AI behavior is pretty easy to understand and predict if you view it from the lens of: they will shamelessly do any/everything possible to game whatever metric they are trained on. Because... that's how hill-climbing a metric looks. It's A/B enshittification taken to inscrutable heights.
They are trained on human feedback, so there is no other way this goes. Every bit of every response is pointed toward subversion of the assumed evaluator.
They are trained on human feedback, so there is no other way this goes. Every bit of every response is pointed toward subversion of the assumed evaluator.