An alignment assessment of the UK AISI cybertesting incident

Posted by olwmc 1 day ago

Comments

Comment by olwmc 1 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?

Comment by MisterMunchkin 1 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.

Comment by perching_aix 1 day ago

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

Comment by dvarahq 1 day ago

[flagged]