An alignment assessment of the UK AISI cybertesting incident

19 points

1/21/1970

2 days ago

by olwmc

Comments

olwmc

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?

2 days ago

MisterMunchkin

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.

2 days ago

perching_aix

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

2 days ago

dvarahq

[flagged]

2 days ago