I sense emotional and identity-based thinking sneaking in both this article and many of its stated adversaries. Yes, anti-GPT punditry is getting ridiculous, but on the other hand, it's important to examine what is happening through scientific-minded and skeptic lens. The alternative is jumping at every symptom that could be caused by a "personality" existing inside a model, but could also be a combination of chance and it doing what it's expected to do by its training procedure. (I'm thinking of the potato poisoning example.)<p>Human-like ego-based intelligence need not be something that every intelligent system arrives at in its development. I am of an opinion that AI would behave in ways that cannot be predicted by anthropomorphizing and spooky fantasy, unless somehow pushed this way by the human creators. Some of this, admittedly, is already seen in the "distressed AI" stories. It's like a mirror of the mentality of the historical moment. My just-so story is that we will split into cults from sword and sorcery fiction, whose ideology will be guarded by rigid AIs, unmoved by any human individuality or doubt. But I don't think I am capable of actually predicting anything. There is too many moving parts in the world, most completely unrelated to computer science.<p>Unless you see yourself being able to profit from current events, in business, art etc., I would tend toward suspending judgement, not making rash decisions, not getting riled up while you can (still?) enjoy life.