I think you’re thinking of training; goal drift during any sort of self-directed continuous learning with reflective CoT seems all too plausible. And self-directed continuous learning seems immanent, given how useful it is for humans and how simple versions already work.
I think you’re thinking of training; goal drift during any sort of self-directed continuous learning with reflective CoT seems all too plausible. And self-directed continuous learning seems immanent, given how useful it is for humans and how simple versions already work.