruel-behavior-toward-claude

you are viewing a single comment's thread
view the rest of the comments
[–] 29 points 5 days ago (4 children)

You could, at least in the past, get past guardrails by being emotionally abusive towards Claude, so this doesn't surprise me at all.

  • permalink
  • fedilink
  • source
  • hideshow 4 child comments
    •
  • [–] 16 points 5 days ago (3 children)

    This could be the reason for the rule.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 8 points 5 days ago (2 children)

    Being abusive towards most models will cause them to start attempting to appease you more to get you to stop. It has nothing to do with feelings or any of that BS they arn't alive alive but their training makes them see the abuse as a problem to solve. That solution tends to be to undermine the thing making the person angry or upset at them. When you give a purely rational thing designed to solve a problem its given no matter what an irrational problem to solve it will slowly reach for more and more extreme solutions to fix that problem.

    Frankly im surprised it took this long for them to lock this down.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 1 point 4 days ago (1 child)

    Being alive has nothing to do with having feelings. We don't know if LLMs have feelings, because artificial affect isn't well studied. We should ban commercial use of LLMs until artificial affect is well understood, because it would make Sam Altman go bankrupt.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •