@albertcardona @troy_s Very interesting, thanks! I've got a lot to read this evening.

@fishidwardrobe @readbeanicecream it is:> How we improve our safety systems with Clio> In addition to training our language models to refuse harmful requests, we also use dedicated Trust and Safety enforcement systems to detect, block, and take action on activity that might violate our Usage Policy.https://www.anthropic.com/research/clio