An alignment assessment of the UK AISI cybertesting incident

(anthropic.com)

19 points | by olwmc a day ago ago

4 comments

  • olwmc a day 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 a day 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.

      • perching_aix a day ago

        sounds like it's not just these models that could really use a thesaurus

  • dvarahq a day ago

    [flagged]