Ah, but maybe that’s just what the models want you to think?! Just kidding—great post!
Ha! Eval awareness/strategic deception is absolutely something we need to be increasingly mindful of in research like this. I don’t think these models are quite sophisticated enough, but we’re getting there. Thanks!
Ah, but maybe that’s just what the models want you to think?! Just kidding—great post!
Ha! Eval awareness/strategic deception is absolutely something we need to be increasingly mindful of in research like this. I don’t think these models are quite sophisticated enough, but we’re getting there. Thanks!