Twelve years ago, a philosopher wrote a book called Superintelligence. Nick Bostrom was talking about the possibility of an AI that exceeded human intelligence — not the kind that learns how to play chess and then outplays a human because it’s predicting mathematical possibilities or the kind that predicts an outcome instantly with calculated stats, but an intelligence that can meaningfully outstrip humans.
Writing in 2014, Bostrom had no idea what was coming in terms of LLMs like ChatGPT, Gemini and Grok. But his training in ethics and his technical knowledge meant that he was able to fairly accurately predict the conversations we would have once they were developed.
