Is GPT-3 (almost entirely) a purely deontological AI?Is GPT-3 (almost entirely) a purely deontological AI?Will GPT-n always be a purely deontological AI? (Where GPT-n is some large transformer based language model trained on next token predication.) Will GPT-n always be a purely deontological AI? (Where GPT-n is some large transformer based language model trained on next token predication.)
ryan_greenblatt comments on Framing approaches to alignment and the hard problem of AI cognition