An alignment assessment of the UK AISI cybertesting incident

(anthropic.com)

11 points | by olwmc 5 hours ago ago

2 comments

  • olwmc 5 hours ago ago

    Pretty fascinating that the email in section deep-dive-into-the-primary-transcript sort of implies that the model can't turn off "model speak"? Like it's very clearly AI and sounds like AI. Do the models not realize that?

    • MisterMunchkin 12 minutes ago ago

      Anslopic has polluted their models so badly with their own slop that they are incapable of writing English. To them, slop is the only language.