An alignment assessment of the UK AISI cybertesting incident (anthropic.com) 1 points by olwmc 6d ago ↗ HN
[–] olwmc 6d 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 6d 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 6d ago ↗ [delayed]
[–] MisterMunchkin 6d 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 6d ago ↗ [delayed]
4 comments
[ 6.5 ms ] story [ 123 ms ] thread