Thinking that you can design and control a super intelligent AI & make it safe and aligned with humanity's interests is the tech-bro equivalent of thinking the stripper likes you.
We trained a model to predict AI-written blog posts from structural features - and discovered the shape of slop.
On posts it had never seen, it told AI and human apart with 98% accuracy, getting only 19 of 1,740 wrong.
Paper and code: https://t.co/knexA6QVyE