An alignment assessment of the UK AISI cybertesting incident (anthropic.com)19 points by olwmc 1 day ago
olwmc 1 day agoPretty 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 1 day agoAnslopic 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 1 day agosounds like it's not just these models that could really use a thesaurus
MisterMunchkin 1 day agoAnslopic 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 1 day agosounds like it's not just these models that could really use a thesaurus
olwmc 1 day ago
MisterMunchkin 1 day ago
perching_aix 1 day ago